abyszone / abysz-lab-ext Goto Github PK
View Code? Open in Web Editor NEWTemporal Coherence tools. Automatic1111 extension.
License: GNU General Public License v3.0
Temporal Coherence tools. Automatic1111 extension.
License: GNU General Public License v3.0
On linux Ubuntu, assuming imagemagick is installed (through repo), the command "magick" doesn't exist. Instead, it should be called by the command (here: composite)
For linux Ubuntu:
Line 310 in Abysz_Lab.py needs to replaced by:
composite_command = f"composite -compose CopyOpacity {os.path.join(maskD, mask)} {output_file} {os.path.join(maskS, 'result.png')}"
The same for line for line 367, the correct line is:
os.system(f"composite {'-dissolve ' + str(dissolve) + '%' if dissolve is not None else ''} {maskS}/{filename}.png {ruta_entrada_2}/{filename}{ext} {ruta_salida}/{filename}{ext}")
Besides this, Abysz_Lab is very interresting! Good job! It will take me some time to figure all of its possibilities. Thanks!
Hi when I hit 'Run DIF' I got this error. Any help will be appriciated.
venv "C:\Users\giantstep01\Documents\AI\stable-diffusion-webui\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)]
Version: v1.9.0
Commit hash: adadb4e3c7382bf3e4f7519126cd6c70f4f8557b
Installing sd-webui-controlnet requirement: changing opencv-python version from None to 4.8.0
CUDA 12.1
Launching Web UI with arguments: --xformers --no-half-vae --theme dark
[-] ADetailer initialized. version: 24.4.2, num models: 10
CivitAI Browser+: Aria2 RPC started
ControlNet preprocessor location: C:\Users\giantstep01\Documents\AI\stable-diffusion-webui\extensions\sd-webui-controlnet\annotator\downloads
2024-04-24 01:14:05,658 - ControlNet - INFO - ControlNet v1.1.445
2024-04-24 01:14:05,758 - ControlNet - INFO - ControlNet v1.1.445
01:14:06 - ReActor - STATUS - Running v0.7.0-b7 on Device: CUDA
01:14:06 - ReActor - STATUS - Running v0.7.0-b7 on Device: CUDA
Loading weights [ef76aa2332] from C:\Users\giantstep01\Documents\AI\stable-diffusion-webui\models\Stable-diffusion\V15\realisticVisionV60B1_v51VAE.safetensors
Creating model from config: C:\Users\giantstep01\Documents\AI\stable-diffusion-webui\configs\v1-inference.yaml
2024-04-24 01:14:07,038 - ControlNet - INFO - ControlNet UI callback registered.
LAB
Deforum ControlNet support: enabled
Running on local URL: http://127.0.0.1:7860
To create a public link, set share=True
in launch()
.
Startup time: 25.0s (prepare environment: 8.9s, import torch: 3.9s, import gradio: 0.8s, setup paths: 1.2s, initialize shared: 2.1s, other imports: 0.5s, list SD models: 0.2s, load scripts: 5.3s, create ui: 1.6s, gradio launch: 0.3s, app_started_callback: 0.2s).
Loading VAE weights specified in settings: C:\Users\giantstep01\Documents\AI\stable-diffusion-webui\models\VAE\vae-ft-mse-840000-ema-pruned.ckpt
Applying attention optimization: xformers... done.
Model loaded in 8.5s (create model: 0.5s, apply weights to model: 6.6s, load VAE: 0.2s, calculate empty prompt: 1.0s).
No se encontró en Z:\AnimTest\04\output una imagen con el mismo nombre que 0001.
Traceback (most recent call last):
File "C:\Users\giantstep01\Documents\AI\stable-diffusion-webui\venv\lib\site-packages\gradio\routes.py", line 488, in run_predict
output = await app.get_blocks().process_api(
File "C:\Users\giantstep01\Documents\AI\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1431, in process_api
result = await self.call_function(
File "C:\Users\giantstep01\Documents\AI\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1103, in call_function
prediction = await anyio.to_thread.run_sync(
File "C:\Users\giantstep01\Documents\AI\stable-diffusion-webui\venv\lib\site-packages\anyio\to_thread.py", line 33, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "C:\Users\giantstep01\Documents\AI\stable-diffusion-webui\venv\lib\site-packages\anyio_backends_asyncio.py", line 877, in run_sync_in_worker_thread
return await future
File "C:\Users\giantstep01\Documents\AI\stable-diffusion-webui\venv\lib\site-packages\anyio_backends_asyncio.py", line 807, in run
result = context.run(func, *args)
File "C:\Users\giantstep01\Documents\AI\stable-diffusion-webui\venv\lib\site-packages\gradio\utils.py", line 707, in wrapper
response = f(*args, **kwargs)
File "C:\Users\giantstep01\Documents\AI\stable-diffusion-webui\extensions\Abysz-LAB-Ext\scripts\Abysz_Lab.py", line 305, in main
exit(1)
File "C:\Users\giantstep01\AppData\Local\Programs\Python\Python310\lib_sitebuiltins.py", line 26, in call
raise SystemExit(code)
SystemExit: 1
I have been trying out your extension for a while and it looks quite promising! I have had mixed results so far but overall its robust albeit the user experience could be better. But it is sometimes frustrating, I can't tell how many times I have broken it and had to restart the whole UI because I did something too fast or clicked twice accidentally, I suspect adding some more try-excepts will solve the problem but I am not quite sure because some of the code is in spanish?
Hello. I am trying to improve deflicking issue
Using latest version of automatic1111 and Abysz-LAB-Ext
img2img processed folder
original images folder
everything is default because your guide is very poor unfortunately. I am trying to prepare a guide tutorial video
And here the full error message i am getting
El archivo 101 ya existe. Se omite su renombre.
El archivo 102 ya existe. Se omite su renombre.
.
.
.
El archivo 1524 ya existe. Se omite su renombre.
El archivo 1525 ya existe. Se omite su renombre.
composite: unable to open image 'C:\control': No such file or directory @ error/blob.c/OpenBlob/3537.
composite: no decode delegate for this image format `' @ error/constitute.c/ReadImage/572.
composite: unable to open image 'net': No such file or directory @ error/blob.c/OpenBlob/3537.
composite: unable to open image 'net': No such file or directory @ error/blob.c/OpenBlob/3537.
composite: no decode delegate for this image format `' @ error/constitute.c/ReadImage/572.
composite: unable to open image 'automatic\extensions\Abysz-LAB-Ext\scripts\Run\MaskD\001.png': No such file or directory @ error/blob.c/OpenBlob/3537.
composite: unable to open image 'automatic\extensions\Abysz-LAB-Ext\scripts\Run\MaskD\001.png': No such file or directory @ error/blob.c/OpenBlob/3537.
composite: unable to open image 'C:\animation': No such file or directory @ error/blob.c/OpenBlob/3537.
composite: unable to open image 'C:\animation': No such file or directory @ error/blob.c/OpenBlob/3537.
composite: no decode delegate for this image format `' @ error/constitute.c/ReadImage/572.
composite: unable to open image 'video\abysz\001.png': No such file or directory @ error/blob.c/OpenBlob/3537.
composite: unable to open image 'video\abysz\001.png': No such file or directory @ error/blob.c/OpenBlob/3537.
composite: no decode delegate for this image format `' @ error/constitute.c/ReadImage/572.
composite: unable to open image 'net': No such file or directory @ error/blob.c/OpenBlob/3537.
composite: unable to open image 'net': No such file or directory @ error/blob.c/OpenBlob/3537.
composite: no decode delegate for this image format `' @ error/constitute.c/ReadImage/572.
composite: `automatic\extensions\Abysz-LAB-Ext\scripts\Run\MaskS\result.png' @ error/composite.c/CompositeImageCommand/1632.
Traceback (most recent call last):
File "C:\control net automatic\venv\lib\site-packages\gradio\routes.py", line 394, in run_predict
output = await app.get_blocks().process_api(
File "C:\control net automatic\venv\lib\site-packages\gradio\blocks.py", line 1075, in process_api
result = await self.call_function(
File "C:\control net automatic\venv\lib\site-packages\gradio\blocks.py", line 884, in call_function
prediction = await anyio.to_thread.run_sync(
File "C:\control net automatic\venv\lib\site-packages\anyio\to_thread.py", line 31, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "C:\control net automatic\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 937, in run_sync_in_worker_thread
return await future
File "C:\control net automatic\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 867, in run
result = context.run(func, *args)
File "C:\control net automatic\extensions\Abysz-LAB-Ext\scripts\Abysz_Lab.py", line 323, in main
os.rename(os.path.join(maskS, 'result.png'), os.path.join(maskS, f"{name}.png"))
FileNotFoundError: [WinError 2] The system cannot find the file specified: 'C:\\control net automatic\\extensions\\Abysz-LAB-Ext\\scripts\\Run\\MaskS\\result.png' -> 'C:\\control net automatic\\extensions\\Abysz-LAB-Ext\\scripts\\Run\\MaskS\\001.png'
Hi, May i have youe linkedin or your Email address?
Thanks
Best regards
I am trying to use Deflickers Playground but it is throwing an error. It doesn't seem to like my input path - but I have tried different paths and the error remains the same;
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('A:\Downloads\walker_test\processed'): can't open/read file: check file path/integrity
Traceback (most recent call last):
File "S:\WebUI\stable-diffusion-webui\venv\lib\site-packages\gradio\routes.py", line 399, in run_predict
output = await app.get_blocks().process_api(
File "S:\WebUI\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1299, in process_api
result = await self.call_function(
File "S:\WebUI\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1022, in call_function
prediction = await anyio.to_thread.run_sync(
File "S:\WebUI\stable-diffusion-webui\venv\lib\site-packages\anyio\to_thread.py", line 31, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "S:\WebUI\stable-diffusion-webui\venv\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_worker_thread
return await future
File "S:\WebUI\stable-diffusion-webui\venv\lib\site-packages\anyio_backends_asyncio.py", line 867, in run
result = context.run(func, *args)
File "S:\WebUI\stable-diffusion-webui\extensions\Abysz-LAB-Ext\scripts\Abysz_Lab.py", line 671, in deflickers
dyndef(ruta_entrada_3, ruta_salida_1, ddf_strength)
File "S:\WebUI\stable-diffusion-webui\extensions\Abysz-LAB-Ext\scripts\Abysz_Lab.py", line 416, in dyndef
current_img = cv2.addWeighted(current_img, alpha, prev_img, 1-alpha, 0)
cv2.error: OpenCV(4.7.0) D:\a\opencv-python\opencv-python\opencv\modules\core\src\arithm.cpp:650: error: (-209:Sizes of input arguments do not match) The operation is neither 'array op array' (where arrays have the same size and the same number of channels), nor 'array op scalar', nor 'scalar op array' in function 'cv::arithm_op'
Hi there - great job! Looks very intriguing from your demos and a tool I'd love to try out. However personally I find the instructions too minimal to know where to begin. Could you provide a sample walk-through either in a readme or video?
Many thanks! Jon
When I try the Blend or Overlay methods in the Deflickers Playground it doesn't seem to process all the video frames in order. For example every 18 (or 38 on another run) frames is a frame from a different part of the video. It is almost like it loses the order of the frames when it combines them. This is with a video that has been extracted into 855 frames so maybe it is a limit problem or something like that???
I have folder A and I want to apply img2img to this folder
I will upscale them
Then I have folder B, this folder contains images that I want to use as controlnet net images
So I will be able to batch process a folder with img2img and controlnet together
Image names of the both folder can be same
Here what I want to achieve
Original image that I want to use as controlnet canny + hed
input img2img
output img2img
without controlnet this is the output
you see hands are too bad
For some reason I can't your extension and I'm really excited to. I keep running into an error.
commit: 22bcc7be • checkpoint: f037812a2c
(I'm running the latest version of the app)
Console Data
To create a public link, set share=True
in launch()
.
Startup time: 22.3s (load scripts: 5.1s, reload script modules: 0.2s, list SD models: 2.4s, create ui: 14.5s, gradio launch: 0.2s).
Calculating sha256 for E:\Documents\AI\stable-diffusion-webui\models\Stable-diffusion\icomix_V03Pruned.safetensors: f037812a2c49f851ae88134e88c3dae9c40fa840c6f2f04defff627eeac114e0
Loading weights [f037812a2c] from E:\Documents\AI\stable-diffusion-webui\models\Stable-diffusion\icomix_V03Pruned.safetensors
Applying cross attention optimization (Doggettx).
Weights loaded in 29.3s (calculate hash: 27.3s, load weights from disk: 0.2s, apply weights to model: 0.8s, move model to device: 1.0s).
'magick' is not recognized as an internal or external command,
operable program or batch file.
Traceback (most recent call last):
File "E:\Documents\AI\stable-diffusion-webui\venv\lib\site-packages\gradio\routes.py", line 394, in run_predict
output = await app.get_blocks().process_api(
File "E:\Documents\AI\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1075, in process_api
result = await self.call_function(
File "E:\Documents\AI\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 884, in call_function
prediction = await anyio.to_thread.run_sync(
File "E:\Documents\AI\stable-diffusion-webui\venv\lib\site-packages\anyio\to_thread.py", line 31, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "E:\Documents\AI\stable-diffusion-webui\venv\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_worker_thread
return await future
File "E:\Documents\AI\stable-diffusion-webui\venv\lib\site-packages\anyio_backends_asyncio.py", line 867, in run
result = context.run(func, *args)
File "E:\Documents\AI\stable-diffusion-webui\extensions\Abysz-LAB-Ext\scripts\Abysz_Lab.py", line 317, in main
os.rename(os.path.join(maskS, 'result.png'), os.path.join(maskS, f"{name}.png"))
FileNotFoundError: [WinError 2] The system cannot find the file specified: 'E:\Documents\AI\stable-diffusion-webui\extensions\Abysz-LAB-Ext\scripts\Run\MaskS\result.png' -> 'E:\Documents\AI\stable-diffusion-webui\extensions\Abysz-LAB-Ext\scripts\Run\MaskS\0001.png'
'magick' is not recognized as an internal or external command,
operable program or batch file.
Traceback (most recent call last):
File "E:\Documents\AI\stable-diffusion-webui\venv\lib\site-packages\gradio\routes.py", line 394, in run_predict
output = await app.get_blocks().process_api(
File "E:\Documents\AI\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1075, in process_api
result = await self.call_function(
File "E:\Documents\AI\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 884, in call_function
prediction = await anyio.to_thread.run_sync(
File "E:\Documents\AI\stable-diffusion-webui\venv\lib\site-packages\anyio\to_thread.py", line 31, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "E:\Documents\AI\stable-diffusion-webui\venv\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_worker_thread
return await future
File "E:\Documents\AI\stable-diffusion-webui\venv\lib\site-packages\anyio_backends_asyncio.py", line 867, in run
result = context.run(func, *args)
File "E:\Documents\AI\stable-diffusion-webui\extensions\Abysz-LAB-Ext\scripts\Abysz_Lab.py", line 317, in main
os.rename(os.path.join(maskS, 'result.png'), os.path.join(maskS, f"{name}.png"))
FileNotFoundError: [WinError 2] The system cannot find the file specified: 'E:\Documents\AI\stable-diffusion-webui\extensions\Abysz-LAB-Ext\scripts\Run\MaskS\result.png' -> 'E:\Documents\AI\stable-diffusion-webui\extensions\Abysz-LAB-Ext\scripts\Run\MaskS\0001.png'
Plugin version: a1b22e4
System: Ubuntu 20.04
I got an error after click DFI button:
No se encontró en /home/b/Documents/tmp/controlnet-canny-abysz una imagen con el mismo nombre que 001.
Traceback (most recent call last):
File "/home/b/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/routes.py", line 337, in run_predict
output = await app.get_blocks().process_api(
File "/home/b/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/blocks.py", line 1015, in process_api
result = await self.call_function(
File "/home/b/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/blocks.py", line 833, in call_function
prediction = await anyio.to_thread.run_sync(
File "/home/b/stable-diffusion-webui/venv/lib/python3.10/site-packages/anyio/to_thread.py", line 31, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "/home/b/stable-diffusion-webui/venv/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 937, in run_sync_in_worker_thread
return await future
File "/home/b/stable-diffusion-webui/venv/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 867, in run
result = context.run(func, *args)
File "/home/b/stable-diffusion-webui/extensions/Abysz-LAB-Ext/scripts/Abysz_Lab.py", line 275, in main
exit(1)
File "/home/b/.pyenv/versions/3.10.10/lib/python3.10/_sitebuiltins.py", line 26, in __call__
raise SystemExit(code)
SystemExit: 1
Here's what I did:
Use Abysz Lab -> LAB Tools extract frames from video.
Video path /home/b/Documents/tmp/origin.mp4
Output folder /home/b/Documents/tmp/origin-extract
Fps 0
.
Use img2img -> Batch with ControlNet process all frames.
Input directory /home/b/Documents/tmp/origin-extract
Output directory /home/b/Documents/tmp/controlnet-canny
Run Abysz Lab -> Main DFI with default params.
Original frames folder /home/b/Documents/tmp/origin-extract
Generated frames folder /home/b/Documents/tmp/controlnet-canny
Output folder /home/b/Documents/tmp/controlnet-canny-abysz
I noticed that, after step2, there are many image named frame_###.jpeg
in /home/b/Documents/tmp/controlnet-canny
. After step3, these files are renamed to ###.jpeg
and seems sorted randomly.
In addition, after step3, there are some images in ./extensions/Abysz-LAB-Ext/scripts/Run/Source
and ./extensions/Abysz-LAB-Ext/scripts/Run/MaskD
, but ./extensions/Abysz-LAB-Ext/scripts/Run/MaskS
is empty.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.