lshqqytiger / stable-diffusion-webui-directml Goto Github PK

This project forked from automatic1111/stable-diffusion-webui

Stable Diffusion web UI

License: GNU Affero General Public License v3.0

Shell 0.58% JavaScript 7.68% Python 88.40% CSS 1.95% HTML 1.28% Batchfile 0.11%

ai ai-art amd amdgpu deep-learning directml hip image-generation image2image img2img radeon rocm stable-diffusion text2image torch txt2img web

stable-diffusion-webui-directml's Introduction

Stable Diffusion web UI for AMDGPUs

A web interface for Stable Diffusion, implemented using Gradio library.

Features

Detailed feature showcase with images:

Original txt2img and img2img modes
One click install and run script (but you still must install python and git)
Outpainting
Inpainting
Color Sketch
Prompt Matrix
Stable Diffusion Upscale
Attention, specify parts of text that the model should pay more attention to
- a man in a ((tuxedo)) - will pay more attention to tuxedo
- a man in a (tuxedo:1.21) - alternative syntax
- select text and press Ctrl+Up or Ctrl+Down (or Command+Up or Command+Down if you're on a MacOS) to automatically adjust attention to selected text (code contributed by anonymous user)
Loopback, run img2img processing multiple times
X/Y/Z plot, a way to draw a 3 dimensional plot of images with different parameters
Textual Inversion
- have as many embeddings as you want and use any names you like for them
- use multiple embeddings with different numbers of vectors per token
- works with half precision floating point numbers
- train embeddings on 8GB (also reports of 6GB working)
Extras tab with:
- GFPGAN, neural network that fixes faces
- CodeFormer, face restoration tool as an alternative to GFPGAN
- RealESRGAN, neural network upscaler
- ESRGAN, neural network upscaler with a lot of third party models
- SwinIR and Swin2SR (see here), neural network upscalers
- LDSR, Latent diffusion super resolution upscaling
Resizing aspect ratio options
Sampling method selection
- Adjust sampler eta values (noise multiplier)
- More advanced noise setting options
Interrupt processing at any time
4GB video card support (also reports of 2GB working)
Correct seeds for batches
Live prompt token length validation
Generation parameters
- parameters you used to generate images are saved with that image
- in PNG chunks for PNG, in EXIF for JPEG
- can drag the image to PNG info tab to restore generation parameters and automatically copy them into UI
- can be disabled in settings
- drag and drop an image/text-parameters to promptbox
Read Generation Parameters Button, loads parameters in promptbox to UI
Settings page
Running arbitrary python code from UI (must run with --allow-code to enable)
Mouseover hints for most UI elements
Possible to change defaults/mix/max/step values for UI elements via text config
Tiling support, a checkbox to create images that can be tiled like textures
Progress bar and live image generation preview
- Can use a separate neural network to produce previews with almost none VRAM or compute requirement
Negative prompt, an extra text field that allows you to list what you don't want to see in generated image
Styles, a way to save part of prompt and easily apply them via dropdown later
Variations, a way to generate same image but with tiny differences
Seed resizing, a way to generate same image but at slightly different resolution
CLIP interrogator, a button that tries to guess prompt from an image
Prompt Editing, a way to change prompt mid-generation, say to start making a watermelon and switch to anime girl midway
Batch Processing, process a group of files using img2img
Img2img Alternative, reverse Euler method of cross attention control
Highres Fix, a convenience option to produce high resolution pictures in one click without usual distortions
Reloading checkpoints on the fly
Checkpoint Merger, a tab that allows you to merge up to 3 checkpoints into one
Custom scripts with many extensions from community
Composable-Diffusion, a way to use multiple prompts at once
- separate prompts using uppercase AND
- also supports weights for prompts: a cat :1.2 AND a dog AND a penguin :2.2
No token limit for prompts (original stable diffusion lets you use up to 75 tokens)
DeepDanbooru integration, creates danbooru style tags for anime prompts
xformers, major speed increase for select cards: (add --xformers to commandline args)
via extension: History tab: view, direct and delete images conveniently within the UI
Generate forever option
Training tab
- hypernetworks and embeddings options
- Preprocessing images: cropping, mirroring, autotagging using BLIP or deepdanbooru (for anime)
Clip skip
Hypernetworks
Loras (same as Hypernetworks but more pretty)
A separate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt
Can select to load a different VAE from settings screen
Estimated completion time in progress bar
API
Support for dedicated inpainting model by RunwayML
via extension: Aesthetic Gradients, a way to generate images with a specific aesthetic by using clip images embeds (implementation of https://github.com/vicgalle/stable-diffusion-aesthetic-gradients)
Stable Diffusion 2.0 support - see wiki for instructions
Alt-Diffusion support - see wiki for instructions
Now without any bad letters!
Load checkpoints in safetensors format
Eased resolution restriction: generated image's dimensions must be a multiple of 8 rather than 64
Now with a license!
Reorder elements in the UI from settings screen
Segmind Stable Diffusion support

What's different from upstream repo?

DirectML support for every GPUs that support DirectX 12 API.

ZLUDA support for AMDGPUs.

--use-directml: Use DirectML as a torch backend.
--use-zluda: Use ZLUDA as a torch backend.
Support ONNX Runtime.
Support Olive model optimization.

Installation and Running

Make sure the required dependencies are met and follow the instructions available for:

NVidia (recommended)
AMD GPUs.
Intel CPUs, Intel GPUs (both integrated and discrete) (external wiki page)
Ascend NPUs (external wiki page)

Alternatively, use online services (like Google Colab):

List of Online Services

Installation on Windows 10/11 with NVidia-GPUs using release package

Download sd.webui.zip from v1.0.0-pre and extract its contents.
Run update.bat.
Run run.bat.

For more details see Install-and-Run-on-NVidia-GPUs

Automatic Installation on Windows

Install Python 3.10.6 (Newer version of Python does not support torch), checking "Add Python to PATH".
Install git.
Download the stable-diffusion-webui-amdgpu repository, for example by running git clone https://github.com/lshqqytiger/stable-diffusion-webui-amdgpu.git.
Run webui-user.bat from Windows Explorer as normal, non-administrator, user.

Automatic Installation on Linux

Install the dependencies:

# Debian-based:
sudo apt install wget git python3 python3-venv libgl1 libglib2.0-0
# Red Hat-based:
sudo dnf install wget git python3 gperftools-libs libglvnd-glx
# openSUSE-based:
sudo zypper install wget git python3 libtcmalloc4 libglvnd
# Arch-based:
sudo pacman -S wget git python3

If your system is very new, you need to install python3.11 or python3.10:

# Ubuntu 24.04
sudo add-apt-repository ppa:deadsnakes/ppa
sudo apt update
sudo apt install python3.11

# Manjaro/Arch
sudo pacman -S yay
yay -S python311 # do not confuse with python3.11 package

# Only for 3.11
# Then set up env variable in launch script
export python_cmd="python3.11"
# or in webui-user.sh
python_cmd="python3.11"

Navigate to the directory you would like the webui to be installed and execute the following command:

wget -q https://raw.githubusercontent.com/lshqqytiger/stable-diffusion-webui-amdgpu/master/webui.sh

Or just clone the repo wherever you want:

git clone https://github.com/lshqqytiger/stable-diffusion-webui-amdgpu

Run webui.sh.
Check webui-user.sh for options.

Installation on Apple Silicon

Find the instructions here.

Contributing

Here's how to add code to this repo: Contributing

Documentation

The documentation was moved from this README over to the project's wiki.

For the purposes of getting Google and other search engines to crawl the wiki, here's a link to the (not for humans) crawlable wiki.

Credits

Licenses for borrowed code can be found in Settings -> Licenses screen, and also in html/licenses.html file.

Stable Diffusion - https://github.com/Stability-AI/stablediffusion, https://github.com/CompVis/taming-transformers, https://github.com/mcmonkey4eva/sd3-ref
k-diffusion - https://github.com/crowsonkb/k-diffusion.git
Spandrel - https://github.com/chaiNNer-org/spandrel implementing
- GFPGAN - https://github.com/TencentARC/GFPGAN.git
- CodeFormer - https://github.com/sczhou/CodeFormer
- ESRGAN - https://github.com/xinntao/ESRGAN
- SwinIR - https://github.com/JingyunLiang/SwinIR
- Swin2SR - https://github.com/mv-lab/swin2sr
LDSR - https://github.com/Hafiidz/latent-diffusion
MiDaS - https://github.com/isl-org/MiDaS
Ideas for optimizations - https://github.com/basujindal/stable-diffusion
Cross Attention layer optimization - Doggettx - https://github.com/Doggettx/stable-diffusion, original idea for prompt editing.
Cross Attention layer optimization - InvokeAI, lstein - https://github.com/invoke-ai/InvokeAI (originally http://github.com/lstein/stable-diffusion)
Sub-quadratic Cross Attention layer optimization - Alex Birch (Birch-san/diffusers#1), Amin Rezaei (https://github.com/AminRezaei0x443/memory-efficient-attention)
Textual Inversion - Rinon Gal - https://github.com/rinongal/textual_inversion (we're not using his code, but we are using his ideas).
Idea for SD upscale - https://github.com/jquesnelle/txt2imghd
Noise generation for outpainting mk2 - https://github.com/parlance-zz/g-diffuser-bot
CLIP interrogator idea and borrowing some code - https://github.com/pharmapsychotic/clip-interrogator
Idea for Composable Diffusion - https://github.com/energy-based-model/Compositional-Visual-Generation-with-Composable-Diffusion-Models-PyTorch
xformers - https://github.com/facebookresearch/xformers
DeepDanbooru - interrogator for anime diffusers https://github.com/KichangKim/DeepDanbooru
Sampling in float32 precision from a float16 UNet - marunine for the idea, Birch-san for the example Diffusers implementation (https://github.com/Birch-san/diffusers-play/tree/92feee6)
Instruct pix2pix - Tim Brooks (star), Aleksander Holynski (star), Alexei A. Efros (no star) - https://github.com/timothybrooks/instruct-pix2pix
Security advice - RyotaK
UniPC sampler - Wenliang Zhao - https://github.com/wl-zhao/UniPC
TAESD - Ollin Boer Bohan - https://github.com/madebyollin/taesd
LyCORIS - KohakuBlueleaf
Restart sampling - lambertae - https://github.com/Newbeeer/diffusion_restart_sampling
Hypertile - tfernd - https://github.com/tfernd/HyperTile
Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
Olive - https://github.com/microsoft/Olive
kohya-ss/sd-scripts - https://github.com/kohya-ss/sd-scripts
(You)

stable-diffusion-webui-directml's People

Contributors

Stargazers

Watchers

Forkers

qwerkilo hjhsjywanan xchange colapumpkinpie ttntech fenglui xavierlicorish hydrz huihuidashuaibi gentoolman 280322918 monylots minecraft123-uname chenxqiyu borgsid hejunv onetapv4 demonxxx zouston cpro222 nathan-dm hanruochen1 yuanhao1026 lamqhoang yang0011102 iamleon121 grftsol wujun4code donglinyin free-hat00 lizhibboy kasteldel terrafaster flying1989 vox1981 plzspara demifox10 olvasdnight shbonny samobernik yuan199696 th-neu hexenisaliveagain inntzero acup1 uynaib wenchui shadowembrace sc32024826 risharde cue-vi tangcan1600 arahaan gaelicthunder doulammeng oscartorres9 swastikgorai lonelam picotech1984 jfontestad holmes-jack etleredelgard yingyue5 tamachi77 moonjob liby0102 robonxt swjtuhyq hysondre illusiveman196 inomix8 mdnicker kocwei aserafin94 4geeksacademy jackbuls fanlen davinwang ssgmr life1are2bennett3it4want5 blaz-nanotek marktsai0316 ramstorage biosnod calberdrift92 kazssym rasyidkaromi prisesoul zzy64311 ponderingken mastermach50 cocktailpeanutlabs enjoyzed jackiliffe ghtyn darkdhamon alyabunker emily-li djonce obiyomida

stable-diffusion-webui-directml's Issues

[Bug]: NotImplementedError: No operator found for `memory_efficient_attention_forward` with inputs:

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

I tried to generate my first prompt using stable diffusion v2.1 base and got the error mentioned.

Steps to reproduce the problem

Go to ....
Press ....
...

What should have happened?

Image should have been generated

Commit where the problem happens

AUTOMATIC1111@a0f4cd6

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

I use --xformers, but same happens if I don't.

List of extensions

Console logs

venv "C:\Users\Fanis\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash: a0f4cd6fdd2b7ef3e2b666694f1a1ca13ee17066
Installing requirements for Web UI
Launching Web UI with arguments: --xformers
Warning: experimental graphic memory optimizations are disabled due to gpu vendor.
Disabled experimental graphic memory optimizations.
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:
    PyTorch 1.13.1+cu117 with CUDA 1107 (you have 1.13.1+cpu)
    Python  3.10.9 (you have 3.10.6)
  Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)
  Memory-efficient attention, SwiGLU, sparse and more won't be available.
  Set XFORMERS_MORE_DETAILS=1 for more details
Loading weights [88ecb78256] from C:\Users\Φάνης\stable-diffusion-webui-directml\models\Stable-diffusion\v2-1_512-ema-pruned.ckpt
Creating model from config: C:\Users\Φάνης\stable-diffusion-webui-directml\models\Stable-diffusion\v2-1_512-ema-pruned.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 865.91 M params.
Applying cross attention optimization (InvokeAI).
Textual inversion embeddings loaded(0):
Model loaded in 142.4s (load weights from disk: 26.4s, load config: 0.2s, create model: 6.8s, apply weights to model: 76.3s, apply half(): 28.4s, move model to device: 3.9s, hijack: 0.1s, load textual inversion embeddings: 0.2s).
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
100%|████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:08<00:00,  4.06s/it]
Error completing request█████████████████████████████████████████████████████████████████| 2/2 [00:02<00:00,  1.11s/it]
Arguments: ('task(n53zcn2fd1sam6h)', 'a cat', '', [], 2, 0, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0) {}
Traceback (most recent call last):
  File "C:\Users\Φάνης\stable-diffusion-webui-directml\modules\call_queue.py", line 56, in f
    res = list(func(*args, **kwargs))
  File "C:\Users\Φάνης\stable-diffusion-webui-directml\modules\call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "C:\Users\Φάνης\stable-diffusion-webui-directml\modules\txt2img.py", line 56, in txt2img
    processed = process_images(p)
  File "C:\Users\Φάνης\stable-diffusion-webui-directml\modules\processing.py", line 486, in process_images
    res = process_images_inner(p)
  File "C:\Users\Φάνης\stable-diffusion-webui-directml\modules\processing.py", line 630, in process_images_inner
    x_samples_ddim = [decode_first_stage(p.sd_model, samples_ddim[i:i+1].to(dtype=devices.dtype_vae))[0].cpu() for i in range(samples_ddim.size(0))]
  File "C:\Users\Φάνης\stable-diffusion-webui-directml\modules\processing.py", line 630, in <listcomp>
    x_samples_ddim = [decode_first_stage(p.sd_model, samples_ddim[i:i+1].to(dtype=devices.dtype_vae))[0].cpu() for i in range(samples_ddim.size(0))]
  File "C:\Users\Φάνης\stable-diffusion-webui-directml\modules\processing.py", line 423, in decode_first_stage
    x = model.decode_first_stage(x)
  File "C:\Users\Fanis\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 17, in <lambda>
    setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
  File "C:\Users\Fanis\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 28, in __call__
    return self.__orig_func(*args, **kwargs)
  File "C:\Users\Fanis\stable-diffusion-webui-directml\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "C:\Users\Φάνης\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 826, in decode_first_stage
    return self.first_stage_model.decode(z)
  File "C:\Users\Φάνης\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\autoencoder.py", line 90, in decode
    dec = self.decoder(z)
  File "C:\Users\Fanis\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\Users\Φάνης\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\model.py", line 631, in forward
    h = self.mid.attn_1(h)
  File "C:\Users\Fanis\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\Users\Φάνης\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\model.py", line 258, in forward
    out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=None, op=self.attention_op)
  File "C:\Users\Fanis\stable-diffusion-webui-directml\venv\lib\site-packages\xformers\ops\fmha\__init__.py", line 197, in memory_efficient_attention
    return _memory_efficient_attention(
  File "C:\Users\Fanis\stable-diffusion-webui-directml\venv\lib\site-packages\xformers\ops\fmha\__init__.py", line 293, in _memory_efficient_attention
    return _memory_efficient_attention_forward(
  File "C:\Users\Fanis\stable-diffusion-webui-directml\venv\lib\site-packages\xformers\ops\fmha\__init__.py", line 309, in _memory_efficient_attention_forward
    op = _dispatch_fw(inp)
  File "C:\Users\Fanis\stable-diffusion-webui-directml\venv\lib\site-packages\xformers\ops\fmha\dispatch.py", line 95, in _dispatch_fw
    return _run_priority_list(
  File "C:\Users\Fanis\stable-diffusion-webui-directml\venv\lib\site-packages\xformers\ops\fmha\dispatch.py", line 70, in _run_priority_list
    raise NotImplementedError(msg)
NotImplementedError: No operator found for `memory_efficient_attention_forward` with inputs:
     query       : shape=(1, 4096, 1, 512) (torch.float16)
     key         : shape=(1, 4096, 1, 512) (torch.float16)
     value       : shape=(1, 4096, 1, 512) (torch.float16)
     attn_bias   : <class 'NoneType'>

Additional information

I try to run stable diffusion 2.1 with a RX 580 gpu card. Is it supposed to run only in a Nvidia card?

It says in installation guide for amd that it is currently in testing for windows. Does this mean that it only works with rocm in linux?

[Bug]: restore faces error

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

Tick restore faces ,Prompt for errors in the last step.

Error completing request
TypeError: 'NoneType' object is not subscriptable

Steps to reproduce the problem

Tick restore faces ,
prompt ' boy face '
generate
4.last step error

What should have happened?

finish

Commit where the problem happens

c888249

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

--opt-sub-quad-attention --precision full --no-half --medvram --no-half-vae --share --opt-split-attention-v1 --disable-nan-check

List of extensions

Console logs

ebui-directml\venv\Scripts\Python.exe"
Python 3.10.10 (tags/v3.10.10:aad5f6a, Feb  7 2023, 17:20:36) [MSC v.1929 64 bit (AMD64)]
Commit hash: c88824995d87be36a62b110dd509ff7ccb6eeaa2
Installing requirements for Web UI
Launching Web UI with arguments: --opt-sub-quad-attention --precision full --no-half --medvram --no-half-vae --share --opt-split-attention-v1 --disable-nan-check
Warning: experimental graphic memory optimization is disabled due to gpu vendor. Currently this optimization is only available for AMDGPUs.
Disabled experimental graphic memory optimizations.
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
Loading weights [7234b76e42] from D:\SD\stable-diffusion-webui-directml\models\Stable-diffusion\Chilloutmix-Ni.safetensors
Creating model from config: D:\SD\stable-diffusion-webui-directml\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying sub-quadratic cross attention optimization.
Textual inversion embeddings loaded(1): ulzzang-6500-v1.1
Model loaded in 1.3s (create model: 0.5s, apply weights to model: 0.7s).
Running on local URL:  http://127.0.0.1:7860
Running on public URL: https://xxxxxxxxxxxxxx.gradio.live

This share link expires in 72 hours. For free permanent hosting and GPU upgrades (NEW!), check out Spaces: https://huggingface.co/spaces
100%|█████████████████████████████████████| 20/20 [00:07<00:00,  2.63it/s]
Error verifying pickled file from D:\SD\stable-diffusion-webui-directml\models\Codeformer\tmp1eiusxvd:
Traceback (most recent call last):
  File "D:\SD\stable-diffusion-webui-directml\modules\safe.py", line 81, in check_pt
    with zipfile.ZipFile(filename) as z:
  File "C:\Users\CXK\AppData\Local\Programs\Python\Python310\lib\zipfile.py", line 1267, in __init__
    self._RealGetContents()
  File "C:\Users\CXK\AppData\Local\Programs\Python\Python310\lib\zipfile.py", line 1334, in _RealGetContents
    raise BadZipFile("File is not a zip file")
zipfile.BadZipFile: File is not a zip file

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "D:\SD\stable-diffusion-webui-directml\modules\safe.py", line 135, in load_with_extra
    check_pt(filename, extra_handler)
  File "D:\SD\stable-diffusion-webui-directml\modules\safe.py", line 102, in check_pt
    unpickler.load()
_pickle.UnpicklingError: persistent IDs in protocol 0 must be ASCII strings

-----> !!!! The file is most likely corrupted !!!! <-----
You can skip this check with --disable-safe-unpickle commandline argument, but that is not going to help you.


Error completing request
Arguments: ('task(5a7r42gce19wgdb)', 'boy face', '', [], 20, 0, True, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 200, 200, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0) {}
Traceback (most recent call last):
  File "D:\SD\stable-diffusion-webui-directml\modules\call_queue.py", line 56, in f
    res = list(func(*args, **kwargs))
  File "D:\SD\stable-diffusion-webui-directml\modules\call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "D:\SD\stable-diffusion-webui-directml\modules\txt2img.py", line 56, in txt2img
    processed = process_images(p)
  File "D:\SD\stable-diffusion-webui-directml\modules\processing.py", line 486, in process_images
    res = process_images_inner(p)
  File "D:\SD\stable-diffusion-webui-directml\modules\processing.py", line 661, in process_images_inner
    x_sample = modules.face_restoration.restore_faces(x_sample)
  File "D:\SD\stable-diffusion-webui-directml\modules\face_restoration.py", line 19, in restore_faces
    return face_restorer.restore(np_image)
  File "D:\SD\stable-diffusion-webui-directml\modules\codeformer_model.py", line 88, in restore
    self.create_models()
  File "D:\SD\stable-diffusion-webui-directml\modules\codeformer_model.py", line 65, in create_models
    checkpoint = torch.load(ckpt_path)['params_ema']
TypeError: 'NoneType' object is not subscriptable

Additional information

RX590
win10
cup i5-8500

[Feature Request]: Implementation of Token Merging for fast SD

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What would your feature do ?

Assuming its possible - an implementation of https://github.com/dbolya/tomesd would be great!
They claim significant memory savings and inference speed improvements with very little quality loss.
However, it requires pytorch >= 1.12.1 (for scatter_reduce) so I'm not sure this can be ported to DirectML though.

Proposed workflow

Additional information

No response

[Bug]: Couldn't find Stable Diffusion in any of:

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

I tried launching webui.bat, but when I do it just gives me this error message.

Steps to reproduce the problem

Go to Stable Diffusion installation path
Press webui.bat or webui-user,bat
error

What should have happened?

Well I guess it should have worked.

Commit where the problem happens

f64ad25

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

no

List of extensions

Console logs

Traceback (most recent call last):
  File "D:\AI\amd\stable-diffusion-webui-directml\launch.py", line 377, in <module>
    start()
  File "D:\AI\amd\stable-diffusion-webui-directml\launch.py", line 368, in start
    import webui
  File "D:\AI\amd\stable-diffusion-webui-directml\webui.py", line 15, in <module>
    from modules import paths, timer, import_hook, errors
  File "D:\AI\amd\stable-diffusion-webui-directml\modules\paths.py", line 26, in <module>
    assert sd_path is not None, "Couldn't find Stable Diffusion in any of: " + str(possible_sd_paths)
AssertionError: Couldn't find Stable Diffusion in any of: ['D:\\AI\\amd\\stable-diffusion-webui-directml\\repositories/stable-diffusion-stability-ai', '.', 'D:\\AI\\amd']

Additional information

pls help.

[Bug]: mat1 and mat2 must have the same dtype

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

i'm just install with the following steps but appear this RuntimeError: mat1 and mat2 must have the same dtype, help me for solve the problem

Steps to reproduce the problem

Go to stable-diffusion-webui-directml
Open webui-user.bat
And wait until RuntimeError: mat1 and mat2 must have the same dtype appear

What should have happened?

The RuntimeError: mat1 and mat2 must have the same dtype not appear, and stable diffusion can launch

Commit where the problem happens

return F.linear(input, self.weight, self.bias) RuntimeError: mat1 and mat2 must have the same dtype

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Microsoft Edge

Command Line Arguments

ya, i modified webui-user with --medvram

List of extensions

Console logs

venv "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash: ff558348682fea569785dcfae1f1282cfbefda6b
Installing requirements for Web UI
Launching Web UI with arguments: --medvram
Warning: experimental graphic memory optimization is disabled due to gpu vendor. Currently this optimization is only available for AMDGPUs.
Disabled experimental graphic memory optimizations.
Interrogations are fallen back to cpu. This doesn't affect on image generation. But if you want to use interrogate (CLIP or DeepBooru), check out this issue: https://github.com/lshqqytiger/stable-diffusion-webui-directml/issues/10
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
Loading weights [bfcaf07557] from D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\models\Stable-diffusion\768-v-ema.ckpt
loading stable diffusion model: RuntimeError
Traceback (most recent call last):
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\webui.py", line 111, in initialize
    modules.sd_models.load_model()
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\sd_models.py", line 385, in load_model
    checkpoint_config = sd_models_config.find_checkpoint_config(state_dict, checkpoint_info)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\sd_models_config.py", line 100, in find_checkpoint_config
    return guess_model_config_from_state_dict(state_dict, info.filename)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\sd_models_config.py", line 75, in guess_model_config_from_state_dict
    elif is_using_v_parameterization_for_sd2(sd):
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\sd_models_config.py", line 60, in is_using_v_parameterization_for_sd2
    out = (unet(x_test, torch.asarray([999], device=device), context=test_cond) - x_test).mean().item()
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\openaimodel.py", line 770, in forward
    emb = self.time_embed(t_emb)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\container.py", line 204, in forward
    input = module(input)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\extensions-builtin\Lora\lora.py", line 178, in lora_Linear_forward
    return lora_forward(self, input, torch.nn.Linear_forward_before_lora(self, input))
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\devices.py", line 229, in forward
    return super().forward(x)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\linear.py", line 114, in forward
    return F.linear(input, self.weight, self.bias)
RuntimeError: mat1 and mat2 must have the same dtype


Stable diffusion model failed to load, exiting
Press any key to continue . . .

Additional information

No response

[Bug]: Different outputs than Nvidia GPUs, with identical prompts and seeds

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

When generating an image with a specific seed and prompt, images generated differ from images generated on the main Automatic1111 branch.

Result from SD1.5, with a seed of "100" and a prompt of "apple" on Euler A

Result from the main Automatic1111 branch, with an Nvidia GPU. SD1.5, with a seed of "100" and a prompt of "apple" on Euler A

Steps to reproduce the problem

Generate an image of your choosing, noting the prompt, seed, and model
Install an Nvidia GPU and the main Automatic1111 branch
Attempt to replicate the image with the same settings

What should have happened?

The images generated should match

Commit where the problem happens

ff55834

What platforms do you use to access the UI ?

No response

What browsers do you use to access the UI ?

No response

Command Line Arguments

--opt-split-attention-v1 --opt-sub-quad-attention --always-batch-cond-uncond --disable-nan-check --sub-quad-kv-chunk-size 512 --sub-quad-q-chunk-size 512 --sub-quad-chunk-threshold 25 --no-half --no-half-vae --precision full --medvram

List of extensions

Console logs

Log not saved, and no longer have AMD GPU (see below)

Additional information

I recently purchased a 7900XT, and noticed I could no longer replicate images with specific prompts. I returned it this afternoon, but decided to generate a side-by-side before I uninstalled it. Sadly this means I am no longer able to generate the bugged images.

[Bug]: Unable to install dependencies.gfpgan\clip\openclip

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

Unable to install dependencies
gfpgan_package = os.environ.get('GFPGAN_PACKAGE', "git+https://github.com/TencentARC/GFPGAN.git@8d2447a2d918f8eba5a4a01463fd48e45126a379")
clip_package = os.environ.get('CLIP_PACKAGE', "git+https://github.com/openai/CLIP.git@d50d76daa670286dd6cacf3bcd80b5e4823fc8e1")
openclip_package = os.environ.get('OPENCLIP_PACKAGE', "git+https://github.com/mlfoundations/open_clip.git@bb6e834e9c70d9c27d0dc3ecedeebeaeb1ffad6b")

Steps to reproduce the problem

After the git source code, run webui-user.bat and it cannot be installed. Open the launch.py and find that the links of these 3 dependent files are not found.

What should have happened?

Normally, these dependencies should be installed sequentially

Commit where the problem happens

Run:webui-user.bat

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

--opt-sub-quad-attention --no-half --precision full --lowvram

List of extensions

Console logs

Installing gfpgan
Traceback (most recent call last):
  File "D:\stable-diffusion-webui-directml\launch.py", line 352, in <module>
    prepare_environment()
  File "D:\stable-diffusion-webui-directml\launch.py", line 262, in prepare_environment
    run_pip(f"install {gfpgan_package}", "gfpgan")
  File "D:\stable-diffusion-webui-directml\launch.py", line 129, in run_pip
    return run(f'"{python}" -m pip {args} --prefer-binary{index_url_line}', desc=f"Installing {desc}", errdesc=f"Couldn't install {desc}")
  File "D:\stable-diffusion-webui-directml\launch.py", line 97, in run
    raise RuntimeError(message)
RuntimeError: Couldn't install gfpgan.
Command: "D:\stable-diffusion-webui-directml\venv\Scripts\python.exe" -m pip install git+https://github.com/TencentARC/GFPGAN.git@8d2447a2d918f8eba5a4a01463fd48e45126a379 --prefer-binary
Error code: 1
stdout: Collecting git+https://github.com/TencentARC/GFPGAN.git@8d2447a2d918f8eba5a4a01463fd48e45126a379
  Cloning https://github.com/TencentARC/GFPGAN.git (to revision 8d2447a2d918f8eba5a4a01463fd48e45126a379) to c:\users\kuron\appdata\local\temp\pip-req-build-a553kloq

stderr:   Running command git clone --filter=blob:none --quiet https://github.com/TencentARC/GFPGAN.git 'C:\Users\kuron\AppData\Local\Temp\pip-req-build-a553kloq'
  fatal: unable to access 'https://github.com/TencentARC/GFPGAN.git/': Failed to connect to github.com port 443 after 21044 ms: Couldn't connect to server
  error: subprocess-exited-with-error

  git clone --filter=blob:none --quiet https://github.com/TencentARC/GFPGAN.git 'C:\Users\kuron\AppData\Local\Temp\pip-req-build-a553kloq' did not run successfully.
  exit code: 128

  See above for output.

  note: This error originates from a subprocess, and is likely not a problem with pip.
error: subprocess-exited-with-error

git clone --filter=blob:none --quiet https://github.com/TencentARC/GFPGAN.git 'C:\Users\kuron\AppData\Local\Temp\pip-req-build-a553kloq' did not run successfully.
exit code: 128

See above for output.

note: This error originates from a subprocess, and is likely not a problem with pip.

### Additional information

_No response_

[Bug]: Can't load any model

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

I'm getting this error no matter what when I try to run webui-user.bat :

Installing requirements for Web UI
Launching Web UI with arguments:
Interrogations are fallen back to cpu. This doesn't affect on image generation. But if you want to use interrogate (CLIP or DeepBooru), check out this issue: #10
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
Calculating sha256 for F:\Stable diffusion\stable-diffusion-webui-directml\models\Stable-diffusion\model1.ckpt: b77d2fec5fba71b0f473cb1685a06221f1d36ab76cbe41b95e94aebb24145e17
Loading weights [b77d2fec5f] from F:\Stable diffusion\stable-diffusion-webui-directml\models\Stable-diffusion\model1.ckpt
loading stable diffusion model: RuntimeError
Traceback (most recent call last):
File "F:\Stable diffusion\stable-diffusion-webui-directml\webui.py", line 136, in initialize
modules.sd_models.load_model()
File "F:\Stable diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 383, in load_model
state_dict = get_checkpoint_state_dict(checkpoint_info, timer)
File "F:\Stable diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 238, in get_checkpoint_state_dict
res = read_state_dict(checkpoint_info.filename)
File "F:\Stable diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 219, in read_state_dict
pl_sd = torch.load(checkpoint_file, map_location=map_location or shared.weight_load_location)
File "F:\Stable diffusion\stable-diffusion-webui-directml\modules\safe.py", line 106, in load
return load_with_extra(filename, extra_handler=global_extra_handler, *args, **kwargs)
File "F:\Stable diffusion\stable-diffusion-webui-directml\modules\safe.py", line 151, in load_with_extra
return unsafe_torch_load(filename, *args, **kwargs)
File "F:\Stable diffusion\stable-diffusion-webui-directml\venv\lib\site-packages\torch\serialization.py", line 789, in load
return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
File "F:\Stable diffusion\stable-diffusion-webui-directml\venv\lib\site-packages\torch\serialization.py", line 1131, in _load
result = unpickler.load()
File "F:\Stable diffusion\stable-diffusion-webui-directml\venv\lib\site-packages\torch\serialization.py", line 1101, in persistent_load
load_tensor(dtype, nbytes, key, _maybe_decode_ascii(location))
File "F:\Stable diffusion\stable-diffusion-webui-directml\venv\lib\site-packages\torch\serialization.py", line 1079, in load_tensor
storage = zip_file.get_storage_from_record(name, numel, torch.UntypedStorage).storage().untyped()
RuntimeError: PytorchStreamReader failed reading file data/95: invalid header or archive is corrupted

Stable diffusion model failed to load, exiting

Can anyone help me to fix it?

I have an AMD Radeon RX 6800XT

Steps to reproduce the problem

Go to ....
Press ....
...

What should have happened?

Commit where the problem happens

What platforms do you use to access the UI ?

No response

What browsers do you use to access the UI ?

No response

Command Line Arguments

List of extensions

Console logs

Additional information

No response

[Bug]: Entry point for LoadLibraryW not found in api-ms-win-core-libraryloader-l1-2-1.dll

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

Entry point for LoadLibraryW not found in api-ms-win-core-libraryloader-l1-2-1.dll

Steps to reproduce the problem

Launch webui-user.bat

What should have happened?

No error

Commit where the problem happens

ae337fa

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

No response

Command Line Arguments

None

List of extensions

None

Console logs

Installing requirements for Web UI
Launching Web UI with arguments:
Traceback (most recent call last):
  File "launch.py", line 353, in <module>
    start()
  File "launch.py", line 344, in start
    import webui
  File "K:\stable-diffusion-webui-directml\webui.py", line 31, in <module>
    from modules import extra_networks, ui_extra_networks_checkpoints
  File "K:\stable-diffusion-webui-directml\modules\ui_extra_networks_checkpoints
.py", line 5, in <module>
    from modules import shared, ui_extra_networks, sd_models
  File "K:\stable-diffusion-webui-directml\modules\shared.py", line 12, in <modu
le>
    import modules.interrogate
  File "K:\stable-diffusion-webui-directml\modules\interrogate.py", line 15, in
<module>
    from modules import devices, paths, shared, lowvram, modelloader, errors
  File "K:\stable-diffusion-webui-directml\modules\devices.py", line 4, in <modu
le>
    import torch_directml
  File "K:\stable-diffusion-webui-directml\venv\lib\site-packages\torch_directml
\__init__.py", line 13, in <module>
    torch.ops.load_library(directml_dll)
  File "K:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\_ops.py"
, line 573, in load_library
    ctypes.CDLL(path)
  File "C:\Program Files\Python38\lib\ctypes\__init__.py", line 373, in __init__

    self._handle = _dlopen(self._name, mode)
FileNotFoundError: Could not find module 'K:\stable-diffusion-webui-directml\ven
v\Lib\site-packages\torch_directml\DirectML.dll' (or one of its dependencies). T
ry using the full path with constructor syntax.

Additional information

Can maybe somebody share the working api-ms-win-core-libraryloader-l1-2-1.dll ?

[Bug]: Massive slowdown after first image

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

After the first image, there is a massive slowdown, going from 10it/s to 90it/s. I'm on Windows 11, using the latest commit on Intel Iris Xe.

Steps to reproduce the problem

Launch stable-diffusion-webui
Generate an image
Try generating a second image

What should have happened?

Speed is maintained between images.

Commit where the problem happens

b2f7f88

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

--lowvram

List of extensions

Console logs

D:\stable-diffusion-webui-directml>webui-user.bat
venv "D:\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.10 (tags/v3.10.10:aad5f6a, Feb  7 2023, 17:20:36) [MSC v.1929 64 bit (AMD64)]
Commit hash: c88824995d87be36a62b110dd509ff7ccb6eeaa2
Installing requirements for Web UI
Launching Web UI with arguments: --lowvram
Warning: experimental graphic memory optimization is disabled due to gpu vendor. Currently this optimization is only available for AMDGPUs.
Disabled experimental graphic memory optimizations.
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
Loading weights [e4b17ce185] from D:\stable-diffusion-webui-directml\models\Stable-diffusion\anything-v4.5-pruned.ckpt
Creating model from config: D:\stable-diffusion-webui-directml\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying cross attention optimization (InvokeAI).
Textual inversion embeddings loaded(0):
Model loaded in 93.9s (load weights from disk: 84.4s, create model: 1.3s, apply weights to model: 4.9s, apply half(): 2.5s, load VAE: 0.1s, hijack: 0.1s, load textual inversion embeddings: 0.4s).
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
 70%|█████████████████████████████████████████████████████████▍                        | 14/20 [03:44<01:36, 16.07s/it]
Total progress:  70%|██████████████████████████████████████████████▏                   | 14/20 [03:47<01:37, 16.25s/it]
 10%|████████▎                                                                          | 2/20 [03:09<28:53, 96.30s/it]

Additional information

No response

[Bug]: Can't call numpy on Tensor that requires grad... when training on AMD 6950 XT

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

Embedding training crashes at the point of creating the first image.

Steps to reproduce the problem

Any embedding training on my GPU

What should have happened?

An embedding should have been created

Commit where the problem happens

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Microsoft Edge

Command Line Arguments

--no-half --precision full --no-half-vae --opt-sub-quad-attention --opt-split-attention-v1

List of extensions

Console logs

File "G:\stable-diffusion-webui-directml\modules\textual_inversion\textual_inversion.py", line 531, in train_embedding
    save_embedding(embedding, optimizer, checkpoint, embedding_name_every, last_saved_file, remove_cached_checksum=True)
  File "G:\stable-diffusion-webui-directml\modules\textual_inversion\textual_inversion.py", line 651, in save_embedding
    embedding.save(filename)
  File "G:\stable-diffusion-webui-directml\modules\textual_inversion\textual_inversion.py", line 65, in save
    torch.save(embedding_data, filename)
  File "G:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\serialization.py", line 423, in save
    _save(obj, opened_zipfile, pickle_module, pickle_protocol)
  File "G:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\serialization.py", line 635, in _save
    pickler.dump(obj)
  File "G:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\_tensor.py", line 225, in __reduce_ex__
    return self._reduce_ex_internal(proto)
  File "G:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\_tensor.py", line 284, in _reduce_ex_internal
    self.cpu().numpy()
RuntimeError: Can't call numpy() on Tensor that requires grad. Use tensor.detach().numpy() instead.

Applying sub-quadratic cross attention optimization.

Additional information

I'm assuming that embedding training cannot be performed at this time for reasons, but I also haven't seen this issue come up and I have seen some AMD users mention that they are training. This doesn't happen when I train with CPU-All, but then training is very slow. Just wanted to pop this up here in case there was a solution to this, but likely I just have to wait for better AMD support. Thanks!

[Bug]: Impossible to send a text 2 image to : img2img or extra or inpaint

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

I just finished an image in text 2 image. I can't send it to any other tab of the application.

Steps to reproduce the problem

Create an image
Try to send it to any other tab : text2img / inpaint / extra.
The tab change but the image is not send.

What should have happened?

Switching with the image to the correct tab.

Commit where the problem happens

41d5450

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Mozilla Firefox

Command Line Arguments

--medvram --no-half --precision full --no-half-vae --opt-sub-quad-attention --opt-split-attention-v1

List of extensions

Console logs

venv "D:\Super Stable Diffusion 2.0\stable-diffusion-webui-amd\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.7 (tags/v3.10.7:6cc6b13, Sep  5 2022, 14:08:36) [MSC v.1933 64 bit (AMD64)]
Commit hash: 41d5450a0a559469b354fd56cac0fe1ab3cf2f40
Installing requirements for Web UI
Launching Web UI with arguments: --medvram --no-half --precision full --no-half-vae --opt-sub-quad-attention --opt-split-attention-v1
Interrogations are fallen back to cpu. This doesn't affect on image generation. But if you want to use interrogate (CLIP or DeepBooru), check out this issue: https://github.com/lshqqytiger/stable-diffusion-webui-directml/issues/10
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
Loading weights [a64810e2e1] from D:\Super Stable Diffusion 2.0\stable-diffusion-webui-amd\stable-diffusion-webui-directml\models\Stable-diffusion\clarity_19.safetensors
Creating model from config: D:\Super Stable Diffusion 2.0\stable-diffusion-webui-amd\stable-diffusion-webui-directml\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying sub-quadratic cross attention optimization.
Textual inversion embeddings loaded(0):
Textual inversion embeddings skipped(3): nartfixer, nfixer, nrealfixer
Model loaded in 58.9s (load weights from disk: 3.4s, create model: 0.8s, apply weights to model: 54.4s, load textual inversion embeddings: 0.2s).
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 103.4s (import torch: 16.7s, import gradio: 9.5s, import ldm: 1.4s, other imports: 13.2s, list extensions: 0.3s, list SD models: 0.2s, setup codeformer: 0.4s, load scripts: 1.8s, load SD checkpoint: 59.2s, create ui: 0.5s, gradio launch: 0.3s).

Additional information

No error in the logs. Restart the interface doesn't fix it.

[Bug]: Blue Screen with VRAM memory error after trying to generate photo 'Torch not compiled with CUDA enabled', memory monitor disabled

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

Trying to run on a laptop with a Ryzen 2700U with Vega10 graphics. When starting up the webui-user bat this is the message that appeared:
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled

When trying to generate a test photo, i immediately crashed to a windows bluescreen with a VRAM memory error.

Steps to reproduce the problem

Go to ....
Press ....
...

What should have happened?

Not crash

Commit where the problem happens

https://github.com/lshqqytiger/stable-diffusion-webui-directml

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

No

List of extensions

Console logs

venv "C:\StableDifusion\stable-diffusion-directml\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.10 (tags/v3.10.10:aad5f6a, Feb  7 2023, 17:20:36) [MSC v.1929 64 bit (AMD64)]
Commit hash: a0f4cd6fdd2b7ef3e2b666694f1a1ca13ee17066
Installing requirements for Web UI
Launching Web UI with arguments:
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
Loading weights [543bcbc212] from C:\StableDifusion\stable-diffusion-directml\stable-diffusion-webui-directml\models\Stable-diffusion\Anything-V3.0.ckpt
Creating model from config: C:\StableDifusion\stable-diffusion-directml\stable-diffusion-webui-directml\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying cross attention optimization (InvokeAI).
Textual inversion embeddings loaded(0):
Model loaded in 16.1s (load weights from disk: 10.5s, create model: 0.7s, apply weights to model: 1.2s, apply half(): 0.9s, move model to device: 2.7s).
Running on local URL:  http://127.0.0.1:7860

Additional information

No response

[Bug]: CLIP Interrogation crashes

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

Tried interrogating an Image in img2img with CLIP, but got this crash and in the prompts box.

Since my GPU is neither CUDA nor HIP due to being on Win11, this crash happens. Maybe put CPU as a Fallback Default?

Steps to reproduce the problem

Start webui-user.bat
Open IMG2IMG
Put any Picture in the Box
Press "Interrogate CLIP"
???
Crash

What should have happened?

CLIP Output in Prompt, no Crash in Console.

Commit where the problem happens

c888249

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

--opt-split-attention-v1 --opt-sub-quad-attention --autolaunch --no-half --disable-nan-check --precision full

List of extensions

Console logs

load checkpoint from G:\Other\AI\stable-diffusion-webui-directml\models\BLIP\model_base_caption_capfilt_large.pth
Error interrogating
Traceback (most recent call last):
  File "G:\Other\AI\stable-diffusion-webui-directml\modules\interrogate.py", line 198, in interrogate
    caption = self.generate_caption(pil_image)
  File "G:\Other\AI\stable-diffusion-webui-directml\modules\interrogate.py", line 183, in generate_caption
    caption = self.blip_model.generate(gpu_image, sample=False, num_beams=shared.opts.interrogate_clip_num_beams, min_length=shared.opts.interrogate_clip_min_length, max_length=shared.opts.interrogate_clip_max_length)
  File "G:\Other\AI\stable-diffusion-webui-directml\repositories\BLIP\models\blip.py", line 156, in generate
    outputs = self.text_decoder.generate(input_ids=input_ids,
  File "G:\Other\AI\stable-diffusion-webui-directml\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "G:\Other\AI\stable-diffusion-webui-directml\venv\lib\site-packages\transformers\generation\utils.py", line 1518, in generate
    return self.greedy_search(
  File "G:\Other\AI\stable-diffusion-webui-directml\venv\lib\site-packages\transformers\generation\utils.py", line 2267, in greedy_search
    unfinished_sequences = input_ids.new(input_ids.shape[0]).fill_(1)
RuntimeError: new(): expected key in DispatchKeySet(CPU, CUDA, HIP, XLA, MPS, IPU, XPU, HPU, Lazy, Meta) but got: PrivateUse1

Additional information

CPU: 5950x
RAM: 32GB
GPU: 7900 XTX
VRAM: 24GB

[Bug]: RuntimeError: The GPU device instance has been suspended when using autocast precision

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

When I tried to launch webui with --lowvram --precision autocast, I got error during vae decoder in txt2img:
RuntimeError: The GPU device instance has been suspended. Use GetDeviceRemovedReason to determine the appropriate action.

I wonder whether current fp16 is available ?
https://github.com/lshqqytiger/stable-diffusion-webui-directml/blob/master/modules/devices.py#L200-L240 And is this part of the code useful, can it help improve the quality of the fp16 conference?

Steps to reproduce the problem

I just changed webui-user.bat as:

@echo off

set PYTHON=
set GIT=
set VENV_DIR=
set COMMANDLINE_ARGS=--api --lowvram --precision autocast

call webui.bat

What should have happened?

inference successfully.

Commit where the problem happens

Latest version

What platforms do you use to access the UI ?

No response

What browsers do you use to access the UI ?

No response

Command Line Arguments

@echo off

set PYTHON=
set GIT=
set VENV_DIR=
set COMMANDLINE_ARGS=--api --lowvram --precision autocast

call webui.bat

List of extensions

Console logs

Applying cross attention optimization (InvokeAI).
Textual inversion embeddings loaded(0):
Model loaded in 53.9s (load weights from disk: 0.1s, create model: 0.6s, apply weights to model: 12.7s, apply half(): 2.9s, move model to device: 37.4s).
Running on local URL:  http://127.0.0.1:7860
Running on public URL: https://9f72eb6a-6870-425a.gradio.live

This share link expires in 72 hours. For free permanent hosting and GPU upgrades (NEW!), check out Spaces: https://huggingface.co/spaces
Startup time: 136.1s (import gradio: 4.3s, import ldm: 1.7s, other imports: 3.3s, setup codeformer: 0.3s, load scripts: 1.6s, load SD checkpoint: 54.3s, create ui: 0.4s, gradio launch: 70.1s, scripts app_started_callback: 0.1s).
index debug:::
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [17:28<00:00, 52.42s/it]
Error completing request███████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [16:58<00:00, 38.12s/it]
Arguments: ('task(kepz361926z9mgh)', 'cat and dog', '', [], 20, 0, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0) {}
Traceback (most recent call last):
  File "C:\Users\ruonanw1\OneDrive - Intel Corporation\Desktop\code\sd-webui-directml\stable-diffusion-webui-directml\modules\call_queue.py", line 56, in f
    res = list(func(*args, **kwargs))
  File "C:\Users\ruonanw1\OneDrive - Intel Corporation\Desktop\code\sd-webui-directml\stable-diffusion-webui-directml\modules\call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "C:\Users\ruonanw1\OneDrive - Intel Corporation\Desktop\code\sd-webui-directml\stable-diffusion-webui-directml\modules\txt2img.py", line 56, in txt2img
    processed = process_images(p)
  File "C:\Users\ruonanw1\OneDrive - Intel Corporation\Desktop\code\sd-webui-directml\stable-diffusion-webui-directml\modules\processing.py", line 486, in process_images
    res = process_images_inner(p)
  File "C:\Users\ruonanw1\OneDrive - Intel Corporation\Desktop\code\sd-webui-directml\stable-diffusion-webui-directml\modules\processing.py", line 637, in process_images_inner
    x_samples_ddim = [decode_first_stage(p.sd_model, samples_ddim[i:i+1].to(dtype=devices.dtype_vae))[0].cpu() for i in range(samples_ddim.size(0))]
  File "C:\Users\ruonanw1\OneDrive - Intel Corporation\Desktop\code\sd-webui-directml\stable-diffusion-webui-directml\modules\processing.py", line 637, in <listcomp>
    x_samples_ddim = [decode_first_stage(p.sd_model, samples_ddim[i:i+1].to(dtype=devices.dtype_vae))[0].cpu() for i in range(samples_ddim.size(0))]
  File "C:\Users\ruonanw1\OneDrive - Intel Corporation\Desktop\code\sd-webui-directml\stable-diffusion-webui-directml\modules\processing.py", line 423, in decode_first_stage
    x = model.decode_first_stage(x)
  File "C:\Users\ruonanw1\OneDrive - Intel Corporation\Desktop\code\sd-webui-directml\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 17, in <lambda>
    setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
  File "C:\Users\ruonanw1\OneDrive - Intel Corporation\Desktop\code\sd-webui-directml\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 28, in __call__
    return self.__orig_func(*args, **kwargs)
  File "C:\Users\ruonanw1\OneDrive - Intel Corporation\Desktop\code\sd-webui-directml\stable-diffusion-webui-directml\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "C:\Users\ruonanw1\OneDrive - Intel Corporation\Desktop\code\sd-webui-directml\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 826, in decode_first_stage
    return self.first_stage_model.decode(z)
  File "C:\Users\ruonanw1\OneDrive - Intel Corporation\Desktop\code\sd-webui-directml\stable-diffusion-webui-directml\modules\lowvram.py", line 52, in first_stage_model_decode_wrap
    return first_stage_model_decode(z)
  File "C:\Users\ruonanw1\OneDrive - Intel Corporation\Desktop\code\sd-webui-directml\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\autoencoder.py", line 90, in decode
    dec = self.decoder(z)
  File "C:\Users\ruonanw1\OneDrive - Intel Corporation\Desktop\code\sd-webui-directml\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\Users\ruonanw1\OneDrive - Intel Corporation\Desktop\code\sd-webui-directml\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\model.py", line 649, in forward
    h = self.conv_out(h)
  File "C:\Users\ruonanw1\OneDrive - Intel Corporation\Desktop\code\sd-webui-directml\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\Users\ruonanw1\OneDrive - Intel Corporation\Desktop\code\sd-webui-directml\stable-diffusion-webui-directml\extensions-builtin\Lora\lora.py", line 182, in lora_Conv2d_forward
    return lora_forward(self, input, torch.nn.Conv2d_forward_before_lora(self, input))
  File "C:\Users\ruonanw1\OneDrive - Intel Corporation\Desktop\code\sd-webui-directml\stable-diffusion-webui-directml\modules\devices.py", line 245, in forward
    return super().forward(x.float()).type(x.dtype)
  File "C:\Users\ruonanw1\OneDrive - Intel Corporation\Desktop\code\sd-webui-directml\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\conv.py", line 463, in forward
    return self._conv_forward(input, self.weight, self.bias)
  File "C:\Users\ruonanw1\OneDrive - Intel Corporation\Desktop\code\sd-webui-directml\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\conv.py", line 459, in _conv_forward
    return F.conv2d(input, weight, bias, self.stride,
RuntimeError: The GPU device instance has been suspended. Use GetDeviceRemovedReason to determine the appropriate action.

Additional information

No response

[Bug]: Embedding Training fails with DirectML without --no-half

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

Training embeddings not possible and an error is raised

Steps to reproduce the problem

Start this for with cmdline "--medvram"
Create a new embedding and train it with otions:

Lean Rate: 0.005
Gradient Clipping: disabled
Batch size: 1
Width: 64
Height: 64
Do not resize images: False
Max Steps: 2000
Save images with embedding in PNG chunks: False
Read parameters: False
Shuffle tags: false
Choose latent sampling method: once

Train Embedding

What should have happened?

Embedding is trained

Commit where the problem happens

commit: ba374c7

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Brave

Command Line Arguments

--medvram

List of extensions

None

Console logs

Training at rate of 0.005 until step 2000
Preparing dataset...
100%|████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:06<00:00,  2.30s/it]
No saved optimizer exists in checkpoint
  0%|                                                                                         | 0/2000 [00:00<?, ?it/s]Traceback (most recent call last):
  File "D:\stable-diffusion-webui-directml\modules\textual_inversion\textual_inversion.py", line 497, in train_embedding
    scaler.scale(loss).backward()
  File "D:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\_tensor.py", line 488, in backward
    torch.autograd.backward(
  File "D:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\autograd\__init__.py", line 197, in backward
    Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
RuntimeError: m_device->CreateOperator(&opDesc, IID_PPV_ARGS(&op))



### Additional information

_No response_

[Bug]: Deforum 3D mode not working on AMD card

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

Tried to use the 3D animation mode in the latest Deforum release and Stable Diffusion returns this error

Steps to reproduce the problem

go to the Deforum tab
select the 3D option
enter all your prompts and such
click generate

What should have happened?

Generation should have continued as normal

Commit where the problem happens

AUTOMATIC1111@ff55834

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

--autolaunch --opt-split-attention

List of extensions

Deforum
Controlnet
Openposeeditor

Console logs

Deforum extension for auto1111 webui, v2.2b
Saving animation frames to:
J:\SDAMD\new\stable-diffusion-webui-directml\outputs/img2img-images\Deforum
Loading base model ()...Done.
Removing last two layers (global_pool & classifier).
Building Encoder-Decoder model..Done.
Animation frame: 0/10
Seed: 3151898744
Prompt: apple
Not using an init image (doing pure txt2img)
╭─────┬───┬───────┬────┬────┬────┬────┬────┬────╮
│Steps│CFG│Denoise│Tr X│Tr Y│Tr Z│Ro X│Ro Y│Ro Z│
├─────┼───┼───────┼────┼────┼────┼────┼────┼────┤
│ 25  │7.0│ None  │ 0  │ 0  │1.75│ 0  │ 0  │ 0  │
╰─────┴───┴───────┴────┴────┴────┴────┴────┴────╯
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 25/25 [00:08<00:00,  3.06it/s]
Animation frame: 2/10  ██████████████████████████████████████████████████████████████████████████████████████████████████████████▉                                                                                                                                                          | 25/61 [00:07<00:11,  3.07it/s]
 Creating in-between frame: 0; tween:0.50;
Deforum progress:  41%|██████████████████████████████████████████████████████████████████████████████████████████████████████████▉                                                                                                                                                          | 25/61 [00:09<00:13,  2.74it/s]
Error completing request
Arguments: ('task(erf15n4lnf2pha9)', None, False, '', '3D', 10, 'replicate', '0:(0)', '0:(1.0025+0.002*sin(1.25*3.14*t/30))', '0:(0)', '0:(0)', '0:(1.75)', '0:(0.5)', '0:(0.5)', '0:(0)', '0:(0)', '0:(0)', False, '0:(0)', '0:(0)', '0:(0)', '0:(53)', '0: (0.065)', '0: (0.65)', '0: (1.0)', '0: (7)', '0:(1.5)', False, '0:(1)', '0:(0)', False, '0: (25)', '0: (70)', '0: (1)', '0: (200)', '0: (10000)', '0:(5), 1:(-1), 219:(-1), 220:(5)', False, '0: ("Euler a")', '0: ("!({everywhere}^({init_mask}|{video_mask}) ) ")', False, '0: ("!({everywhere}^({init_mask}|{video_mask}) ) ")', False, '0: ("model1.ckpt"), 100: ("model2.ckpt")', False, '0: (2)', '0: (5)', '0: (1.0)', '0: (0.35)', '0: (0.0)', 'Match Frame 0 LAB', 1.0, False, '2', 'perlin', 8, 8, 4, 0.5, True, 0.2, 'border', 'bicubic', False, 'https://github.com/hithereai/d/releases/download/m/vid.mp4', 1, 0, -1, False, False, '/content/video_in.mp4', False, '20230129210106', '{\n    "0": "apple",\n \n    "60": "orange"\n}\n    ', '', '', 512, 512, False, False, -1, 'Euler a', False, 0, 0, 25, 0.0, 1, True, True, False, False, False, 'Deforum', '{timestring}_{index}_{prompt}.png', 'iter', 1, False, False, True, 0, 'https://github.com/hithereai/d/releases/download/m/kaba.png', False, False, False, True, 'https://github.com/hithereai/d/releases/download/m/mask.jpg', 1.0, 1.0, 4, 1, True, 4, 'reroll', False, 15, False, 'FFMPEG mp4', 'J:\\SDAMD\\new\\stable-diffusion-webui-directml\\venv\\lib\\site-packages\\imageio_ffmpeg\\binaries\\ffmpeg-win64-v4.2.2.exe', '17', 'slow', 'None', 'https://freetestdata.com/wp-content/uploads/2021/09/Free_Test_Data_1MB_MP3.mp3', False, 'realesr-animevideov3', 'x2', True, False, 'x0_pred', 'C:/SD/20230124234916_%05d.png', 'testvidmanualsettings.mp4', False, 'None', 2, False, 2, False, '', True, False, 'None', True, 'None', False, 'Farneback', False, 'None', False, 'None', False, False, '0:(1)', '0:(0.5)', '0:(1)', '0:(100)', '0:(0)', False, '{\n    "0": "https://user-images.githubusercontent.com/121192995/215279228-1673df8a-f919-4380-b04c-19379b2041ff.png",\n    "50": "https://user-images.githubusercontent.com/121192995/215279281-7989fd6f-4b9b-4d90-9887-b7960edd59f8.png",\n    "100": "https://user-images.githubusercontent.com/121192995/215279284-afc14543-d220-4142-bbf4-503776ca2b8b.png",\n    "150": "https://user-images.githubusercontent.com/121192995/215279286-23378635-85b3-4457-b248-23e62c048049.jpg",\n    "200": "https://user-images.githubusercontent.com/121192995/215279228-1673df8a-f919-4380-b04c-19379b2041ff.png"\n}', '0:(0.75)', '0:(0.35)', '0:(0.25)', '0:(20)', '0:(0.075)', None, None, False, False, False, False, 'none', 'None', 1, 1, 64, 64, 64, 'Scale to Fit (Inner Fit)') {}
Traceback (most recent call last):
  File "J:\SDAMD\new\stable-diffusion-webui-directml\modules\call_queue.py", line 56, in f
    res = list(func(*args, **kwargs))
  File "J:\SDAMD\new\stable-diffusion-webui-directml\modules\call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "J:\SDAMD\new\stable-diffusion-webui-directml\extensions\deforum-for-automatic1111-webui\scripts\deforum.py", line 79, in run_deforum
    render_animation(args, anim_args, video_args, parseq_args, loop_args, controlnet_args, root.animation_prompts, root)
  File "J:\SDAMD\new\stable-diffusion-webui-directml/extensions/deforum-for-automatic1111-webui/scripts\deforum_helpers\render.py", line 234, in render_animation
    depth = depth_model.predict(turbo_next_image, anim_args.midas_weight, root.half_precision)
  File "J:\SDAMD\new\stable-diffusion-webui-directml/extensions/deforum-for-automatic1111-webui/scripts\deforum_helpers\depth.py", line 122, in predict
    midas_depth = torch.nn.functional.interpolate(
  File "J:\SDAMD\new\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\functional.py", line 3958, in interpolate
    return torch._C._nn.upsample_bicubic2d(input, output_size, align_corners, scale_factors)
RuntimeError: "compute_indices_weights_cubic" not implemented for 'Half'

Additional information

my GPU is an AMD 6800 XT with the latest driver
could this perhaps be a physical limitation due to my card being AMD?
Previously asked on the main release but was told to here aswell

[Bug]: VRAM doesn't go down after generating an image.

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

OS: Windows 11
GPU: AMD Radeon 6700 XT
VRAM: 12 GB
Processor: AMD Ryzen 7 3700X 8-Core Processor
Primary Memory: 16 GB

I have some VRAM usage when I load up stable diffusion, but it doubles and stays there once I generate an image. If I continue to generate images, they will stack on top of each other and crash unless I close my command prompt window, at which point it will return to normal.

before generating

after generating

Steps to reproduce the problem

Open the WebUI
Generate 5 to 6 images
Crashes PC or I close the command prompt window to stop it.

What should have happened?

It shouldn't stack VRAM usage after every generation.

Commit where the problem happens

ff55834

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome, Microsoft Edge

Command Line Arguments

--lowvram --no-half --precision full --no-half-vae --opt-sub-quad-attention --opt-split-attention-v1

List of extensions

Console logs

No certain point, just after every generation.

Additional information

To generate more than a few images I have to close and reopen my command prompt window.

[Bug]: Inpainting non-functional

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

Inpainting does not return a new image, but does show progress towards a unique problem in the view finder

Steps to reproduce the problem

Inpainting
Add image
Highlight any part of the image, I chose top of the head as a hat
Hit generate
Verify Same image

What should have happened?

It should have inpainted new content into the image

Commit where the problem happens

c888249

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Mozilla Firefox, Google Chrome, Microsoft Edge

Command Line Arguments

--medvram --autolaunch

List of extensions

Console logs

100%|██████████████████████████████████████████████████████████████████████████████████| 16/16 [00:24<00:00,  1.56s/it]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 16/16 [00:24<00:00,  1.54s/it]

Additional information

want to emphasize that it does appear to be inpainting because I can see progress in the viewfinder, but the final image is always the original image with default inpainting settings

Video card 6700XT
CPU 15-12400F
OS Windows 11

[Bug]: Pc is crashing when creating image

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

I followed this guide to download and get SD running : https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs

I can open and use the webui, but when i attempt to create an image once its at 20-30% my pc immediately turns off. Happens almost every time. when it doesnt turn off I get this error "RuntimeError: Could not allocate tensor with 4915840 bytes. There is not enough GPU video memory available!"

PC specs:
16gb ram
rx 5700 xt
ryzen 7 1800x
750W gold psu

Steps to reproduce the problem

Install using https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs
run webui-user.bat
enter prompt and run
within seconds computer crashes

What should have happened?

Image should have generated normally

Commit where the problem happens

3e85552

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

set COMMANDLINE_ARGS=--medvram --precision full --no-half --opt-sub-quad-attention --opt-split-attention-v1 --disable-nan-check

List of extensions

Console logs

venv "E:\stable-diffusion-webui-directml-master\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash: <none>
Installing requirements for Web UI
Launching Web UI with arguments: --medvram --precision full --no-half --opt-sub-quad-attention --opt-split-attention-v1 --disable-nan-check
Interrogations are fallen back to cpu. This doesn't affect on image generation. But if you want to use interrogate (CLIP or DeepBooru), check out this issue: https://github.com/lshqqytiger/stable-diffusion-webui-directml/issues/10
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
Loading weights [fe4efff1e1] from E:\stable-diffusion-webui-directml-master\models\Stable-diffusion\model.ckpt
Creating model from config: E:\stable-diffusion-webui-directml-master\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying sub-quadratic cross attention optimization.
Textual inversion embeddings loaded(0):
Model loaded in 6.3s (load weights from disk: 4.1s, create model: 0.9s, apply weights to model: 1.2s).
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.

Additional information

No response

[Bug]: Torch and Torchvision wont install

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

Stable Diffusion Wont Install Torch

Steps to reproduce the problem

Launch webui-user.bat

What should have happened?

It Should install the Torch

Commit where the problem happens

Commit hash: ae337fa

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

No

List of extensions

Console logs

venv "C:\Users\Username\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.11 (tags/v3.10.11:7d4cc5a, Apr  5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]
Commit hash: ae337fa39b6d4598b377ff312c53b14c15142331
Installing torch and torchvision
C:\Users\vwite\stable-diffusion-webui-directml\venv\Scripts\python.exe: No module named pip
Traceback (most recent call last):
  File "C:\Users\Username\stable-diffusion-webui-directml\launch.py", line 352, in <module>
    prepare_environment()
  File "C:\Users\Username\stable-diffusion-webui-directml\launch.py", line 259, in prepare_environment
    run(f'"{python}" -m {torch_command}', "Installing torch and torchvision", "Couldn't install torch", live=True)
  File "C:\Users\Username\stable-diffusion-webui-directml\launch.py", line 81, in run
    raise RuntimeError(f"""{errdesc or 'Error running command'}.
RuntimeError: Couldn't install torch.
Command: "C:\Users\Username\stable-diffusion-webui-directml\venv\Scripts\python.exe" -m pip install torch==1.13.1 torchvision==0.14.1 torch-directml
Error code: 1

Additional information

No response

[Bug]: 7900xtx only can generate 512*512 picture

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

7900xtx only can generate 512*512 picture,but I have 24GB vram，that's really strange

Steps to reproduce the problem

Go to ....
Press ....
...

What should have happened?

DirectML has bad memory control?

Commit where the problem happens

。

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Microsoft Edge

Command Line Arguments

I tried some command lines, but all usless
such as 
--opt-sub-quad-attention --lowvram --no-half

List of extensions

。

Console logs

。

Additional information

Could you give me some advice ,thank u

[Bug]: AttributeError: function 'ADL2_Adapter_DedicatedVRAMUsage_Get' not found

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

Launching Web UI with arguments: --opt-sub-quad-attention --lowvram --no-half --precision full
Traceback (most recent call last):
File "D:\sd.webui-amd\launch.py", line 377, in
start()
File "D:\sd.webui-amd\launch.py", line 368, in start
import webui
File "D:\sd.webui-amd\webui.py", line 28, in
from modules import extra_networks, ui_extra_networks_checkpoints
File "D:\sd.webui-amd\modules\ui_extra_networks_checkpoints.py", line 5, in
from modules import shared, ui_extra_networks, sd_models
File "D:\sd.webui-amd\modules\shared.py", line 12, in
import modules.interrogate
File "D:\sd.webui-amd\modules\interrogate.py", line 15, in
from modules import devices, paths, shared, lowvram, modelloader, errors
File "D:\sd.webui-amd\modules\devices.py", line 101, in
from modules import atiadlxx
File "D:\sd.webui-amd\modules\atiadlxx.py", line 2, in
from .atiadlxx_apis import *
File "D:\sd.webui-amd\modules\atiadlxx_apis.py", line 41, in
ADL2_Adapter_DedicatedVRAMUsage_Get = atiadlxx.ADL2_Adapter_DedicatedVRAMUsage_Get
File "C:\Users\28670\AppData\Local\Programs\Python\Python310\lib\ctypes_init_.py", line 387, in getattr
func = self.getitem(name)
File "C:\Users\28670\AppData\Local\Programs\Python\Python310\lib\ctypes_init_.py", line 392, in getitem
func = self._FuncPtr((name_or_ordinal, self))
AttributeError: function 'ADL2_Adapter_DedicatedVRAMUsage_Get' not found

Steps to reproduce the problem

重新安装了系统就出现了这个

What should have happened?

进入webui

Commit where the problem happens

启动的时候

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

--opt-sub-quad-attention --lowvram --no-half --precision full

List of extensions

无

Console logs

Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash: f64ad25386ad77d1e07986a204dac923b9a46894
Installing requirements for Web UI

Launching Web UI with arguments: --opt-sub-quad-attention --lowvram --no-half --precision full
Traceback (most recent call last):
  File "D:\sd.webui-amd\launch.py", line 377, in <module>
    start()
  File "D:\sd.webui-amd\launch.py", line 368, in start
    import webui
  File "D:\sd.webui-amd\webui.py", line 28, in <module>
    from modules import extra_networks, ui_extra_networks_checkpoints
  File "D:\sd.webui-amd\modules\ui_extra_networks_checkpoints.py", line 5, in <module>
    from modules import shared, ui_extra_networks, sd_models
  File "D:\sd.webui-amd\modules\shared.py", line 12, in <module>
    import modules.interrogate
  File "D:\sd.webui-amd\modules\interrogate.py", line 15, in <module>
    from modules import devices, paths, shared, lowvram, modelloader, errors
  File "D:\sd.webui-amd\modules\devices.py", line 101, in <module>
    from modules import atiadlxx
  File "D:\sd.webui-amd\modules\atiadlxx.py", line 2, in <module>
    from .atiadlxx_apis import *
  File "D:\sd.webui-amd\modules\atiadlxx_apis.py", line 41, in <module>
    ADL2_Adapter_DedicatedVRAMUsage_Get = atiadlxx.ADL2_Adapter_DedicatedVRAMUsage_Get
  File "C:\Users\28670\AppData\Local\Programs\Python\Python310\lib\ctypes\__init__.py", line 387, in __getattr__
    func = self.__getitem__(name)
  File "C:\Users\28670\AppData\Local\Programs\Python\Python310\lib\ctypes\__init__.py", line 392, in __getitem__
    func = self._FuncPtr((name_or_ordinal, self))
AttributeError: function 'ADL2_Adapter_DedicatedVRAMUsage_Get' not found

Additional information

No response

[Bug]: Generated output is black image

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

UI is booting up without any error, error comes when generating an image it comes out as a black image as Final, and while generating it's white.

Steps to reproduce the problem

Go to web ui.
Press generate button.
While generating it's white and the final image is black.

What should have happened?

The output should have been colorful ig.

Commit where the problem happens

ff55834

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

@echo off

set PYTHON=
set GIT=
set VENV_DIR=
set COMMANDLINE_ARGS=--opt-sub-quad-attention --lowvram --precision full --no-half --disable-nan-check --autolaunch --opt-split-attention-v1

call webui.bat

List of extensions

gif2gif
openpose-editor
sd-extension-steps-animation
sd_dreambooth_extension
stable-diffusion-webui-images-browser
LDSR (built-in)
Lora (built-in)
ScuNET (built-in)
SwinIR (built-in)
prompt-bracket-checker (built-in)

Console logs

venv "D:\Anime\Software\ai\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.10 (tags/v3.10.10:aad5f6a, Feb  7 2023, 17:20:36) [MSC v.1929 64 bit (AMD64)]
Commit hash: ff558348682fea569785dcfae1f1282cfbefda6b
Installing requirements for Web UI

#######################################################################################################
Initializing Dreambooth
If submitting an issue on github, please provide the below text for debugging purposes:

Python revision: 3.10.10 (tags/v3.10.10:aad5f6a, Feb  7 2023, 17:20:36) [MSC v.1929 64 bit (AMD64)]
Dreambooth revision: bff61c6b92b79ece2e140ee240e0628dd9a4ebef
SD-WebUI revision: ff558348682fea569785dcfae1f1282cfbefda6b

Checking Dreambooth requirements...
Ignoring tensorflow-macos: markers 'sys_platform == "darwin" and platform_machine == "arm64"' don't match your environment
Ignoring mediapipe-silicon: markers 'sys_platform == "darwin"' don't match your environment
Collecting accelerate==0.16.0
  Using cached accelerate-0.16.0-py3-none-any.whl (199 kB)
Collecting gitpython~=3.1.31
  Using cached GitPython-3.1.31-py3-none-any.whl (184 kB)
Collecting transformers~=4.26.1
  Using cached transformers-4.26.1-py3-none-any.whl (6.3 MB)
Collecting requests
  Using cached requests-2.28.2-py3-none-any.whl (62 kB)
Installing collected packages: requests, gitpython, accelerate, transformers
  Attempting uninstall: requests
    Found existing installation: requests 2.25.1
    Uninstalling requests-2.25.1:
      Successfully uninstalled requests-2.25.1
  Attempting uninstall: gitpython
    Found existing installation: GitPython 3.1.27
    Uninstalling GitPython-3.1.27:
      Successfully uninstalled GitPython-3.1.27
  Attempting uninstall: accelerate
    Found existing installation: accelerate 0.12.0
    Uninstalling accelerate-0.12.0:
      Successfully uninstalled accelerate-0.12.0
  Attempting uninstall: transformers
    Found existing installation: transformers 4.25.1
    Uninstalling transformers-4.25.1:
      Successfully uninstalled transformers-4.25.1
Successfully installed accelerate-0.16.0 gitpython-3.1.31 requests-2.28.2 transformers-4.26.1

[!] torch version 1.13.1 installed.
[!] torchvision version 0.14.1 installed.
[+] accelerate version 0.16.0 installed.
[+] bitsandbytes version 0.35.4 installed.
[+] diffusers version 0.13.1 installed.
[+] transformers version 4.26.1 installed.
[+] xformers version 0.0.17.dev464 installed.
Interrogations are fallen back to cpu. This doesn't affect on image generation. But if you want to use interrogate (CLIP or DeepBooru), check out this issue: https://github.com/lshqqytiger/stable-diffusion-webui-directml/issues/10
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
Launch errors detected: ['Incorrect version of torch installed.', 'Incorrect version of torchvision installed.']

#######################################################################################################


Launching Web UI with arguments: --opt-sub-quad-attention --lowvram --precision full --no-half --disable-nan-check --autolaunch --opt-split-attention-v1
Interrogations are fallen back to cpu. This doesn't affect on image generation. But if you want to use interrogate (CLIP or DeepBooru), check out this issue: https://github.com/lshqqytiger/stable-diffusion-webui-directml/issues/10
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
Script path is D:\Anime\Software\ai\stable-diffusion-webui-directml
Loading weights [b67fff7a42] from D:\Anime\Software\ai\stable-diffusion-webui-directml\models\Stable-diffusion\samdoesartsSamYang_offsetRightFilesize.safetensors
Creating model from config: D:\Anime\Software\ai\stable-diffusion-webui-directml\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
'HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /openai/clip-vit-large-patch14/resolve/main/vocab.json (Caused by ConnectTimeoutError(<urllib3.connection.HTTPSConnection object at 0x000000006E946800>, 'Connection to huggingface.co timed out. (connect timeout=10)'))' thrown while requesting HEAD https://huggingface.co/openai/clip-vit-large-patch14/resolve/main/vocab.json
Applying sub-quadratic cross attention optimization.
Textual inversion embeddings loaded(0):
Model loaded in 41.7s (create model: 41.6s).
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [04:12<00:00, 12.62s/it]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [04:05<00:00, 12.25s/it]
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [03:57<00:00, 11.90s/it]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [03:52<00:00, 11.63s/it]

Additional information

I used SamDoesArts (Sam Yang) Style LoRA Model just to test out:

Prompt: sam yang, 1girl, backlighting, bare shoulders, black choker, blurry, blurry background, blush, breasts, choker, cleavage, closed mouth, collarbone, earrings, forehead, freckles, hair over shoulder, jewelry, long hair, looking down, pointy nose, red lips, (masterpiece)

Negative Prompt: (painting by bad-artist-anime:0.9), (painting by bad-artist:0.9), watermark, text, error, blurry, jpeg artifacts, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, artist name, (worst quality, low quality:1.4), bad anatomy, (painting by bad-artist-anime:0.9)

Sampling method: DPM++ SDE Karras
Sampling steps: 20
WidthxHeight: 512x512
CFG Scale: 8
Seed: 1

Btw, my PC Specs are:
CPU: i3-12100F
GPU: RX 6500XT

[Bug]: Can't click on the "Generate" button after a few prompt (very random)

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

After a few prompts, I cannot click on "Generate" until I reload the page/UI. No message is visible in the terminal.

Steps to reproduce the problem

Make a few prompt (5-100? > Full random).
Press "Generate" for a new prompt.

What should have happened?

Generate a new image.

Commit where the problem happens

41d5450

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Mozilla Firefox

Command Line Arguments

--medvram --no-half --precision full --no-half-vae --opt-sub-quad-attention --opt-split-attention-v1

List of extensions

Console logs

Python 3.10.7 (tags/v3.10.7:6cc6b13, Sep  5 2022, 14:08:36) [MSC v.1933 64 bit (AMD64)]
Commit hash: 41d5450a0a559469b354fd56cac0fe1ab3cf2f40
Installing requirements for Web UI
Launching Web UI with arguments: --medvram --no-half --precision full --no-half-vae --opt-sub-quad-attention --opt-split-attention-v1
Interrogations are fallen back to cpu. This doesn't affect on image generation. But if you want to use interrogate (CLIP or DeepBooru), check out this issue: https://github.com/lshqqytiger/stable-diffusion-webui-directml/issues/10
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
Loading weights [a64810e2e1] from D:\Super Stable Diffusion 2.0\stable-diffusion-webui-amd\stable-diffusion-webui-directml\models\Stable-diffusion\clarity_19.safetensors
Creating model from config: D:\Super Stable Diffusion 2.0\stable-diffusion-webui-amd\stable-diffusion-webui-directml\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying sub-quadratic cross attention optimization.
Textual inversion embeddings loaded(0):
Textual inversion embeddings skipped(3): nartfixer, nfixer, nrealfixer
Model loaded in 76.2s (load weights from disk: 17.5s, load config: 0.4s, create model: 3.4s, apply weights to model: 54.5s, load textual inversion embeddings: 0.3s).
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 133.6s (import torch: 26.1s, import gradio: 10.9s, import ldm: 1.8s, other imports: 12.9s, list extensions: 0.2s, list SD models: 0.3s, setup codeformer: 0.9s, list builtin upscalers: 0.6s, load scripts: 2.4s, load SD checkpoint: 76.5s, create ui: 0.5s, gradio launch: 0.4s).

Additional information

I didn't found any way to reproduce it. Didn't find any assocation with a specific action or something. It's looks like its full random. I will provide more information if I can reproduce it more easily.
Quite annoying for now, because it can happen very often in a short timing. But I can't figure out what's going on.
That bug was not in the last build before this one.

black image output

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

UI boots up without error and after generating an image it comes out as black image

Steps to reproduce the problem

Go to .... web ui
Press .... generate
... a black image comes out

What should have happened?

output should have been a bit colorful

Commit where the problem happens

commit: 3e85552

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

@echo off

set PYTHON=
set GIT=
set VENV_DIR=
set COMMANDLINE_ARGS=--opt-sub-quad-attention --lowvram --disable-nan-check --autolaunch


call webui.bat

List of extensions

none

Console logs

venv "E:\New folder\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash: 3e8555242836192c9e3e79c91962418e1f51d5d6
Installing requirements for Web UI
Launching Web UI with arguments: --opt-sub-quad-attention --lowvram --disable-nan-check --autolaunch
Interrogations are fallen back to cpu. This doesn't affect on image generation. But if you want to use interrogate (CLIP or DeepBooru), check out this issue: https://github.com/lshqqytiger/stable-diffusion-webui-directml/issues/10
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
Loading weights [e04b020012] from E:\New folder\stable-diffusion-webui-directml\models\Stable-diffusion\rpg_V4.safetensors
Creating model from config: E:\New folder\stable-diffusion-webui-directml\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying sub-quadratic cross attention optimization.
Textual inversion embeddings loaded(0):
Model loaded in 42.4s (load weights from disk: 2.5s, create model: 1.8s, apply weights to model: 30.8s, apply half(): 6.5s, load VAE: 0.1s, load textual inversion embeddings: 0.5s).
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [04:45<00:00, 14.29s/it]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [04:41<00:00, 14.07s/it]

Additional information

model im using is rpg v4 and its a safetensor file

[Bug]: Fails with memory error

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

OS: Windows 11 Pro
GPU: AMD RX 5700XT
VRAM: 8GB
Processor: AMD Ryzen 5600X
Primary Memory: 16GB

I followed the installation instructions from here: https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs
After installation, I was able to start the WebUI but was unable to generate anything, I keep getting the error : RuntimeError: Could not allocate tensor with 9831040 bytes. There is not enough GPU video memory available!

Please check console logs for complete error information

Steps to reproduce the problem

RX 5700XT GPU
2, Follow the manual installation guide for Windows from https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs
Start WebUI

What should have happened?

It should have generated the image.

Commit where the problem happens

6a6dd58

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Microsoft Edge

Command Line Arguments

set COMMANDLINE_ARGS=--opt-sub-quad-attention --medvram --disable-nan-check --no-half --precision full

List of extensions

none

Console logs

PS H:\Python\AI\stable-diffusion-webui-directml> .\webui.bat
venv "H:\Python\AI\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.10 (tags/v3.10.10:aad5f6a, Feb  7 2023, 17:20:36) [MSC v.1929 64 bit (AMD64)]
Commit hash: 6a6dd5879811156baeea3a1c5b8c6aa306ec9dd9
Installing requirements for Web UI
Launching Web UI with arguments:
Interrogate will be fallen back to cpu. Because DirectML device does not support it.
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
Loading weights [fe4efff1e1] from H:\Python\AI\stable-diffusion-webui-directml\models\Stable-diffusion\model.ckpt
Creating model from config: H:\Python\AI\stable-diffusion-webui-directml\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying cross attention optimization (InvokeAI).
Textual inversion embeddings loaded(0):
Model loaded in 48.1s (load weights from disk: 41.8s, create model: 2.1s, apply weights to model: 1.3s, apply half(): 1.4s, move model to device: 1.4s).
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
  5%|████▏                                                                              | 1/20 [00:08<02:42,  8.56s/it]
Error completing request                                                                        | 0/20 [00:00<?, ?it/s]
Arguments: ('task(h16ycxt2jmydnil)', 'book with red cover', '', [], 20, 0, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0) {}
Traceback (most recent call last):
  File "H:\Python\AI\stable-diffusion-webui-directml\modules\call_queue.py", line 56, in f
    res = list(func(*args, **kwargs))
  File "H:\Python\AI\stable-diffusion-webui-directml\modules\call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "H:\Python\AI\stable-diffusion-webui-directml\modules\txt2img.py", line 56, in txt2img
    processed = process_images(p)
  File "H:\Python\AI\stable-diffusion-webui-directml\modules\processing.py", line 486, in process_images
    res = process_images_inner(p)
  File "H:\Python\AI\stable-diffusion-webui-directml\modules\processing.py", line 632, in process_images_inner
    samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts)
  File "H:\Python\AI\stable-diffusion-webui-directml\modules\processing.py", line 832, in sample
    samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
  File "H:\Python\AI\stable-diffusion-webui-directml\modules\sd_samplers_kdiffusion.py", line 349, in sample
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
  File "H:\Python\AI\stable-diffusion-webui-directml\modules\sd_samplers_kdiffusion.py", line 225, in launch_sampling
    return func()
  File "H:\Python\AI\stable-diffusion-webui-directml\modules\sd_samplers_kdiffusion.py", line 349, in <lambda>
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
  File "H:\Python\AI\stable-diffusion-webui-directml\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "H:\Python\AI\stable-diffusion-webui-directml\repositories\k-diffusion\k_diffusion\sampling.py", line 150, in sample_euler_ancestral
    denoised = model(x, sigmas[i] * s_in, **extra_args)
  File "H:\Python\AI\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "H:\Python\AI\stable-diffusion-webui-directml\modules\sd_samplers_kdiffusion.py", line 117, in forward
    x_out = self.inner_model(x_in, sigma_in, cond={"c_crossattn": [cond_in], "c_concat": [image_cond_in]})
  File "H:\Python\AI\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "H:\Python\AI\stable-diffusion-webui-directml\repositories\k-diffusion\k_diffusion\external.py", line 112, in forward
    eps = self.get_eps(input * c_in, self.sigma_to_t(sigma), **kwargs)
  File "H:\Python\AI\stable-diffusion-webui-directml\repositories\k-diffusion\k_diffusion\external.py", line 138, in get_eps
    return self.inner_model.apply_model(*args, **kwargs)
  File "H:\Python\AI\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 17, in <lambda>
    setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
  File "H:\Python\AI\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 28, in __call__
    return self.__orig_func(*args, **kwargs)
  File "H:\Python\AI\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 858, in apply_model
    x_recon = self.model(x_noisy, t, **cond)
  File "H:\Python\AI\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "H:\Python\AI\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 1335, in forward
    out = self.diffusion_model(x, t, context=cc)
  File "H:\Python\AI\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "H:\Python\AI\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\openaimodel.py", line 778, in forward
    h = module(h, emb, context)
  File "H:\Python\AI\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "H:\Python\AI\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\openaimodel.py", line 84, in forward
    x = layer(x, context)
  File "H:\Python\AI\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "H:\Python\AI\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\attention.py", line 334, in forward
    x = block(x, context=context[i])
  File "H:\Python\AI\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "H:\Python\AI\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\attention.py", line 269, in forward
    return checkpoint(self._forward, (x, context), self.parameters(), self.checkpoint)
  File "H:\Python\AI\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\util.py", line 114, in checkpoint
    return CheckpointFunction.apply(func, len(inputs), *args)
  File "H:\Python\AI\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\util.py", line 129, in forward
    output_tensors = ctx.run_function(*ctx.input_tensors)
  File "H:\Python\AI\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\attention.py", line 272, in _forward
    x = self.attn1(self.norm1(x), context=context if self.disable_self_attn else None) + x
  File "H:\Python\AI\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "H:\Python\AI\stable-diffusion-webui-directml\modules\sd_hijack_optimizations.py", line 246, in split_cross_attention_forward_invokeAI
    r = einsum_op(q, k, v)
  File "H:\Python\AI\stable-diffusion-webui-directml\modules\sd_hijack_optimizations.py", line 221, in einsum_op
    return einsum_op_dml(q, k, v)
  File "H:\Python\AI\stable-diffusion-webui-directml\modules\sd_hijack_optimizations.py", line 209, in einsum_op_dml
    return einsum_op_tensor_mem(q, k, v, (mem_reserved - mem_active) if mem_reserved > mem_active else 1)
  File "H:\Python\AI\stable-diffusion-webui-directml\modules\sd_hijack_optimizations.py", line 194, in einsum_op_tensor_mem
    return einsum_op_slice_1(q, k, v, max(q.shape[1] // div, 1))
  File "H:\Python\AI\stable-diffusion-webui-directml\modules\sd_hijack_optimizations.py", line 169, in einsum_op_slice_1    r[:, i:end] = einsum_op_compvis(q[:, i:end], k, v)
RuntimeError: Could not allocate tensor with 9831040 bytes. There is not enough GPU video memory available!

Additional information

No response

[Bug]: assert sd_path is not None

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

I follow the Installation but i can't work.

Steps to reproduce the problem

Go to ....
Press ....
...

What should have happened?

try a lot no help

Commit where the problem happens

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Microsoft Edge

Command Line Arguments

no

List of extensions

Console logs

venv "F:\stable-diffusion-webui-directml-master\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash: <none>
Installing requirements for Web UI
Launching Web UI with arguments:
Traceback (most recent call last):
  File "F:\stable-diffusion-webui-directml-master\launch.py", line 353, in <module>
    start()
  File "F:\stable-diffusion-webui-directml-master\launch.py", line 344, in start
    import webui
  File "F:\stable-diffusion-webui-directml-master\webui.py", line 16, in <module>
    from modules import paths, timer, import_hook, errors
  File "F:\stable-diffusion-webui-directml-master\modules\paths.py", line 19, in <module>
    assert sd_path is not None, "Couldn't find Stable Diffusion in any of: " + str(possible_sd_paths)
AssertionError: Couldn't find Stable Diffusion in any of: ['F:\\stable-diffusion-webui-directml-master\\repositories/stable-diffusion-stability-ai', '.', 'F:\\']

Additional information

No response

[Bug]: Web UI link failed

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

Im sorry to sound like a noob,
Followed the steps - Installed Python latest + Git 2.40
Ran the .bat file
First time some installations came up and then did not get Web UI link
got some kinda line error texts.
Ran it again to get the errors..
Have provided the console log for the second run.

Steps to reproduce the problem

same as above

What should have happened?

Should have got the WEB UI link?

Commit where the problem happens

Always

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

No response

Command Line Arguments

no

List of extensions

Console logs

Creating venv in directory C:\Users\deepn\Downloads\Stable Diffusion Stuf\stable-diffusion-webui-directml-master\stable-diffusion-webui-directml-master\venv using python "C:\Users\deepn\AppData\Local\Programs\Python\Python310\python.exe"
venv "C:\Users\deepn\Downloads\Stable Diffusion Stuf\stable-diffusion-webui-directml-master\stable-diffusion-webui-directml-master\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash: <none>
Installing torch and torchvision
Collecting torch==1.13.1
  Using cached torch-1.13.1-cp310-cp310-win_amd64.whl (162.6 MB)
Collecting torchvision==0.14.1
  Using cached torchvision-0.14.1-cp310-cp310-win_amd64.whl (1.1 MB)
Collecting torch-directml
  Using cached torch_directml-0.1.13.1.dev230301-cp310-cp310-win_amd64.whl (7.4 MB)
Collecting typing-extensions
  Using cached typing_extensions-4.5.0-py3-none-any.whl (27 kB)
Collecting numpy
  Using cached numpy-1.24.2-cp310-cp310-win_amd64.whl (14.8 MB)
Collecting requests
  Using cached requests-2.28.2-py3-none-any.whl (62 kB)
Collecting pillow!=8.3.*,>=5.3.0
  Using cached Pillow-9.4.0-cp310-cp310-win_amd64.whl (2.5 MB)
Collecting certifi>=2017.4.17
  Using cached certifi-2022.12.7-py3-none-any.whl (155 kB)
Collecting urllib3<1.27,>=1.21.1
  Using cached urllib3-1.26.15-py2.py3-none-any.whl (140 kB)
Collecting idna<4,>=2.5
  Using cached idna-3.4-py3-none-any.whl (61 kB)
Collecting charset-normalizer<4,>=2
  Using cached charset_normalizer-3.1.0-cp310-cp310-win_amd64.whl (97 kB)
Installing collected packages: urllib3, typing-extensions, pillow, numpy, idna, charset-normalizer, certifi, torch, requests, torchvision, torch-directml
Successfully installed certifi-2022.12.7 charset-normalizer-3.1.0 idna-3.4 numpy-1.24.2 pillow-9.4.0 requests-2.28.2 torch-1.13.1 torch-directml-0.1.13.1.dev230301 torchvision-0.14.1 typing-extensions-4.5.0 urllib3-1.26.15

[notice] A new release of pip available: 22.2.1 -> 23.0.1
[notice] To update, run: C:\Users\deepn\Downloads\Stable Diffusion Stuf\stable-diffusion-webui-directml-master\stable-diffusion-webui-directml-master\venv\Scripts\python.exe -m pip install --upgrade pip
Installing gfpgan
Installing clip
Installing open_clip
Cloning Taming Transformers into C:\Users\deepn\Downloads\Stable Diffusion Stuf\stable-diffusion-webui-directml-master\stable-diffusion-webui-directml-master\repositories\taming-transformers...
Cloning CodeFormer into C:\Users\deepn\Downloads\Stable Diffusion Stuf\stable-diffusion-webui-directml-master\stable-diffusion-webui-directml-master\repositories\CodeFormer...
Cloning BLIP into C:\Users\deepn\Downloads\Stable Diffusion Stuf\stable-diffusion-webui-directml-master\stable-diffusion-webui-directml-master\repositories\BLIP...
Installing requirements for CodeFormer
Installing requirements for Web UI
Launching Web UI with arguments:
Traceback (most recent call last):
  File "C:\Users\deepn\Downloads\Stable Diffusion Stuf\stable-diffusion-webui-directml-master\stable-diffusion-webui-directml-master\launch.py", line 377, in <module>
    start()
  File "C:\Users\deepn\Downloads\Stable Diffusion Stuf\stable-diffusion-webui-directml-master\stable-diffusion-webui-directml-master\launch.py", line 368, in start
    import webui
  File "C:\Users\deepn\Downloads\Stable Diffusion Stuf\stable-diffusion-webui-directml-master\stable-diffusion-webui-directml-master\webui.py", line 15, in <module>
    from modules import paths, timer, import_hook, errors
  File "C:\Users\deepn\Downloads\Stable Diffusion Stuf\stable-diffusion-webui-directml-master\stable-diffusion-webui-directml-master\modules\paths.py", line 26, in <module>
    assert sd_path is not None, "Couldn't find Stable Diffusion in any of: " + str(possible_sd_paths)
AssertionError: Couldn't find Stable Diffusion in any of: ['C:\\Users\\deepn\\Downloads\\Stable Diffusion Stuf\\stable-diffusion-webui-directml-master\\stable-diffusion-webui-directml-master\\repositories/stable-diffusion-stability-ai', '.', 'C:\\Users\\deepn\\Downloads\\Stable Diffusion Stuf\\stable-diffusion-webui-directml-master']
Press any key to continue . . .

----

Additional information

No response

[Bug]: Error charging model

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

This is a new error.
Yesterday I was working with my SD without problems with a RX6600.
I updated my driver like another days but it gives always this error:

Steps to reproduce the problem

Execute webui-user.bat

What should have happened?

Starts without problems like other days

Commit where the problem happens

In the console

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Microsoft Edge

Command Line Arguments

--listen --api --medvram --disable-nan-check --opt-sub-quad-attention --precision full --no-half --autolaunch

List of extensions

Openpose, controlnet...

Console logs

Already up to date.
venv "D:\Datos\Downloads\GitHub\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.9 (tags/v3.10.9:1dd9be6, Dec  6 2022, 20:01:21) [MSC v.1934 64 bit (AMD64)]
Commit hash: ae337fa39b6d4598b377ff312c53b14c15142331
Installing requirements for Web UI
Interrogations are fallen back to cpu. This doesn't affect on image generation. But if you want to use interrogate (CLIP or DeepBooru), check out this issue: https://github.com/lshqqytiger/stable-diffusion-webui-directml/issues/10
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled




Launching Web UI with arguments: --listen --api --medvram --disable-nan-check --opt-sub-quad-attention --precision full --no-half --autolaunch
Interrogations are fallen back to cpu. This doesn't affect on image generation. But if you want to use interrogate (CLIP or DeepBooru), check out this issue: https://github.com/lshqqytiger/stable-diffusion-webui-directml/issues/10
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
Loading weights [58a28bf595] from D:\Datos\Downloads\GitHub\stable-diffusion-webui-directml\models\Stable-diffusion\PeachTachyon2.safetensors
Creating model from config: D:\Datos\Downloads\GitHub\stable-diffusion-webui-directml\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
Failed to create model quickly; will retry using slow method.
LatentDiffusion: Running in eps-prediction mode
loading stable diffusion model: RuntimeError
Traceback (most recent call last):
  File "D:\Datos\Downloads\GitHub\stable-diffusion-webui-directml\webui.py", line 139, in initialize
    modules.sd_models.load_model()
  File "D:\Datos\Downloads\GitHub\stable-diffusion-webui-directml\modules\sd_models.py", line 438, in load_model
    sd_model = instantiate_from_config(sd_config.model)
  File "D:\Datos\Downloads\GitHub\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\util.py", line 79, in instantiate_from_config
    return get_obj_from_str(config["target"])(**config.get("params", dict()))
  File "D:\Datos\Downloads\GitHub\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 550, in __init__
    super().__init__(conditioning_key=conditioning_key, *args, **kwargs)
  File "D:\Datos\Downloads\GitHub\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 92, in __init__
    self.model = DiffusionWrapper(unet_config, conditioning_key)
  File "D:\Datos\Downloads\GitHub\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 1314, in __init__
    self.diffusion_model = instantiate_from_config(diff_model_config)
  File "D:\Datos\Downloads\GitHub\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\util.py", line 79, in instantiate_from_config
    return get_obj_from_str(config["target"])(**config.get("params", dict()))
  File "D:\Datos\Downloads\GitHub\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\openaimodel.py", line 669, in __init__
    ResBlock(
  File "D:\Datos\Downloads\GitHub\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\openaimodel.py", line 203, in __init__
    conv_nd(dims, channels, self.out_channels, 3, padding=1),
  File "D:\Datos\Downloads\GitHub\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\util.py", line 229, in conv_nd
    return nn.Conv2d(*args, **kwargs)
  File "D:\Datos\Downloads\GitHub\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\conv.py", line 450, in __init__
    super(Conv2d, self).__init__(
  File "D:\Datos\Downloads\GitHub\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\conv.py", line 137, in __init__
    self.weight = Parameter(torch.empty(
RuntimeError: [enforce fail at ..\c10\core\impl\alloc_cpu.cpp:72] data. DefaultCPUAllocator: not enough memory: you tried to allocate 117964800 bytes.


Stable diffusion model failed to load, exiting

Additional information

No response

[Bug]: Runtime Error

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

Tried running webui-user.bat, but after everything has finished downloaded, it errors out and fails to launch.

Steps to reproduce the problem

Followed these steps under Windows:
https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs

What should have happened?

Program should have started after the set-up process.

Commit where the problem happens

f64ad25

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

--medvram 
--no-half

List of extensions

No.

Console logs

loading stable diffusion model: RuntimeError
Traceback (most recent call last):
  File "C:\Users\danga\Desktop\AI Gen II\stable-diffusion-webui-directml\webui.py", line 136, in initialize
    modules.sd_models.load_model()
  File "C:\Users\danga\Desktop\AI Gen II\stable-diffusion-webui-directml\modules\sd_models.py", line 383, in load_model
    state_dict = get_checkpoint_state_dict(checkpoint_info, timer)
  File "C:\Users\danga\Desktop\AI Gen II\stable-diffusion-webui-directml\modules\sd_models.py", line 238, in get_checkpoint_state_dict
    res = read_state_dict(checkpoint_info.filename)
  File "C:\Users\danga\Desktop\AI Gen II\stable-diffusion-webui-directml\modules\sd_models.py", line 217, in read_state_dict
    pl_sd = safetensors.torch.load_file(checkpoint_file, device=device)
  File "C:\Users\danga\Desktop\AI Gen II\stable-diffusion-webui-directml\venv\lib\site-packages\safetensors\torch.py", line 100, in load_file
    result[k] = f.get_tensor(k)
RuntimeError: self.size(-1) must be divisible by 4 to view Byte as Float (different element sizes), but got 7289158

Additional information

Using a Radeon RX 580 series GPU.

New to github. My apologies for being too vague/posting anything incorrect.

[Bug]: web ui找不到存储库

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

venv "D:\aihuihua\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.10 (tags/v3.10.10:aad5f6a, Feb 7 2023, 17:20:36) [MSC v.1929 64 bit (AMD64)]
Commit hash: 3e85552
Installing requirements for Web UI
Launching Web UI with arguments:
Traceback (most recent call last):
File "D:\aihuihua\stable-diffusion-webui-directml\launch.py", line 360, in
start()
File "D:\aihuihua\stable-diffusion-webui-directml\launch.py", line 351, in start
import webui
File "D:\aihuihua\stable-diffusion-webui-directml\webui.py", line 15, in
from modules import import_hook, errors, extra_networks, ui_extra_networks_checkpoints
File "D:\aihuihua\stable-diffusion-webui-directml\modules\ui_extra_networks_checkpoints.py", line 6, in
from modules import shared, ui_extra_networks, sd_models
File "D:\aihuihua\stable-diffusion-webui-directml\modules\shared.py", line 12, in
import modules.interrogate
File "D:\aihuihua\stable-diffusion-webui-directml\modules\interrogate.py", line 15, in
from modules import devices, paths, shared, lowvram, modelloader, errors
File "D:\aihuihua\stable-diffusion-webui-directml\modules\paths.py", line 26, in
assert sd_path is not None, "Couldn't find Stable Diffusion in any of: " + str(possible_sd_paths)
AssertionError: Couldn't find Stable Diffusion in any of: ['D:\aihuihua\stable-diffusion-webui-directml\repositories/stable-diffusion-stability-ai', '.', 'D:\aihuihua']

Steps to reproduce the problem

运行webui.bat

What should have happened?

出现本地网址

Commit where the problem happens

Traceback (most recent call last): File "D:\aihuihua\stable-diffusion-webui-directml\launch.py", line 360, in start() File "D:\aihuihua\stable-diffusion-webui-directml\launch.py", line 351, in start import webui File "D:\aihuihua\stable-diffusion-webui-directml\webui.py", line 15, in from modules import import_hook, errors, extra_networks, ui_extra_networks_checkpoints File "D:\aihuihua\stable-diffusion-webui-directml\modules\ui_extra_networks_checkpoints.py", line 6, in from modules import shared, ui_extra_networks, sd_models File "D:\aihuihua\stable-diffusion-webui-directml\modules\shared.py", line 12, in import modules.interrogate File "D:\aihuihua\stable-diffusion-webui-directml\modules\interrogate.py", line 15, in from modules import devices, paths, shared, lowvram, modelloader, errors File "D:\aihuihua\stable-diffusion-webui-directml\modules\paths.py", line 26, in assert sd_path is not None, "Couldn't find Stable Diffusion in any of: " + str(possible_sd_paths) AssertionError: Couldn't find Stable Diffusion in

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

否

List of extensions

否

Console logs

Traceback (most recent call last):
  File "D:\aihuihua\stable-diffusion-webui-directml\launch.py", line 360, in <module>
    start()
  File "D:\aihuihua\stable-diffusion-webui-directml\launch.py", line 351, in start
    import webui
  File "D:\aihuihua\stable-diffusion-webui-directml\webui.py", line 15, in <module>
    from modules import import_hook, errors, extra_networks, ui_extra_networks_checkpoints
  File "D:\aihuihua\stable-diffusion-webui-directml\modules\ui_extra_networks_checkpoints.py", line 6, in <module>
    from modules import shared, ui_extra_networks, sd_models
  File "D:\aihuihua\stable-diffusion-webui-directml\modules\shared.py", line 12, in <module>
    import modules.interrogate
  File "D:\aihuihua\stable-diffusion-webui-directml\modules\interrogate.py", line 15, in <module>
    from modules import devices, paths, shared, lowvram, modelloader, errors
  File "D:\aihuihua\stable-diffusion-webui-directml\modules\paths.py", line 26, in <module>
    assert sd_path is not None, "Couldn't find Stable Diffusion in any of: " + str(possible_sd_paths)
AssertionError: Couldn't find Stable Diffusion in any of: ['D:\\aihuihua\\stable-diffusion-webui-directml\\repositories/stable-diffusion-stability-ai', '.', 'D:\\aihuihua']

Additional information

No response

[Bug]: Upscaling errors with the last update

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

Batch process upscaling using R-ESGRAN Anime gives errors

Steps to reproduce the problem

Go to the extras tab
Go to batch processing
Add images and choose R-ESGRAN Anime

What should have happened?

It should have upscaled the images without giving me any errors

Commit where the problem happens

41d5450

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Microsoft Edge

Command Line Arguments

--opt-sub-quad-attention --no-half

List of extensions

Console logs

https://pastebin.com/GPg2pxNv

Additional information

Prior to the latest update this has always worked and I never had any issues before.

[Bug]: Virtual machine

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

Trying to install this over a virtual machine VMware Fusion on my Intel MacBook Pro to try and use the AMD gpu.

I know this is probably a horrible idea but the local install of SD on a Mac can not use the GPU and CPU generation is like trying to download a movie over 56k internet speed. If you did not get that reference or never lived through that, it is gruelingly slow.

I need better than 2min generations... =[

Steps to reproduce the problem

Fallowed std install instructions:
https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs

What should have happened?

It does not seem to be detecting the GPU.

Commit where the problem happens

Starting Web UI

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

No

List of extensions

Console logs

venv "C:\Users\VM_PC\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash: 41d5450a0a559469b354fd56cac0fe1ab3cf2f40
Installing requirements for Web UI
Launching Web UI with arguments:
Traceback (most recent call last):
  File "C:\Users\VM_PC\stable-diffusion-webui-directml\launch.py", line 349, in <module>
    start()
  File "C:\Users\VM_PC\stable-diffusion-webui-directml\launch.py", line 340, in start
    import webui
  File "C:\Users\VM_PC\stable-diffusion-webui-directml\webui.py", line 31, in <module>
    from modules import extra_networks, ui_extra_networks_checkpoints
  File "C:\Users\VM_PC\stable-diffusion-webui-directml\modules\ui_extra_networks_checkpoints.py", line 5, in <module>
    from modules import shared, ui_extra_networks, sd_models
  File "C:\Users\VM_PC\stable-diffusion-webui-directml\modules\shared.py", line 12, in <module>
    import modules.interrogate
  File "C:\Users\VM_PC\stable-diffusion-webui-directml\modules\interrogate.py", line 15, in <module>
    from modules import devices, paths, shared, lowvram, modelloader, errors
  File "C:\Users\VM_PC\stable-diffusion-webui-directml\modules\devices.py", line 99, in <module>
    dml = torch_directml.device(torch_directml.default_device())
  File "C:\Users\VM_PC\stable-diffusion-webui-directml\venv\lib\site-packages\torch_directml\device.py", line 38, in device
    raise Exception(f"Invalid device_id argument supplied {device_id}. device_id must be in range [0, {num_devices}).")
Exception: Invalid device_id argument supplied 0. device_id must be in range [0, 0).
Press any key to continue . . .

Additional information

No response

[Bug]: install clip failed

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

i dont know how to install clip and whats wrong

Steps to reproduce the problem

just follow this
and upgrade pip version

What should have happened?

WeUI should have been launched

Commit where the problem happens

git fetch -q https://github.com/openai/CLIP.git d50d76daa670286dd6cacf3bcd80b5e4823fc8e1 did not run successfully.

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Microsoft Edge

Command Line Arguments

no

List of extensions

Console logs

venv "D:\Project\StableDiffusionWebui\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash: ff558348682fea569785dcfae1f1282cfbefda6b
Installing clip
Traceback (most recent call last):
  File "D:\Project\StableDiffusionWebui\stable-diffusion-webui-directml\launch.py", line 356, in <module>
    prepare_environment()
  File "D:\Project\StableDiffusionWebui\stable-diffusion-webui-directml\launch.py", line 276, in prepare_environment
    run_pip(f"install {clip_package}", "clip")
  File "D:\Project\StableDiffusionWebui\stable-diffusion-webui-directml\launch.py", line 137, in run_pip
    return run(f'"{python}" -m pip {args} --prefer-binary{index_url_line}', desc=f"Installing {desc}", errdesc=f"Couldn't install {desc}")
  File "D:\Project\StableDiffusionWebui\stable-diffusion-webui-directml\launch.py", line 105, in run
    raise RuntimeError(message)
RuntimeError: Couldn't install clip.
Command: "D:\Project\StableDiffusionWebui\stable-diffusion-webui-directml\venv\Scripts\python.exe" -m pip install git+https://github.com/openai/CLIP.git@d50d76daa670286dd6cacf3bcd80b5e4823fc8e1 --prefer-binary
Error code: 1
stdout: Collecting git+https://github.com/openai/CLIP.git@d50d76daa670286dd6cacf3bcd80b5e4823fc8e1
  Cloning https://github.com/openai/CLIP.git (to revision d50d76daa670286dd6cacf3bcd80b5e4823fc8e1) to c:\users\zxy\appdata\local\temp\pip-req-build-rx2qalf3

stderr:   Running command git clone --filter=blob:none --quiet https://github.com/openai/CLIP.git 'C:\Users\ZXY\AppData\Local\Temp\pip-req-build-rx2qalf3'
  Running command git rev-parse -q --verify 'sha^d50d76daa670286dd6cacf3bcd80b5e4823fc8e1'
  Running command git fetch -q https://github.com/openai/CLIP.git d50d76daa670286dd6cacf3bcd80b5e4823fc8e1
  fatal: unable to access 'https://github.com/openai/CLIP.git/': Recv failure: Connection was reset
  error: subprocess-exited-with-error

  git fetch -q https://github.com/openai/CLIP.git d50d76daa670286dd6cacf3bcd80b5e4823fc8e1 did not run successfully.
  exit code: 128

  See above for output.

  note: This error originates from a subprocess, and is likely not a problem with pip.
error: subprocess-exited-with-error

git fetch -q https://github.com/openai/CLIP.git d50d76daa670286dd6cacf3bcd80b5e4823fc8e1 did not run successfully.
exit code: 128

See above for output.

note: This error originates from a subprocess, and is likely not a problem with pip.

Additional information

No response

[Bug]: Live Preview not working

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

Live preview is not working, shows only brown image. I try change n steps, but still same problem.

Steps to reproduce the problem

Go to .... txt2img
Press ....generate
...

What should have happened?

In automatic1111 fork its working, but i have AMD card, then i try your fork and this happen. Is it possible to verify that it works for you?

Commit where the problem happens

AUTOMATIC1111@b2f7f88

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

No

List of extensions

Console logs

venv "E:\_DOWNLOADS\stable-diffusion-webui-directml-master (1)\stable-diffusion-webui-directml-master\venv\Scripts\Python.exe"
Python 3.10.9 (tags/v3.10.9:1dd9be6, Dec  6 2022, 20:01:21) [MSC v.1934 64 bit (AMD64)]
Commit hash: <none>
Installing requirements for Web UI
Launching Web UI with arguments:
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
Calculating sha256 for E:\_DOWNLOADS\stable-diffusion-webui-directml-master (1)\stable-diffusion-webui-directml-master\models\Stable-diffusion\AbyssOrangeMix2_sfw.safetensors: 038ba203d8ba3c8af24f14e01fbb870c85bbb8d4b6d9520804828f4193d12ce9
Loading weights [038ba203d8] from E:\_DOWNLOADS\stable-diffusion-webui-directml-master (1)\stable-diffusion-webui-directml-master\models\Stable-diffusion\AbyssOrangeMix2_sfw.safetensors
Creating model from config: E:\_DOWNLOADS\stable-diffusion-webui-directml-master (1)\stable-diffusion-webui-directml-master\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying cross attention optimization (InvokeAI).
Textual inversion embeddings loaded(0):
Model loaded in 9.6s (calculate hash: 5.3s, load weights from disk: 0.4s, create model: 0.9s, apply weights to model: 0.5s, apply half(): 0.4s, move model to device: 1.9s).
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:44<00:00,  2.24s/it]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:43<00:00,  2.19s/it]
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:44<00:00,  2.23s/it]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:43<00:00,  2.17s/it]

Additional information

Unfortunately I'm not a programmer and I don't understand python very well. I'm just trying to somehow get Automatic1111 ui running on an AMD gpu. So I apologize if I didn't add enough information.

[Bug]: AssertionError: Couldn't find Stable Diffusion in any of: ['C:\\Users\\user\\Downloads\\stable-diffusion-webui-directml\\repositories/stable-diffusion-stability-ai', '.', 'C:\\Users\\user\\Downloads']

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

Webui will not launch when webui-user.bat is opened

Steps to reproduce the problem

Go to webui-user.bat
Press webui-user.bat
error will occur

What should have happened?

Webui should have launched

Commit where the problem happens

ae337fa

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Microsoft Edge

Command Line Arguments

No

List of extensions

Console logs

venv "C:\Users\user\Downloads\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash: ae337fa39b6d4598b377ff312c53b14c15142331
Installing requirements for Web UI
Launching Web UI with arguments:
Traceback (most recent call last):
  File "C:\Users\user\Downloads\stable-diffusion-webui-directml\launch.py", line 353, in <module>
    start()
  File "C:\Users\user\Downloads\stable-diffusion-webui-directml\launch.py", line 344, in start
    import webui
  File "C:\Users\user\Downloads\stable-diffusion-webui-directml\webui.py", line 16, in <module>
    from modules import paths, timer, import_hook, errors
  File "C:\Users\user\Downloads\stable-diffusion-webui-directml\modules\paths.py", line 19, in <module>
    assert sd_path is not None, "Couldn't find Stable Diffusion in any of: " + str(possible_sd_paths)
AssertionError: Couldn't find Stable Diffusion in any of: ['C:\\Users\\user\\Downloads\\stable-diffusion-webui-directml\\repositories/stable-diffusion-stability-ai', '.', 'C:\\Users\\user\\Downloads']
Press any key to continue . . .

Additional information

No response

[Bug]: Stable Diffusion running on CPU not GPU

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

Steps to reproduce the problem

Go to
Running webui-user.bat
Go to Img2Img
Add your Image

What should have happened?

Stable Diffusion running on GPU

Commit where the problem happens

Could not allocate tensor with 1048576 bytes. There is not enough GPU video memory available!

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Microsoft Edge

Command Line Arguments

Yes, i modified webui-user.bat with --medvram and --no-half

List of extensions

Console logs

venv "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash: ff558348682fea569785dcfae1f1282cfbefda6b
Installing requirements for Web UI
Launching Web UI with arguments: --medvram --no-half
Warning: experimental graphic memory optimization is disabled due to gpu vendor. Currently this optimization is only available for AMDGPUs.
Disabled experimental graphic memory optimizations.
Interrogations are fallen back to cpu. This doesn't affect on image generation. But if you want to use interrogate (CLIP or DeepBooru), check out this issue: https://github.com/lshqqytiger/stable-diffusion-webui-directml/issues/10
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
Loading weights [bfcaf07557] from D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\models\Stable-diffusion\768-v-ema.ckpt
Creating model from config: D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\configs\stable-diffusion\v2-inference-v.yaml
LatentDiffusion: Running in v-prediction mode
DiffusionWrapper has 865.91 M params.
Applying cross attention optimization (InvokeAI).
Textual inversion embeddings loaded(0):
Model loaded in 219.0s (load weights from disk: 133.0s, find config: 38.5s, load config: 0.3s, create model: 3.4s, apply weights to model: 38.3s, apply dtype to VAE: 0.3s, load VAE: 2.8s, move model to device: 2.0s, load textual inversion embeddings: 0.3s).
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Downloading: "https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model_base_caption_capfilt_large.pth" to D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\models\BLIP\model_base_caption_capfilt_large.pth

 10%|███████▌                                                                      | 82.3M/855M [00:36<06:36, 2.04MB/s]Downloading: "https://github.com/AUTOMATIC1111/TorchDeepDanbooru/releases/download/v1/model-resnet_custom_v3.pt" to D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\models\torch_deepdanbooru\model-resnet_custom_v3.pt

  0%|                                                                                           | 0/16 [00:08<?, ?it/s]
Error completing request                                                            | 42.1M/614M [06:18<31:22, 319kB/s]
Arguments: ('task(5bhm9n9sz8w7tot)', 0, '', '', [], <PIL.Image.Image image mode=RGBA size=4000x6000 at 0x264321C5D50>, None, None, None, None, None, None, 20, 0, 4, 0, 1, False, False, 1, 1, 9, 1.5, 0.75, -1.0, -1.0, 0, 0, 0, False, 512, 512, 0, 0, 32, 0, '', '', '', [], 0, '<ul>\n<li><code>CFG Scale</code> should be 2 or lower.</li>\n</ul>\n', True, True, '', '', True, 50, True, 1, 0, False, 4, 1, 'None', '<p style="margin-bottom:0.75em">Recommended settings: Sampling Steps: 80-100, Sampler: Euler a, Denoising strength: 0.8</p>', 128, 8, ['left', 'right', 'up', 'down'], 1, 0.05, 128, 4, 0, ['left', 'right', 'up', 'down'], False, False, 'positive', 'comma', 0, False, False, '', '<p style="margin-bottom:0.75em">Will upscale the image by the selected scale factor; use width and height sliders to set tile size</p>', 64, 0, 2, 1, '', 0, '', 0, '', True, False, False, False, 0) {}
 97%|████████████████████████████████████████████████████████████████████████████▉  | 833M/855M [06:57<00:09, 2.36MB/s]Traceback (most recent call last):                                                 | 42.1M/614M [06:19<1:17:50, 128kB/s]
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\call_queue.py", line 56, in f
    res = list(func(*args, **kwargs))
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\img2img.py", line 171, in img2img
    processed = process_images(p)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\processing.py", line 486, in process_images
    res = process_images_inner(p)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\processing.py", line 632, in process_images_inner
    samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\processing.py", line 1048, in sample
    samples = self.sampler.sample_img2img(self, self.init_latent, x, conditioning, unconditional_conditioning, image_conditioning=self.image_conditioning)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\sd_samplers_kdiffusion.py", line 322, in sample_img2img
    samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\sd_samplers_kdiffusion.py", line 225, in launch_sampling
    return func()
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\sd_samplers_kdiffusion.py", line 322, in <lambda>
    samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\repositories\k-diffusion\k_diffusion\sampling.py", line 150, in sample_euler_ancestral
    denoised = model(x, sigmas[i] * s_in, **extra_args)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\sd_samplers_kdiffusion.py", line 123, in forward
    x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond={"c_crossattn": [cond_in[a:b]], "c_concat": [image_cond_in[a:b]]})
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\repositories\k-diffusion\k_diffusion\external.py", line 167, in forward
    return self.get_v(input * c_in, self.sigma_to_t(sigma), **kwargs) * c_out + input * c_skip
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\repositories\k-diffusion\k_diffusion\external.py", line 177, in get_v
    return self.inner_model.apply_model(x, t, cond)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 17, in <lambda>
    setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 28, in __call__
    return self.__orig_func(*args, **kwargs)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 858, in apply_model
    x_recon = self.model(x_noisy, t, **cond)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1201, in _call_impl
    result = hook(self, input)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\lowvram.py", line 35, in send_me_to_gpu
    module.to(devices.device)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\pytorch_lightning\core\mixins\device_dtype_mixin.py", line 113, in to
    return super().to(*args, **kwargs)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 989, in to
    return self._apply(convert)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 641, in _apply
    module._apply(fn)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 641, in _apply
    module._apply(fn)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 641, in _apply
    module._apply(fn)
  [Previous line repeated 3 more times]
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 664, in _apply
    param_applied = fn(param)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 987, in convert
    return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
RuntimeError: Could not allocate tensor with 117964800 bytes. There is not enough GPU video memory available!

100%|███████████████████████████████████████████████████████████████████████████████| 855M/855M [07:07<00:00, 2.10MB/s]
  7%|█████▎                                                                      | 43.1M/614M [06:29<1:40:29, 99.3kB/s]load checkpoint from D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\models\BLIP\model_base_caption_capfilt_large.pth
                                                                                                                       Downloading CLIP categories...                                                       | 166M/614M [07:34<03:19, 2.36MB/s]
100%|██████████████████████████████████████████████████████████████████████████████| 80.5k/80.5k [00:00<00:00, 778kB/s]
100%|█████████████████████████████████████████████████████████████████████████████| 1.72M/1.72M [00:01<00:00, 1.55MB/s]
100%|█████████████████████████████████████████████████████████████████████████████| 1.57k/1.57k [00:00<00:00, 1.61MB/s]
100%|█████████████████████████████████████████████████████████████████████████████| 2.62k/2.62k [00:00<00:00, 1.34MB/s]
100%|████████████████████████████████████████████████████████████████████████████████| 614M/614M [11:01<00:00, 974kB/s]
Traceback (most recent call last):█████████████████████████████████████████████████▉| 614M/614M [11:01<00:00, 3.93MB/s]
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\gradio\routes.py", line 337, in run_predict
    output = await app.get_blocks().process_api(
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\gradio\blocks.py", line 1015, in process_api
    result = await self.call_function(
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\gradio\blocks.py", line 833, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\anyio\to_thread.py", line 31, in run_sync
    return await get_asynclib().run_sync_in_worker_thread(
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 937, in run_sync_in_worker_thread
    return await future
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 867, in run
    result = context.run(func, *args)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\ui.py", line 915, in <lambda>
    fn=lambda *args: process_interrogate(interrogate_deepbooru, *args),
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\ui.py", line 150, in process_interrogate
    return [interrogation_function(ii_singles[mode]), None]
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\ui.py", line 177, in interrogate_deepbooru
    prompt = deepbooru.model.tag(image)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\deepbooru.py", line 44, in tag
    self.start()
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\deepbooru.py", line 36, in start
    self.model.to(devices.device)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 989, in to
    return self._apply(convert)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 641, in _apply
    module._apply(fn)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 664, in _apply
    param_applied = fn(param)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 987, in convert
    return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
RuntimeError: Could not allocate tensor with 1048576 bytes. There is not enough GPU video memory available!

RX 570 4GB
AMD Ryzen 5 3500
RAM 8GB

No response

[Bug]: Launching Web UI with arguments Fails (Even in Clone method)

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

As i had submitted a previous issue, The process fails, Even after using the CLONE method.

I get same error with CLONE method, Just as in Zip method, Have posted the log below

Steps to reproduce the problem

All steps

What should have happened?

Web UI IP

Commit where the problem happens

Everywhere

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

None

List of extensions

None

Console logs

Creating venv in directory C:\Users\deepn\Downloads\Stable Diffusion Stuf\stable-diffusion-webui-directml\venv using python "C:\Users\deepn\AppData\Local\Programs\Python\Python310\python.exe"
venv "C:\Users\deepn\Downloads\Stable Diffusion Stuf\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash: f64ad25386ad77d1e07986a204dac923b9a46894
Installing torch and torchvision
Collecting torch==1.13.1
  Using cached torch-1.13.1-cp310-cp310-win_amd64.whl (162.6 MB)
Collecting torchvision==0.14.1
  Using cached torchvision-0.14.1-cp310-cp310-win_amd64.whl (1.1 MB)
Collecting torch-directml
  Using cached torch_directml-0.1.13.1.dev230301-cp310-cp310-win_amd64.whl (7.4 MB)
Collecting typing-extensions
  Using cached typing_extensions-4.5.0-py3-none-any.whl (27 kB)
Collecting pillow!=8.3.*,>=5.3.0
  Using cached Pillow-9.4.0-cp310-cp310-win_amd64.whl (2.5 MB)
Collecting requests
  Using cached requests-2.28.2-py3-none-any.whl (62 kB)
Collecting numpy
  Using cached numpy-1.24.2-cp310-cp310-win_amd64.whl (14.8 MB)
Collecting charset-normalizer<4,>=2
  Using cached charset_normalizer-3.1.0-cp310-cp310-win_amd64.whl (97 kB)
Collecting idna<4,>=2.5
  Using cached idna-3.4-py3-none-any.whl (61 kB)
Collecting urllib3<1.27,>=1.21.1
  Using cached urllib3-1.26.15-py2.py3-none-any.whl (140 kB)
Collecting certifi>=2017.4.17
  Using cached certifi-2022.12.7-py3-none-any.whl (155 kB)
Installing collected packages: urllib3, typing-extensions, pillow, numpy, idna, charset-normalizer, certifi, torch, requests, torchvision, torch-directml
Successfully installed certifi-2022.12.7 charset-normalizer-3.1.0 idna-3.4 numpy-1.24.2 pillow-9.4.0 requests-2.28.2 torch-1.13.1 torch-directml-0.1.13.1.dev230301 torchvision-0.14.1 typing-extensions-4.5.0 urllib3-1.26.15

[notice] A new release of pip available: 22.2.1 -> 23.0.1
[notice] To update, run: C:\Users\deepn\Downloads\Stable Diffusion Stuf\stable-diffusion-webui-directml\venv\Scripts\python.exe -m pip install --upgrade pip
Installing gfpgan
Installing clip
Installing open_clip
Cloning Taming Transformers into C:\Users\deepn\Downloads\Stable Diffusion Stuf\stable-diffusion-webui-directml\repositories\taming-transformers...
Cloning CodeFormer into C:\Users\deepn\Downloads\Stable Diffusion Stuf\stable-diffusion-webui-directml\repositories\CodeFormer...
Cloning BLIP into C:\Users\deepn\Downloads\Stable Diffusion Stuf\stable-diffusion-webui-directml\repositories\BLIP...
Installing requirements for CodeFormer
Installing requirements for Web UI
Launching Web UI with arguments:
Traceback (most recent call last):
  File "C:\Users\deepn\Downloads\Stable Diffusion Stuf\stable-diffusion-webui-directml\launch.py", line 377, in <module>
    start()
  File "C:\Users\deepn\Downloads\Stable Diffusion Stuf\stable-diffusion-webui-directml\launch.py", line 368, in start
    import webui
  File "C:\Users\deepn\Downloads\Stable Diffusion Stuf\stable-diffusion-webui-directml\webui.py", line 15, in <module>
    from modules import paths, timer, import_hook, errors
  File "C:\Users\deepn\Downloads\Stable Diffusion Stuf\stable-diffusion-webui-directml\modules\paths.py", line 26, in <module>
    assert sd_path is not None, "Couldn't find Stable Diffusion in any of: " + str(possible_sd_paths)
AssertionError: Couldn't find Stable Diffusion in any of: ['C:\\Users\\deepn\\Downloads\\Stable Diffusion Stuf\\stable-diffusion-webui-directml\\repositories/stable-diffusion-stability-ai', '.', 'C:\\Users\\deepn\\Downloads\\Stable Diffusion Stuf']
Press any key to continue . . .

Additional information

No response

[Bug]: Can't run it due to torch_directml_native problem

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

when I run webui.bat I encountered error due to I don't have torch_directml, after I installed it now this message comes
Traceback (most recent call last):
File "stable-diffusion-webui-directml\launch.py", line 353, in
start()
File "stable-diffusion-webui-directml\launch.py", line 344, in start
import webui
File "stable-diffusion-webui-directml\webui.py", line 31, in
from modules import extra_networks, ui_extra_networks_checkpoints
File "stable-diffusion-webui-directml\modules\ui_extra_networks_checkpoints.py", line 5, in
from modules import shared, ui_extra_networks, sd_models
File "stable-diffusion-webui-directml\modules\shared.py", line 12, in
import modules.interrogate
File "stable-diffusion-webui-directml\modules\interrogate.py", line 15, in
from modules import devices, paths, shared, lowvram, modelloader, errors
File "D:\BACKUP11\App\stable-diffusion-webui-directml\modules\devices.py", line 4, in
import torch_directml
File "stable-diffusion-webui-directml\venv\lib\site-packages\torch_directml_init_.py", line 16, in
import torch_directml_native
ModuleNotFoundError: No module named 'torch_directml_native'

And I can't find any source using torch_directml_native

Steps to reproduce the problem

Open webui.bat and run the code

What should have happened?

The code should normally run the ui

Commit where the problem happens

ae337fa

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Mozilla Firefox

Command Line Arguments

NO

List of extensions

Console logs

venv "D:\BACKUP11\App\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash: ae337fa39b6d4598b377ff312c53b14c15142331
Installing requirements for Web UI
Launching Web UI with arguments:
Traceback (most recent call last):
  File "D:\BACKUP11\App\stable-diffusion-webui-directml\launch.py", line 353, in <module>
    start()
  File "D:\BACKUP11\App\stable-diffusion-webui-directml\launch.py", line 344, in start
    import webui
  File "D:\BACKUP11\App\stable-diffusion-webui-directml\webui.py", line 31, in <module>
    from modules import extra_networks, ui_extra_networks_checkpoints
  File "D:\BACKUP11\App\stable-diffusion-webui-directml\modules\ui_extra_networks_checkpoints.py", line 5, in <module>
    from modules import shared, ui_extra_networks, sd_models
  File "D:\BACKUP11\App\stable-diffusion-webui-directml\modules\shared.py", line 12, in <module>
    import modules.interrogate
  File "D:\BACKUP11\App\stable-diffusion-webui-directml\modules\interrogate.py", line 15, in <module>
    from modules import devices, paths, shared, lowvram, modelloader, errors
  File "D:\BACKUP11\App\stable-diffusion-webui-directml\modules\devices.py", line 4, in <module>
    import torch_directml
  File "D:\BACKUP11\App\stable-diffusion-webui-directml\venv\lib\site-packages\torch_directml\__init__.py", line 16, in <module>
    import torch_directml_native
ModuleNotFoundError: No module named 'torch_directml_native'
Press any key to continue . . .

Additional information

No response

[Bug]: Can not finish generating an image on my 6900xt

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

On my 6900xt after following the installation guide above, i cant seem to finish generating a 512x512 image.

even with the parameter -opt-split-attention-v1

I get to the final step then i receive the following error:

NotImplementedError: No operator found for memory_efficient_attention_forward with inputs:
query : shape=(1, 4096, 1, 512) (torch.float16)
key : shape=(1, 4096, 1, 512) (torch.float16)
value : shape=(1, 4096, 1, 512) (torch.float16)
attn_bias : <class 'NoneType'>
p : 0.0
cutlassF is not supported because:
device=privateuseone (supported: {'cuda'})
flshattF is not supported because:
device=privateuseone (supported: {'cuda'})
max(query.shape[-1] != value.shape[-1]) > 128
tritonflashattF is not supported because:
device=privateuseone (supported: {'cuda'})
max(query.shape[-1] != value.shape[-1]) > 128
triton is not available
smallkF is not supported because:
device=privateuseone (supported: {'cuda', 'cpu'})
dtype=torch.float16 (supported: {torch.float32})
max(query.shape[-1] != value.shape[-1]) > 32
unsupported embed per head: 512

the folder outputs does not even get created. it just fails there.

The image generation process is working tho, as I can see the previews of the steps running in the interface.

Steps to reproduce the problem

Go to stable-diffusion-webui-directml
follow instructions to install on AMD machines
Run webui-user.bat
Open the browser interface, write any prompt and hit generate.
At step 20/20 the error comes out.

What should have happened?

The image should have finished generating, an outputs folder should have been created and the image sxhould have been saved there.

Commit where the problem happens

Commit hash: 3e85552

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Mozilla Firefox

Command Line Arguments

@echo off

set PYTHON=
set GIT=
set VENV_DIR=
set COMMANDLINE_ARGS=--xformers --opt-split-attention-v1

call webui.bat

List of extensions

Console logs

venv "C:\Users\xxxxx\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash: 3e8555242836192c9e3e79c91962418e1f51d5d6
Installing requirements for Web UI
Launching Web UI with arguments: --xformers --opt-split-attention-v1
Interrogations are fallen back to cpu. This doesn't affect on image generation. But if you want to use interrogate (CLIP or DeepBooru), check out this issue: https://github.com/lshqqytiger/stable-diffusion-webui-directml/issues/10
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:
    PyTorch 1.13.1+cu117 with CUDA 1107 (you have 1.13.1+cpu)
    Python  3.10.9 (you have 3.10.6)
  Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)
  Memory-efficient attention, SwiGLU, sparse and more won't be available.
  Set XFORMERS_MORE_DETAILS=1 for more details
Loading weights [c35782bad8] from C:\Users\xxxxx\stable-diffusion-webui-directml\models\Stable-diffusion\realisticVisionV13_v13.safetensors
Creating model from config: C:\Users\xxxxx\stable-diffusion-webui-directml\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying v1 cross attention optimization.
Textual inversion embeddings loaded(0):
Model loaded in 4.0s (load weights from disk: 0.2s, create model: 0.5s, apply weights to model: 1.6s, apply half(): 0.7s, move model to device: 1.0s).
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:08<00:00,  2.43it/s]
Error completing request███████████████████████████████████████████████████████████████| 20/20 [00:06<00:00,  3.40it/s]
Arguments: ('task(ywze92bbldj89a2)', 'cute cat', '', [], 20, 0, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0) {}
Traceback (most recent call last):
  File "C:\Users\xxxxx\stable-diffusion-webui-directml\modules\call_queue.py", line 56, in f
    res = list(func(*args, **kwargs))
  File "C:\Users\xxxxx\stable-diffusion-webui-directml\modules\call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "C:\Users\xxxxx\stable-diffusion-webui-directml\modules\txt2img.py", line 56, in txt2img
    processed = process_images(p)
  File "C:\Users\xxxxx\stable-diffusion-webui-directml\modules\processing.py", line 486, in process_images
    res = process_images_inner(p)
  File "C:\Users\xxxxx\stable-diffusion-webui-directml\modules\processing.py", line 634, in process_images_inner
    x_samples_ddim = [decode_first_stage(p.sd_model, samples_ddim[i:i+1].to(dtype=devices.dtype_vae))[0].cpu() for i in range(samples_ddim.size(0))]
  File "C:\Users\xxxxx\stable-diffusion-webui-directml\modules\processing.py", line 634, in <listcomp>
    x_samples_ddim = [decode_first_stage(p.sd_model, samples_ddim[i:i+1].to(dtype=devices.dtype_vae))[0].cpu() for i in range(samples_ddim.size(0))]
  File "C:\Users\xxxxx\stable-diffusion-webui-directml\modules\processing.py", line 423, in decode_first_stage
    x = model.decode_first_stage(x)
  File "C:\Users\xxxxx\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 17, in <lambda>
    setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
  File "C:\Users\xxxxx\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 28, in __call__
    return self.__orig_func(*args, **kwargs)
  File "C:\Users\xxxxx\stable-diffusion-webui-directml\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "C:\Users\xxxxx\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 826, in decode_first_stage
    return self.first_stage_model.decode(z)
  File "C:\Users\xxxxx\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\autoencoder.py", line 90, in decode
    dec = self.decoder(z)
  File "C:\Users\xxxxx\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\Users\xxxxx\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\model.py", line 631, in forward
    h = self.mid.attn_1(h)
  File "C:\Users\xxxxx\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\Users\xxxxx\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\model.py", line 258, in forward
    out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=None, op=self.attention_op)
  File "C:\Users\xxxxx\stable-diffusion-webui-directml\venv\lib\site-packages\xformers\ops\fmha\__init__.py", line 197, in memory_efficient_attention
    return _memory_efficient_attention(
  File "C:\Users\xxxxx\stable-diffusion-webui-directml\venv\lib\site-packages\xformers\ops\fmha\__init__.py", line 293, in _memory_efficient_attention
    return _memory_efficient_attention_forward(
  File "C:\Users\xxxxx\stable-diffusion-webui-directml\venv\lib\site-packages\xformers\ops\fmha\__init__.py", line 309, in _memory_efficient_attention_forward
    op = _dispatch_fw(inp)
  File "C:\Users\xxxxx\stable-diffusion-webui-directml\venv\lib\site-packages\xformers\ops\fmha\dispatch.py", line 95, in _dispatch_fw
    return _run_priority_list(
  File "C:\Users\xxxxx\stable-diffusion-webui-directml\venv\lib\site-packages\xformers\ops\fmha\dispatch.py", line 70, in _run_priority_list
    raise NotImplementedError(msg)
NotImplementedError: No operator found for `memory_efficient_attention_forward` with inputs:
     query       : shape=(1, 4096, 1, 512) (torch.float16)
     key         : shape=(1, 4096, 1, 512) (torch.float16)
     value       : shape=(1, 4096, 1, 512) (torch.float16)
     attn_bias   : <class 'NoneType'>
     p           : 0.0
`cutlassF` is not supported because:
    device=privateuseone (supported: {'cuda'})
`flshattF` is not supported because:
    device=privateuseone (supported: {'cuda'})
    max(query.shape[-1] != value.shape[-1]) > 128
`tritonflashattF` is not supported because:
    device=privateuseone (supported: {'cuda'})
    max(query.shape[-1] != value.shape[-1]) > 128
    triton is not available
`smallkF` is not supported because:
    device=privateuseone (supported: {'cuda', 'cpu'})
    dtype=torch.float16 (supported: {torch.float32})
    max(query.shape[-1] != value.shape[-1]) > 32
    unsupported embed per head: 512

Additional information

No response

[Bug]: The interface have a 0,5s of delay when clicking on any button or when typing.

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

When I click on any button, or tab, or when typing the prompt, the interface have a "new" small delay of 0.5s latency.

Steps to reproduce the problem

Click on any button, tab, or write anything with the UI

What should have happened?

No delay, especially when typing text.

Commit where the problem happens

41d5450

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Mozilla Firefox

Command Line Arguments

--medvram --no-half --precision full --no-half-vae --opt-sub-quad-attention --opt-split-attention-v1

List of extensions

Console logs

Python 3.10.7 (tags/v3.10.7:6cc6b13, Sep  5 2022, 14:08:36) [MSC v.1933 64 bit (AMD64)]
Commit hash: 41d5450a0a559469b354fd56cac0fe1ab3cf2f40
Installing requirements for Web UI
Launching Web UI with arguments: --medvram --no-half --precision full --no-half-vae --opt-sub-quad-attention --opt-split-attention-v1
Interrogations are fallen back to cpu. This doesn't affect on image generation. But if you want to use interrogate (CLIP or DeepBooru), check out this issue: https://github.com/lshqqytiger/stable-diffusion-webui-directml/issues/10
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
Loading weights [a64810e2e1] from D:\Super Stable Diffusion 2.0\stable-diffusion-webui-amd\stable-diffusion-webui-directml\models\Stable-diffusion\clarity_19.safetensors
Creating model from config: D:\Super Stable Diffusion 2.0\stable-diffusion-webui-amd\stable-diffusion-webui-directml\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying sub-quadratic cross attention optimization.
Textual inversion embeddings loaded(0):
Textual inversion embeddings skipped(3): nartfixer, nfixer, nrealfixer
Model loaded in 76.2s (load weights from disk: 17.5s, load config: 0.4s, create model: 3.4s, apply weights to model: 54.5s, load textual inversion embeddings: 0.3s).
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 133.6s (import torch: 26.1s, import gradio: 10.9s, import ldm: 1.8s, other imports: 12.9s, list extensions: 0.2s, list SD models: 0.3s, setup codeformer: 0.9s, list builtin upscalers: 0.6s, load scripts: 2.4s, load SD checkpoint: 76.5s, create ui: 0.5s, gradio launch: 0.4s).

Additional information

No response

[Bug]: Unable to load the model with the. safensere suffix

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

An exception occurs when a model with the suffix. safesensors is in the model library.Expecting value: line 1 column 1 (char 0)

Steps to reproduce the problem

safesensors in model

What should have happened?

Does the current version temporarily not support the model with the suffix. safesensors？

Commit where the problem happens

choose model

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

ython launch.py --precision full --no-half --lowvram --share

List of extensions

none

Console logs

Expecting value: line 1 column 1 (char 0)

Additional information

No response

[Bug]: RuntimeError: The GPU device instance has been suspended. Use GetDeviceRemovedReason to determine the appropriate action.

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

started the ui up with the following arguments: --lowvram --opt-split-attention --precision full --no-half
It started up just fine, loaded the model well, and then it generated the picture fine until 100%, after which it gave me this sprawling error:

100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [12:23<00:00, 37.18s/it]
Error completing request███████████████████████████████████████████████████████████████| 20/20 [11:36<00:00, 43.12s/it]
Arguments: ('task(cv2lpkdnznq2b01)', 'cactus', 'person, people', [], 20, 0, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0) {}
Traceback (most recent call last):
File "E:\stable-diffusion-webui-directml\modules\call_queue.py", line 56, in f
res = list(func(*args, **kwargs))
File "E:\stable-diffusion-webui-directml\modules\call_queue.py", line 37, in f
res = func(*args, **kwargs)
File "E:\stable-diffusion-webui-directml\modules\txt2img.py", line 56, in txt2img
processed = process_images(p)
File "E:\stable-diffusion-webui-directml\modules\processing.py", line 486, in process_images
res = process_images_inner(p)
File "E:\stable-diffusion-webui-directml\modules\processing.py", line 634, in process_images_inner
x_samples_ddim = [decode_first_stage(p.sd_model, samples_ddim[i:i+1].to(dtype=devices.dtype_vae))[0].cpu() for i in range(samples_ddim.size(0))]
File "E:\stable-diffusion-webui-directml\modules\processing.py", line 634, in
x_samples_ddim = [decode_first_stage(p.sd_model, samples_ddim[i:i+1].to(dtype=devices.dtype_vae))[0].cpu() for i in range(samples_ddim.size(0))]
File "E:\stable-diffusion-webui-directml\modules\processing.py", line 423, in decode_first_stage
x = model.decode_first_stage(x)
File "E:\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 17, in
setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
File "E:\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 28, in call
return self.__orig_func(*args, **kwargs)
File "E:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "E:\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 826, in decode_first_stage
return self.first_stage_model.decode(z)
File "E:\stable-diffusion-webui-directml\modules\lowvram.py", line 52, in first_stage_model_decode_wrap
return first_stage_model_decode(z)
File "E:\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\autoencoder.py", line 90, in decode
dec = self.decoder(z)
File "E:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "E:\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\model.py", line 649, in forward
h = self.conv_out(h)
File "E:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "E:\stable-diffusion-webui-directml\extensions-builtin\Lora\lora.py", line 182, in lora_Conv2d_forward
return lora_forward(self, input, torch.nn.Conv2d_forward_before_lora(self, input))
File "E:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\conv.py", line 463, in forward
return self._conv_forward(input, self.weight, self.bias)
File "E:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\conv.py", line 459, in _conv_forward
return F.conv2d(input, weight, bias, self.stride,
RuntimeError: The GPU device instance has been suspended. Use GetDeviceRemovedReason to determine the appropriate action.

So far I have tried re-installing all of the dependencies and the ui. still gave me this error

Steps to reproduce the problem

open stable-diffusion-webui-directml folder, and open the webui-user.bat file (Running on ssd drive)

2.load the ui w/ anything v4.5 ckpt

3.generate a picture

tada! an error!

What should have happened?

finished processing the picture.

Commit where the problem happens

6a6dd58

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

--lowvram --opt-split-attention --precision full --no-half

List of extensions

Lastpass

Console logs

venv "E:\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.9 (tags/v3.10.9:1dd9be6, Dec  6 2022, 20:01:21) [MSC v.1934 64 bit (AMD64)]
Commit hash: 6a6dd5879811156baeea3a1c5b8c6aa306ec9dd9
Installing requirements for Web UI
Launching Web UI with arguments: --lowvram --opt-split-attention --precision full --no-half
Warning: experimental graphic memory optimization is disabled due to gpu vendor. Currently this optimization is only available for AMDGPUs.
Disabled experimental graphic memory optimizations.
Interrogate will be fallen back to cpu. Because DirectML device does not support it.
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
Loading weights [e4b17ce185] from E:\stable-diffusion-webui-directml\models\Stable-diffusion\anything-v4.5-pruned.ckpt
Creating model from config: E:\stable-diffusion-webui-directml\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying cross attention optimization (Doggettx).
Textual inversion embeddings loaded(0):
Model loaded in 103.4s (load weights from disk: 100.7s, create model: 1.3s, apply weights to model: 1.2s).
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [12:23<00:00, 37.18s/it]
Error completing request███████████████████████████████████████████████████████████████| 20/20 [11:36<00:00, 43.12s/it]
Arguments: ('task(cv2lpkdnznq2b01)', 'cactus', 'person, people', [], 20, 0, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0) {}
Traceback (most recent call last):
  File "E:\stable-diffusion-webui-directml\modules\call_queue.py", line 56, in f
    res = list(func(*args, **kwargs))
  File "E:\stable-diffusion-webui-directml\modules\call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "E:\stable-diffusion-webui-directml\modules\txt2img.py", line 56, in txt2img
    processed = process_images(p)
  File "E:\stable-diffusion-webui-directml\modules\processing.py", line 486, in process_images
    res = process_images_inner(p)
  File "E:\stable-diffusion-webui-directml\modules\processing.py", line 634, in process_images_inner
    x_samples_ddim = [decode_first_stage(p.sd_model, samples_ddim[i:i+1].to(dtype=devices.dtype_vae))[0].cpu() for i in range(samples_ddim.size(0))]
  File "E:\stable-diffusion-webui-directml\modules\processing.py", line 634, in <listcomp>
    x_samples_ddim = [decode_first_stage(p.sd_model, samples_ddim[i:i+1].to(dtype=devices.dtype_vae))[0].cpu() for i in range(samples_ddim.size(0))]
  File "E:\stable-diffusion-webui-directml\modules\processing.py", line 423, in decode_first_stage
    x = model.decode_first_stage(x)
  File "E:\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 17, in <lambda>
    setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
  File "E:\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 28, in __call__
    return self.__orig_func(*args, **kwargs)
  File "E:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "E:\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 826, in decode_first_stage
    return self.first_stage_model.decode(z)
  File "E:\stable-diffusion-webui-directml\modules\lowvram.py", line 52, in first_stage_model_decode_wrap
    return first_stage_model_decode(z)
  File "E:\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\autoencoder.py", line 90, in decode
    dec = self.decoder(z)
  File "E:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "E:\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\model.py", line 649, in forward
    h = self.conv_out(h)
  File "E:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "E:\stable-diffusion-webui-directml\extensions-builtin\Lora\lora.py", line 182, in lora_Conv2d_forward
    return lora_forward(self, input, torch.nn.Conv2d_forward_before_lora(self, input))
  File "E:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\conv.py", line 463, in forward
    return self._conv_forward(input, self.weight, self.bias)
  File "E:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\conv.py", line 459, in _conv_forward
    return F.conv2d(input, weight, bias, self.stride,
RuntimeError: The GPU device instance has been suspended. Use GetDeviceRemovedReason to determine the appropriate action.

Additional information

[Bug]: The output img is not dirordered

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

The enviroment was successfully set up , but the output is not right, any suggetions?

Equipments:
amd radeon r5 m315 2g memory

Steps to reproduce the problem

What should have happened?

output

Commit where the problem happens

python: 3.10.6 • torch: 1.13.1+cpu • xformers: N/A • gradio: 3.16.2 • commit: ff55834 • checkpoint: fe4efff1e1

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Microsoft Edge

Command Line Arguments

--lowvram

List of extensions

LDSR [built-in]
Lora [built-in]
ScuNET [built-in]
SwinIR [built-in]
prompt-bracket-checker [built-in]

Console logs

Installing requirements for Web UI

Launching Web UI with arguments: --lowvram

Interrogations are fallen back to cpu. This doesn't affect on image generation. But if you want to use interrogate (CLIP or DeepBooru), check out this issue: https://github.com/lshqqytiger/stable-diffusion-webui-directml/issues/10

Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled

No module 'xformers'. Proceeding without it.

Loading weights [fe4efff1e1] from F:\python\python310\projects\stable-diffusion-webui-directml\models\Stable-diffusion\sd-v1-4.ckpt

Creating model from config: F:\python\python310\projects\stable-diffusion-webui-directml\configs\v1-inference.yaml

LatentDiffusion: Running in eps-prediction mode

DiffusionWrapper has 859.52 M params.

Applying cross attention optimization (InvokeAI).

Textual inversion embeddings loaded(0):
Model loaded in 1723.7s (load weights from disk: 67.4s, find config: 0.2s, load config: 0.7s, create model: 67.5s, apply weights to model: 1190.1s, apply half(): 383.3s, apply dtype to VAE: 1.0s, load VAE: 4.0s, move model to device: 1.3s, hijack: 3.1s, load textual inversion embeddings: 5.1s, scripts callbacks: 0.2s).

Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
 10%|████████▎                                                                          | 2/20 [03:03<27:32, 91.81s/it]
Total progress:  10%|██████▋                                                            | 2/20 [02:14<20:07, 67.11s/it]
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [16:56<00:00, 50.83s/it]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [16:19<00:00, 48.95s/it]

Additional information

I tried these:
arguments --lowvram --no-half same error
model v1-5-pruned-emaonly.safetensors same error

[Bug]: Sketch/Inpaint sketch bug

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

Sketch and inpaint sketch become unusable if you're using the "Copy image to..." feature. It works fine when dragging and dropping the file from outside source.

Steps to reproduce the problem

Add a reference picture to img2img
Press "Copy image to sketch or inpaint sketch"
Experience the ungodly amount of lag

What should have happened?

Should work without any lag.

Commit where the problem happens

ae337fa

What platforms do you use to access the UI ?

No response

What browsers do you use to access the UI

Brave browser

Command Line Arguments

set COMMANDLINE_ARGS=--medvram --precision full --no-half --no-half-vae --opt-split-attention --opt-sub-quad-attention --disable-nan-check --autolaunch --api
set SAFETENSORS_FAST_GPU=1

List of extensions

auto-sd-paint-ext-main
multi-subject-render
sd-dynamic-thresholding
sd-webui-aspect-ratio-helper
sd-webui-controlnet
stable-diffusion-webui-images-browser
stable-diffusion-webui-rembg
stable-diffusion-webui-sonar
stable-diffusion-webui-wd14-tagger
ultimate-upscale-for-automatic1111
LDSR
Lora
ScuNET
SwinIR
prompt-bracket-checker

Console logs

Can't provide

Additional information

No response

Bug]: Error with webui-user

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

I followed the steps provided, and tried to launch the webui-user bat file and got the following error (see below)

Steps to reproduce the problem

venv "E:\SD\stable-diffusion-webui-directml\venv\Scripts\Python.exe"

INCOMPATIBLE PYTHON VERSION

This program is tested with 3.10.6 Python, but you have 3.11.2.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.

You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3109/

Alternatively, use a binary release of WebUI: https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases

Use --skip-python-version-check to suppress this warning.

Python 3.11.2 (tags/v3.11.2:878ead1, Feb 7 2023, 16:38:35) [MSC v.1934 64 bit (AMD64)]
Commit hash: f64ad25
Installing torch and torchvision
ERROR: Could not find a version that satisfies the requirement torch==1.13.1 (from versions: 2.0.0)
ERROR: No matching distribution found for torch==1.13.1

[notice] A new release of pip available: 22.3.1 -> 23.0.1
[notice] To update, run: E:\SD\stable-diffusion-webui-directml\venv\Scripts\python.exe -m pip install --upgrade pip
Traceback (most recent call last):
File "E:\SD\stable-diffusion-webui-directml\launch.py", line 376, in
prepare_environment()
File "E:\SD\stable-diffusion-webui-directml\launch.py", line 285, in prepare_environment
run(f'"{python}" -m {torch_command}', "Installing torch and torchvision", "Couldn't install torch", live=True)
File "E:\SD\stable-diffusion-webui-directml\launch.py", line 97, in run
raise RuntimeError(f"""{errdesc or 'Error running command'}.
RuntimeError: Couldn't install torch.
Command: "E:\SD\stable-diffusion-webui-directml\venv\Scripts\python.exe" -m pip install torch==1.13.1 torchvision==0.14.1 torch-directml
Error code: 1
Press any key to continue . . .

What should have happened?

Pytorch should have installed - could not fetch it.

Commit where the problem happens

Happens when I try to launch webui-user

What platforms do you use to access the UI ?

No response

What browsers do you use to access the UI ?

No response

Command Line Arguments

No

List of extensions

Console logs

venv "E:\SD\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
==============================================================================================================
INCOMPATIBLE PYTHON VERSION

This program is tested with 3.10.6 Python, but you have 3.11.2.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.

You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3109/

Alternatively, use a binary release of WebUI: https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases

Use --skip-python-version-check to suppress this warning.
==============================================================================================================
Python 3.11.2 (tags/v3.11.2:878ead1, Feb  7 2023, 16:38:35) [MSC v.1934 64 bit (AMD64)]
Commit hash: f64ad25386ad77d1e07986a204dac923b9a46894
Installing torch and torchvision
ERROR: Could not find a version that satisfies the requirement torch==1.13.1 (from versions: 2.0.0)
ERROR: No matching distribution found for torch==1.13.1

[notice] A new release of pip available: 22.3.1 -> 23.0.1
[notice] To update, run: E:\SD\stable-diffusion-webui-directml\venv\Scripts\python.exe -m pip install --upgrade pip
Traceback (most recent call last):
  File "E:\SD\stable-diffusion-webui-directml\launch.py", line 376, in <module>
    prepare_environment()
  File "E:\SD\stable-diffusion-webui-directml\launch.py", line 285, in prepare_environment
    run(f'"{python}" -m {torch_command}', "Installing torch and torchvision", "Couldn't install torch", live=True)
  File "E:\SD\stable-diffusion-webui-directml\launch.py", line 97, in run
    raise RuntimeError(f"""{errdesc or 'Error running command'}.
RuntimeError: Couldn't install torch.
Command: "E:\SD\stable-diffusion-webui-directml\venv\Scripts\python.exe" -m pip install torch==1.13.1 torchvision==0.14.1 torch-directml
Error code: 1
Press any key to continue . . .

Additional information

No response

Could not allocate tensor with 377487360 bytes. There is not enough GPU video memory available!

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

Stable diffusion crash, after generating some pixel and appear error : Could not allocate tensor with 377487360 bytes. There is not enough GPU video memory available!

Steps to reproduce the problem

Go to Text2Img
Insert prompt and negative promt
Generating

What should have happened?

Stable diffusion running normally, and generating some image

Commit where the problem happens

RuntimeError: Could not allocate tensor with 377487360 bytes. There is not enough GPU video memory available!

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Microsoft Edge

Command Line Arguments

--lowvram --disable-nan-check --autolaunch --no-half

List of extensions

Console logs

venv "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash: ff558348682fea569785dcfae1f1282cfbefda6b
Installing requirements for Web UI
Launching Web UI with arguments: --lowvram --disable-nan-check --autolaunch --no-half
Warning: experimental graphic memory optimization is disabled due to gpu vendor. Currently this optimization is only available for AMDGPUs.
Disabled experimental graphic memory optimizations.
Interrogations are fallen back to cpu. This doesn't affect on image generation. But if you want to use interrogate (CLIP or DeepBooru), check out this issue: https://github.com/lshqqytiger/stable-diffusion-webui-directml/issues/10
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
Loading weights [bfcaf07557] from D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\models\Stable-diffusion\768-v-ema.ckpt
Creating model from config: D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\configs\stable-diffusion\v2-inference-v.yaml
LatentDiffusion: Running in v-prediction mode
DiffusionWrapper has 865.91 M params.
Applying cross attention optimization (InvokeAI).
Textual inversion embeddings loaded(0):
Model loaded in 235.4s (load weights from disk: 133.7s, find config: 48.2s, load config: 0.3s, create model: 3.4s, apply weights to model: 40.4s, apply dtype to VAE: 0.8s, load VAE: 2.6s, move model to device: 5.0s, hijack: 0.1s, load textual inversion embeddings: 0.8s).
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Calculating sha256 for D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\models\Stable-diffusion\aresMix_v01.safetensors: 6ecece11bf069e9950746d33ab346826c5352acf047c64a3ab74c8884924adf0
Loading weights [6ecece11bf] from D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\models\Stable-diffusion\aresMix_v01.safetensors
Creating model from config: D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying cross attention optimization (InvokeAI).
Model loaded in 42.4s (create model: 1.7s, apply weights to model: 40.2s, load textual inversion embeddings: 0.2s).
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [02:48<00:00,  8.41s/it]
Error completing request███████████████████████████████████████████████████████████████| 20/20 [02:05<00:00,  6.39s/it]
Arguments: ('task(c6cyhnv8oj55v19)', 'photo of a 22 years old Japanese girl, detailed facial features, beautiful detailed face, perfect face, dreamy face expression, high detailed skin, white skin texture, detailed eyes, seductive eyes, alluring eyes, beautiful eyes, full red lips, hourglass body, perfect body, skinny, petite, red pussy, showing pussy, nude, small breast, sitting, hijab, hijab, elegant, sexually suggestive, sex appeal, seductive look, bedroom, submissive, fantasy environment, magical atmosphere, dramatic style, golden hour, embers swirling, soft lighting, volumetric lighting, realistic lighting, cinematic lighting, natural lighting, long exposure trails, hyper detailed, sharp focus, bokeh, masterpiece, award winning photograph, epic character composition,Key light, backlight, soft natural lighting, photography 800 ISO film grain 50mm lens RAW aperture f1.6, highly detailed, Girl, full body, full body view, full body shoot, full body photograph', '(asian:1.2), black and white, sepia, bad art, b&w, canvas frame, cartoon, 3d, Photoshop, video game, 3d render, semi-realistic, cgi, render, sketch, drawing, anime, worst quality, low quality, jpeg artifacts, duplicate, messy drawing, black-white, doll, illustration, lowres, deformed, disfigured, mutation, amputation, distorted, mutated, mutilated, poorly drawn, bad anatomy, wrong anatomy, bad proportions, gross proportions, double body, long body, unnatural body, extra limb, missing limb, floating limb, disconnected limbs, malformed limbs, missing arms, extra arms, disappearing arms, missing legs, extra legs, broken legs, disappearing legs, deformed thighs, malformed hands, mutated hands and fingers, double hands, extra fingers, poorly drawn hands, mutated hands, fused fingers, too many fingers, poorly drawn feet, poorly drawn hands, big hands, hand with more than 5 fingers, hand with less than 5 fingers, bad feet, poorly drawn feet, fused feet, missing feet, bad knee, extra knee, more than 2 legs, poorly drawn face, cloned face, double face, bad hairs, poorly drawn hairs, fused hairs, cross-eye, ugly eyes, bad eyes, poorly drawn eyes, asymmetric eyes, cross-eyed, ugly mouth, missing teeth, crooked teeth, bad mouth, poorly drawn mouth, dirty teeth, bad tongue, fused ears, bad ears, poorly drawn ears, extra ears, heavy ears, missing ears, poorly drawn breasts, more than 2 nipples, missing nipples, different nipples, fused nipples, bad nipples, poorly drawn nipples, bad asshole, poorly drawn asshole, fused asshole, bad anus, bad pussy, bad crotch, fused anus, fused pussy, poorly drawn crotch, poorly drawn anus, poorly drawn pussy, bad clit, fused clit, fused pantie, poorly drawn pantie, fused cloth, poorly drawn cloth, bad pantie, obese, ugly, disgusting, morbid, big muscles, blurry, censored, oversaturated, watermark, watermarked, extra digit, fewer digits, signature, text', [], 20, 15, False, False, 1, 1, 6, -1.0, -1.0, 0, 0, 0, False, 720, 512, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0) {}
Traceback (most recent call last):
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\call_queue.py", line 56, in f
    res = list(func(*args, **kwargs))
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\txt2img.py", line 56, in txt2img
    processed = process_images(p)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\processing.py", line 486, in process_images
    res = process_images_inner(p)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\processing.py", line 634, in process_images_inner
    x_samples_ddim = [decode_first_stage(p.sd_model, samples_ddim[i:i+1].to(dtype=devices.dtype_vae))[0].cpu() for i in range(samples_ddim.size(0))]
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\processing.py", line 634, in <listcomp>
    x_samples_ddim = [decode_first_stage(p.sd_model, samples_ddim[i:i+1].to(dtype=devices.dtype_vae))[0].cpu() for i in range(samples_ddim.size(0))]
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\processing.py", line 423, in decode_first_stage
    x = model.decode_first_stage(x)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 17, in <lambda>
    setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 28, in __call__
    return self.__orig_func(*args, **kwargs)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 826, in decode_first_stage
    return self.first_stage_model.decode(z)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\modules\lowvram.py", line 52, in first_stage_model_decode_wrap
    return first_stage_model_decode(z)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\autoencoder.py", line 90, in decode
    dec = self.decoder(z)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\model.py", line 637, in forward
    h = self.up[i_level].block[i_block](h, temb)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\model.py", line 132, in forward
    h = nonlinearity(h)
  File "D:\Data Imam\Imam File\web-ui\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\functional.py", line 2059, in silu
    return torch._C._nn.silu(input)
RuntimeError: Could not allocate tensor with 377487360 bytes. There is not enough GPU video memory available!

Additional information

RX 570 4GB
Ryzen 5 3500
RAM 8GB single channel
Driver AMD Software PRO Edition
DirectX 12

[Bug]: Couldn't find Stable Diffusion in any of

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

I followed this guide, opened webui-user.bat and got this error

I've tried to clone this repo git clone https://github.com/Stability-AI/stablediffusion repositories/stable-diffusion-stability-ai to \repositories folder but that leads to "ModuleNotFoundError: No module named 'k_diffusion'" error

Steps to reproduce the problem

Go to ....
Press ....
...

What should have happened?

WeUI should have been launched

Commit where the problem happens

a0f4cd6

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

No

List of extensions

Console logs

venv "C:\Applications\Development\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash: a0f4cd6fdd2b7ef3e2b666694f1a1ca13ee17066
Installing requirements for Web UI
Launching Web UI with arguments:
Memory optimization for DirectML is disabled. Because this is not Windows platform.
Traceback (most recent call last):
  File "C:\Applications\Development\stable-diffusion-webui-directml\launch.py", line 353, in <module>
    start()
  File "C:\Applications\Development\stable-diffusion-webui-directml\launch.py", line 344, in start
    import webui
  File "C:\Applications\Development\stable-diffusion-webui-directml\webui.py", line 15, in <module>
    from modules import import_hook, errors, extra_networks, ui_extra_networks_checkpoints
  File "C:\Applications\Development\stable-diffusion-webui-directml\modules\ui_extra_networks_checkpoints.py", line 6, in <module>
    from modules import shared, ui_extra_networks, sd_models
  File "C:\Applications\Development\stable-diffusion-webui-directml\modules\shared.py", line 12, in <module>
    import modules.interrogate
  File "C:\Applications\Development\stable-diffusion-webui-directml\modules\interrogate.py", line 15, in <module>
    from modules import devices, paths, shared, lowvram, modelloader, errors
  File "C:\Applications\Development\stable-diffusion-webui-directml\modules\paths.py", line 26, in <module>
    assert sd_path is not None, "Couldn't find Stable Diffusion in any of: " + str(possible_sd_paths)
AssertionError: Couldn't find Stable Diffusion in any of: ['C:\\Applications\\Development\\stable-diffusion-webui-directml\\repositories/stable-diffusion-stability-ai', '.', 'C:\\Applications\\Development']

Additional information

No response

[Bug]: VRAM fills up and stays at 100% all the time, then crashes

Is there an existing issue for this?

I have searched the existing issues and checked the recent builds/commits

What happened?

Hey there,

I have serious issues running the program on Windows 11 with an AMD 6900XT.
As soon as I start the rendering the process I can see the dedicated memory usage in GPU-Z climbing up from 4.4 GB idle (WebUI launched, doing nothing) to the maximum of 16 GB. After a few seconds the rendering fails.

RuntimeError: Could not allocate tensor with 4719616 bytes. There is not enough GPU video memory available!

The issue occurs at default settings, 512x512px. Once the VRAM is full it stays at 100% until I exit the cmd.
I have tried every ARGS-command suggested over at Windows + AMD GPUs (DirectML) #7870. No success.

Steps to reproduce the problem

Install on W11 machine following the guide.
Run the UI and a test prompt @ 512px @ default settings.

What should have happened?

Render an image.

Commit where the problem happens

3e85552

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Mozilla Firefox

Command Line Arguments

Everything from "--opt-split-attention-v1 --opt-sub-quad-attention --always-batch-cond-uncond --disable-nan-check --sub-quad-kv-chunk-size 512 --sub-quad-q-chunk-size 512 --sub-quad-chunk-threshold 25 --no-half --no-half-vae --precision full --medvram" to nothing.

List of extensions

Console logs

venv "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.10 (tags/v3.10.10:aad5f6a, Feb  7 2023, 17:20:36) [MSC v.1929 64 bit (AMD64)]
Commit hash: 3e8555242836192c9e3e79c91962418e1f51d5d6
Installing requirements for Web UI
Launching Web UI with arguments:
Interrogations are fallen back to cpu. This doesn't affect on image generation. But if you want to use interrogate (CLIP or DeepBooru), check out this issue: https://github.com/lshqqytiger/stable-diffusion-webui-directml/issues/10
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
No module 'xformers'. Proceeding without it.
Loading weights [88ecb78256] from C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\models\Stable-diffusion\v2-1_512-ema-pruned.ckpt
Creating model from config: C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\models\Stable-diffusion\v2-1_512-ema-pruned.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 865.91 M params.
Applying cross attention optimization (InvokeAI).
Textual inversion embeddings loaded(0):
Model loaded in 5.7s (load weights from disk: 0.9s, create model: 0.1s, apply weights to model: 0.6s, apply half(): 0.6s, move model to device: 3.5s).
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\venv\lib\site-packages\torch\amp\autocast_mode.py:202: UserWarning: User provided device_type of 'cuda', but CUDA is not available. Disabling
  warnings.warn('User provided device_type of \'cuda\', but CUDA is not available. Disabling')
C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\repositories\k-diffusion\k_diffusion\external.py:63: UserWarning: The operator 'aten::linspace.out' is not currently supported on the DML backend and will fall back to run on the CPU. This may have performance implications. (Triggered internally at D:\a\_work\1\s\pytorch-directml-plugin\torch_directml\csrc\dml\dml_cpu_fallback.cpp:17.)
  t = torch.linspace(t_max, 0, n, device=self.sigmas.device)
 30%|██████████████████████████████▌                                                                       | 6/20 [00:29<01:07,  4.85s/it]
Error completing request██████████████████████▊                                                            | 6/20 [00:21<01:03,  4.54s/it]
Arguments: ('task(2xnvnyshi5wky2r)', 'test', '', [], 20, 0, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0) {}
Traceback (most recent call last):
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\modules\call_queue.py", line 56, in f
    res = list(func(*args, **kwargs))
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\modules\call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\modules\txt2img.py", line 56, in txt2img
    processed = process_images(p)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\modules\processing.py", line 486, in process_images
    res = process_images_inner(p)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\modules\processing.py", line 632, in process_images_inner
    samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\modules\processing.py", line 832, in sample
    samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\modules\sd_samplers_kdiffusion.py", line 349, in sample
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\modules\sd_samplers_kdiffusion.py", line 225, in launch_sampling
    return func()
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\modules\sd_samplers_kdiffusion.py", line 349, in <lambda>
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\repositories\k-diffusion\k_diffusion\sampling.py", line 150, in sample_euler_ancestral
    denoised = model(x, sigmas[i] * s_in, **extra_args)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\modules\sd_samplers_kdiffusion.py", line 117, in forward
    x_out = self.inner_model(x_in, sigma_in, cond={"c_crossattn": [cond_in], "c_concat": [image_cond_in]})
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\repositories\k-diffusion\k_diffusion\external.py", line 112, in forward
    eps = self.get_eps(input * c_in, self.sigma_to_t(sigma), **kwargs)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\repositories\k-diffusion\k_diffusion\external.py", line 138, in get_eps
    return self.inner_model.apply_model(*args, **kwargs)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 17, in <lambda>
    setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 28, in __call__
    return self.__orig_func(*args, **kwargs)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 858, in apply_model
    x_recon = self.model(x_noisy, t, **cond)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 1335, in forward
    out = self.diffusion_model(x, t, context=cc)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\openaimodel.py", line 783, in forward
    h = module(h, emb, context)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\openaimodel.py", line 84, in forward
    x = layer(x, context)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\attention.py", line 334, in forward
    x = block(x, context=context[i])
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\attention.py", line 269, in forward
    return checkpoint(self._forward, (x, context), self.parameters(), self.checkpoint)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\util.py", line 114, in checkpoint
    return CheckpointFunction.apply(func, len(inputs), *args)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\util.py", line 129, in forward
    output_tensors = ctx.run_function(*ctx.input_tensors)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\attention.py", line 272, in _forward
    x = self.attn1(self.norm1(x), context=context if self.disable_self_attn else None) + x
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\modules\sd_hijack_optimizations.py", line 246, in split_cross_attention_forward_invokeAI
    r = einsum_op(q, k, v)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\modules\sd_hijack_optimizations.py", line 221, in einsum_op
    return einsum_op_dml(q, k, v)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\modules\sd_hijack_optimizations.py", line 209, in einsum_op_dml
    return einsum_op_tensor_mem(q, k, v, (mem_reserved - mem_active) if mem_reserved > mem_active else 1)
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\modules\sd_hijack_optimizations.py", line 194, in einsum_op_tensor_mem
    return einsum_op_slice_1(q, k, v, max(q.shape[1] // div, 1))
  File "C:\stable-diffusion-webui-directml\stable-diffusion-webui-directml\modules\sd_hijack_optimizations.py", line 169, in einsum_op_slice_1
    r[:, i:end] = einsum_op_compvis(q[:, i:end], k, v)
RuntimeError: Could not allocate tensor with 4719616 bytes. There is not enough GPU video memory available!

Additional information

Thank you for taking the effort to host this project! Seriously. We need more supporters like you! :)