Comments (13)
I also got this error
Doing standard LoRA training, both with 1.5 and 2.1 models.
ImportError: cannot import name 'CompVisVDenoiser' from 'k_diffusion.external'
(C:\Users\Brady\AppData\Local\Programs\Python\Python310\lib\site-packages\k_diffusion\external.py)
[Errno 2] No such file or directory:
'E:\AI\kohya_ss\venv\Scripts\accelerate.exe\main.py'
Console Output
│ E:\AI\kohya_ss\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_stable_diffu │
│ sion_k_diffusion.py:20 in <module> │
│ │
│ 17 │
│ 18 import torch │
│ 19 │
│ ❱ 20 from k_diffusion.external import CompVisDenoiser, CompVisVDenoiser │
│ 21 │
│ 22 from ... import DiffusionPipeline │
│ 23 from ...schedulers import LMSDiscreteScheduler │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
ImportError: cannot import name 'CompVisVDenoiser' from 'k_diffusion.external'
(C:\Users\Brady\AppData\Local\Programs\Python\Python310\lib\site-packages\k_diffusion\external.py)
╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ C:\Users\Brady\AppData\Local\Programs\Python\Python310\lib\runpy.py:196 in _run_module_as_main │
│ │
│ 193 │ main_globals = sys.modules["__main__"].__dict__ │
│ 194 │ if alter_argv: │
│ 195 │ │ sys.argv[0] = mod_spec.origin │
│ ❱ 196 │ return _run_code(code, main_globals, None, │
│ 197 │ │ │ │ │ "__main__", mod_spec) │
│ 198 │
│ 199 def run_module(mod_name, init_globals=None, │
│ │
│ C:\Users\Brady\AppData\Local\Programs\Python\Python310\lib\runpy.py:86 in _run_code │
│ │
│ 83 │ │ │ │ │ __loader__ = loader, │
│ 84 │ │ │ │ │ __package__ = pkg_name, │
│ 85 │ │ │ │ │ __spec__ = mod_spec) │
│ ❱ 86 │ exec(code, run_globals) │
│ 87 │ return run_globals │
│ 88 │
│ 89 def _run_module_code(code, init_globals=None, │
│ │
│ E:\AI\kohya_ss\venv\Scripts\accelerate.exe\__main__.py:7 in <module> │
│ │
│ [Errno 2] No such file or directory: │
│ 'E:\\AI\\kohya_ss\\venv\\Scripts\\accelerate.exe\\__main__.py' │
│ │
│ E:\AI\kohya_ss\venv\lib\site-packages\accelerate\commands\accelerate_cli.py:45 in main │
│ │
│ 42 │ │ exit(1) │
│ 43 │ │
│ 44 │ # Run │
│ ❱ 45 │ args.func(args) │
│ 46 │
│ 47 │
│ 48 if __name__ == "__main__": │
│ │
from kohya_ss.
This typically happen if you are installing modules outside the venv... or if you already have installed similar modules outside the venv.
This can be cause if you did not give unrestricted script access to powershell so venv can work:
- Open an administrator powershell window
- Type
Set-ExecutionPolicy Unrestricted
and answer A - Close admin powershell window
One quick fix is to uninstall everything from the local env and re-install everything in the venv:
Open a new powershell window and run:
pip freeze > uninstall.txt
pip uninstall -r uninstall.txt
Then redo the kohya_ss installation.
from kohya_ss.
That got me farther than before, but I still got an error...
Folder 100_charleshardman person: 1200 steps
Use DreamBooth method.
prepare train images.
found directory contains 12 image files
1200 train images with repeating.
loading image sizes.
100%|█████████████████████████████████| 12/12 [00:00<00:00, 1401.02it/s]
make buckets
number of images (including repeats)
bucket 8: resolution (512, 512), count: 1200
mean ar error (without repeats): 0.0
prepare accelerator
Using accelerator 0.15.0 or above.
load StableDiffusion checkpoint
loading u-net: <All keys matched successfully>
loading vae: <All keys matched successfully>
File "E:\AI\kohya_ss\library\train_util.py", line 969, in replace_unet_cross_attn_to_xformers
import xformers.ops
ModuleNotFoundError: No module named 'xformers'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "E:\AI\kohya_ss\train_network.py", line 424, in <module>
train(args)
File "E:\AI\kohya_ss\train_network.py", line 67, in train
train_util.replace_unet_modules(unet, args.mem_eff_attn, args.xformers)
File "E:\AI\kohya_ss\library\train_util.py", line 923, in replace_unet_modules
replace_unet_cross_attn_to_xformers()
File "E:\AI\kohya_ss\library\train_util.py", line 971, in replace_unet_cross_attn_to_xformers
raise ImportError("No xformers / xformersがインストールされていないようです")
ImportError: No xformers / xformersがインストールされていないようです
Traceback (most recent call last):
File "C:\Users\Brady\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "C:\Users\Brady\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code
exec(code, run_globals)
File "E:\AI\kohya_ss\venv\Scripts\accelerate.exe\__main__.py", line 7, in <module>
File "E:\AI\kohya_ss\venv\lib\site-packages\accelerate\commands\accelerate_cli.py", line 45, in main
args.func(args)
File "E:\AI\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 1104, in launch_command
simple_launcher(args)
File "E:\AI\kohya_ss\venv\lib\site-packages\accelerate\commands\launch.py", line 567, in simple_launcher
raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['E:\\AI\\kohya_ss\\venv\\Scripts\\python.exe', 'train_network.py', '--enable_bucket', '--pretrained_model_name_or_path=E:/AI/Training/v1.5.ckpt', '--train_data_dir=E:\\AI\\Training\\aspen-4rd-512-Lora-Final\\img', '--resolution=512,512', '--output_dir=E:\\AI\\Training\\aspen-4rd-512-Lora-Final\\model', '--use_8bit_adam', '--xformers', '--logging_dir=E:\\AI\\Training\\aspen-4rd-512-Lora-Final\\log', '--network_module=networks.lora', '--text_encoder_lr=5e-5', '--unet_lr=1e-3', '--network_dim=8', '--output_name=last', '--learning_rate=1e-5', '--lr_scheduler=cosine', '--lr_warmup_steps=120', '--train_batch_size=1', '--max_train_steps=1200', '--save_every_n_epochs=1', '--mixed_precision=fp16', '--save_precision=fp16', '--seed=1234', '--cache_latents', '--xformers', '--use_8bit_adam']' returned non-zero exit status 1.
from kohya_ss.
I resolved the above error by copying the xformers
and xformers-0.0.14.dev0.dist-info
folders from the venv folder in my Automatic1111 folder.
from kohya_ss.
This typically happen if you are installing modules outside the venv... or if you already have installed similar modules outside the venv.
This can be cause if you did not give unrestricted script access to powershell so venv can work:
* Open an administrator powershell window * Type `Set-ExecutionPolicy Unrestricted` and answer A * Close admin powershell window
One quick fix is to uninstall everything from the local env and re-install everything in the venv:
Open a new powershell window and run:
pip freeze > uninstall.txt pip uninstall -r uninstall.txt
Then redo the kohya_ss installation.
is it really necessary to uninstall from the PC's environment? I honestly don't want to uninstall commonly used modules like torch
from kohya_ss.
I resolved the above error by copying the
xformers
andxformers-0.0.14.dev0.dist-info
folders from the venv folder in my Automatic1111 folder.
did you uninstall from your local environment?
from kohya_ss.
This typically happen if you are installing modules outside the venv... or if you already have installed similar modules outside the venv.
This can be cause if you did not give unrestricted script access to powershell so venv can work:
* Open an administrator powershell window * Type `Set-ExecutionPolicy Unrestricted` and answer A * Close admin powershell window
One quick fix is to uninstall everything from the local env and re-install everything in the venv:
Open a new powershell window and run:
pip freeze > uninstall.txt pip uninstall -r uninstall.txt
Then redo the kohya_ss installation.
Still facing the same.
I uninstalled using
pip uninstall -r requirements.txt
and then redid the setup
from kohya_ss.
Yes, I ran both uninstalls, the second one removed almost all of my AppData python files. It also took a while to say yes to almost 300 items.
I had tried many StableDiffusion reops in the past but almost exclusively use A1111 now, which also uses a VENV folder and not the AppData python folder. So it was kinda nice to remove all of that stuff anyway.
After I removed all of that I deleted the Kohya folder and reinstalled it. Re-running it threw a new error saying xformers was missing so I had to copy that from my a1111 install.
After that, it ran fine and made a decent first LoRA in about 15 minutes.
from kohya_ss.
The error about xformer is puzzling... I will need to try a full re-install... perhaps the source URL for it has been removed... Let me test on my system
from kohya_ss.
All went fine on my end. xformers installed fine also
from kohya_ss.
This typically happen if you are installing modules outside the venv... or if you already have installed similar modules outside the venv.
This can be cause if you did not give unrestricted script access to powershell so venv can work:
- Open an administrator powershell window
- Type
Set-ExecutionPolicy Unrestricted
and answer A- Close admin powershell window
One quick fix is to uninstall everything from the local env and re-install everything in the venv:
Open a new powershell window and run:
pip freeze > uninstall.txt pip uninstall -r uninstall.txt
Then redo the kohya_ss installation.
DIDNT WORK! It still says that the folder venv/Scripts/accelerate doesn't exist?
from kohya_ss.
All went fine on my end. xformers installed fine also
I'm using Kohya's original sd scripts, and they did show these errors sometimes too, It was when RAM wasn't enough to load the stuff, and similar scenarios.
from kohya_ss.
Hi, please, could you provide an installer that work! I tried your suggestions but none worked for me.
from kohya_ss.
Related Issues (20)
- logging wandb is now worst
- Pytorch version inconsistency on google colab notebook
- Bad file descriptor in git clone
- BLIP2 captioning doesn't see .webp files (with patch) HOT 1
- Relationship between toml and json config files HOT 3
- I get an error message that a url: /api/models/stabilityai/stable-diffusion-xl-base-1.0 is missing when i start lora training local on windows without internet. HOT 1
- TypeError: environment can only contain strings
- 49 sec/it on 4090 HOT 3
- ValueError: Key backend: 'module://matplotlib_inline.backend_inline' is not a valid value for backend
- assert abs_path is not None, f"no image / 画像がありません: {image_key}" HOT 1
- Didn't change anything, Lora training spits out non-zero exit status 1 json error? HOT 1
- ValueError: Too many values to unwrap (expected 2)...how to fix
- {Help} Network Rank Slider and No Half VAE checkbox is not showing up in my Kohya_ss after Installation. HOT 1
- AttributeError: 'NoneType' object has no attribute 'dtype' HOT 2
- Additional Parameters "Scheduler args" NOT Saved in Toml file AND NOT passed HOT 8
- No json files on training HOT 4
- WD14 Tagger Not Recognizing CUDA After Update? HOT 12
- sdxl training HOT 4
- unable to train sdxl lora using runpod training stops without throwing error HOT 2
- pip install argument might be passed incorrectly HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from kohya_ss.