fast-stable-diffusion
fast-stable-diffusion copied to clipboard
TheLastBen
Please reinstall xformers. How?
Hello!
Generating images has become impossible lately. Could you please tell me how to install it (xformers) and most importantly where? I'm at a grandfather level in all of this :) I use google collab. Thanks!
I looked in other posts and made changes to webui-user.bat notepad, but nothing changed. I didn't find any other way or didn't understand how to do it. Plus I use a translator :)
Some update on the Googlecolab side broke tons of colabs need to wait until we find a way to fix that. I am not a python guy at all so right now I am at the mercy of others.
That's too bad :( So we'll have to wait. I just usually use paperspace when there are problems with here, but today paperspace doesn't work either. So I'm confused. Thanks.
below is the solution that helped, I'll leave it here, in case someone needs it (I searched in old and new chats):
" In my environment, I added the following code to the beginning of the notebook and ran it, and StableDiffusion ran as before. I also made some modifications to the October Tips: [https://github.com/https://github.com/TheLastBen/fast-stable-diffusion/issues/2615] "
!pip install lmdb !pip install torch==2.1.0+cu118 torchvision==0.16.0+cu118 torchaudio==2.1.0 torchtext==0.16.0+cpu torchdata==0.7.0 --index-url https://download.pytorch.org/whl/cu118
Try adding these two blocks after the "models load/download" block (each line a block)
pip uninstall xformers (On this block, after running it, remember to click on the white space after the line "Proceed? (y/n)?" and then type "y" and then click enter.
pip install xformers
I have found the solution: !pip install lmdb !pip install torch==2.1.2+cu121 --index-url https://download.pytorch.org/whl/cu121 !pip install -U clean-fid torchaudio torchdata torchvision torchtext !pip install xformers --force --index-url https://download.pytorch.org/whl/cu121 !pip install -U bitsandbytes
I've tried all these commands, I don't know what exactly helped
Every week, instead of generating pictures, I have to dance with a notepad for 1 hour, it's sh///t
ControlNet preprocessor location: /content/gdrive/MyDrive/sd/stable-diffusion-webui/extensions/sd-webui-controlnet/annotator/downloads 2023-12-16 17:43:04,550 - ControlNet - INFO - ControlNet v1.1.422 2023-12-16 17:43:18,183 - ControlNet - INFO - ControlNet v1.1.422 Loading weights [fe7578cb5e] from /content/gdrive/MyDrive/sd/stable-diffusion-webui/models/Stable-diffusion/realisticVisionV60B1_v60B1VAE.safetensors ERROR: Exception in ASGI application Traceback (most recent call last): File "/usr/local/lib/python3.10/dist-packages/uvicorn/protocols/http/h11_impl.py", line 404, in run_asgi result = await app( # type: ignore[func-returns-value] File "/usr/local/lib/python3.10/dist-packages/uvicorn/middleware/proxy_headers.py", line 78, in call return await self.app(scope, receive, send) File "/usr/local/lib/python3.10/dist-packages/fastapi/applications.py", line 273, in call await super().call(scope, receive, send) File "/usr/local/lib/python3.10/dist-packages/starlette/applications.py", line 122, in call await self.middleware_stack(scope, receive, send) File "/usr/local/lib/python3.10/dist-packages/starlette/middleware/errors.py", line 184, in call raise exc File "/usr/local/lib/python3.10/dist-packages/starlette/middleware/errors.py", line 162, in call await self.app(scope, receive, _send) File "/usr/local/lib/python3.10/dist-packages/starlette/middleware/cors.py", line 84, in call await self.app(scope, receive, send) File "/usr/local/lib/python3.10/dist-packages/starlette/middleware/exceptions.py", line 79, in call raise exc File "/usr/local/lib/python3.10/dist-packages/starlette/middleware/exceptions.py", line 68, in call await self.app(scope, receive, sender) File "/usr/local/lib/python3.10/dist-packages/fastapi/middleware/asyncexitstack.py", line 21, in call raise e File "/usr/local/lib/python3.10/dist-packages/fastapi/middleware/asyncexitstack.py", line 18, in call await self.app(scope, receive, send) File "/usr/local/lib/python3.10/dist-packages/starlette/routing.py", line 718, in call await route.handle(scope, receive, send) File "/usr/local/lib/python3.10/dist-packages/starlette/routing.py", line 276, in handle await self.app(scope, receive, send) File "/usr/local/lib/python3.10/dist-packages/starlette/routing.py", line 66, in app response = await func(request) File "/usr/local/lib/python3.10/dist-packages/fastapi/routing.py", line 227, in app solved_result = await solve_dependencies( File "/usr/local/lib/python3.10/dist-packages/fastapi/dependencies/utils.py", line 545, in solve_dependencies solved = await run_in_threadpool(call, **sub_values) File "/usr/local/lib/python3.10/dist-packages/starlette/concurrency.py", line 41, in run_in_threadpool return await anyio.to_thread.run_sync(func, *args) File "/usr/local/lib/python3.10/dist-packages/anyio/to_thread.py", line 31, in run_sync return await get_asynclib().run_sync_in_worker_thread( AttributeError: partially initialized module 'anyio._backends._asyncio' has no attribute 'run_sync_in_worker_thread' (most likely due to a circular import) ERROR: Exception in ASGI application Traceback (most recent call last): File "/usr/local/lib/python3.10/dist-packages/uvicorn/protocols/http/h11_impl.py", line 404, in run_asgi result = await app( # type: ignore[func-returns-value] File "/usr/local/lib/python3.10/dist-packages/uvicorn/middleware/proxy_headers.py", line 78, in call return await self.app(scope, receive, send) File "/usr/local/lib/python3.10/dist-packages/fastapi/applications.py", line 273, in call await super().call(scope, receive, send) File "/usr/local/lib/python3.10/dist-packages/starlette/applications.py", line 122, in call await self.middleware_stack(scope, receive, send) File "/usr/local/lib/python3.10/dist-packages/starlette/middleware/errors.py", line 184, in call raise exc File "/usr/local/lib/python3.10/dist-packages/starlette/middleware/errors.py", line 162, in call await self.app(scope, receive, _send) File "/usr/local/lib/python3.10/dist-packages/starlette/middleware/cors.py", line 84, in call await self.app(scope, receive, send) File "/usr/local/lib/python3.10/dist-packages/starlette/middleware/exceptions.py", line 79, in call raise exc File "/usr/local/lib/python3.10/dist-packages/starlette/middleware/exceptions.py", line 68, in call await self.app(scope, receive, sender) File "/usr/local/lib/python3.10/dist-packages/fastapi/middleware/asyncexitstack.py", line 21, in call raise e File "/usr/local/lib/python3.10/dist-packages/fastapi/middleware/asyncexitstack.py", line 18, in call await self.app(scope, receive, send) File "/usr/local/lib/python3.10/dist-packages/starlette/routing.py", line 718, in call await route.handle(scope, receive, send) File "/usr/local/lib/python3.10/dist-packages/starlette/routing.py", line 276, in handle await self.app(scope, receive, send) File "/usr/local/lib/python3.10/dist-packages/starlette/routing.py", line 66, in app response = await func(request) File "/usr/local/lib/python3.10/dist-packages/fastapi/routing.py", line 227, in app solved_result = await solve_dependencies( File "/usr/local/lib/python3.10/dist-packages/fastapi/dependencies/utils.py", line 545, in solve_dependencies solved = await run_in_threadpool(call, **sub_values) File "/usr/local/lib/python3.10/dist-packages/starlette/concurrency.py", line 41, in run_in_threadpool return await anyio.to_thread.run_sync(func, *args) File "/usr/local/lib/python3.10/dist-packages/anyio/to_thread.py", line 31, in run_sync return await get_asynclib().run_sync_in_worker_thread( AttributeError: partially initialized module 'anyio._backends._asyncio' has no attribute 'run_sync_in_worker_thread' (most likely due to a circular import) Creating model from config: /content/gdrive/MyDrive/sd/stable-diffusion-webui/configs/v1-inference.yaml Running on public URL: https://bcb8cfcc40292ab36d.gradio.live/ ✔ Connected Startup time: 338.8s (launcher: 1.9s, import torch: 18.9s, import gradio: 2.1s, setup paths: 55.6s, import ldm: 1.8s, initialize shared: 15.4s, other imports: 77.8s, setup codeformer: 23.2s, setup gfpgan: 1.0s, list SD models: 4.4s, load scripts: 76.6s, load upscalers: 1.6s, initialize extra networks: 8.7s, scripts before_ui_callback: 0.1s, create ui: 35.2s, gradio launch: 14.3s, add APIs: 0.1s). The future belongs to a different loop than the one specified as the loop argument The future belongs to a different loop than the one specified as the loop argument The future belongs to a different loop than the one specified as the loop argument The future belongs to a different loop than the one specified as the loop argument The future belongs to a different loop than the one specified as the loop argument Applying attention optimization: xformers... done. Model loaded in 84.3s (load weights from disk: 55.9s, create model: 13.4s, apply weights to model: 14.2s, calculate empty prompt: 0.5s). The future belongs to a different loop than the one specified as the loop argument
Check this out https://github.com/TheLastBen/fast-stable-diffusion/issues/2615#issuecomment-1858931505
Check this out #2615 (comment)
Just tried solution #2 in fast-dreambooth on Colab, FWIW, and CUDA still fails as soon as text encoder training begins.
#Update python version to 3.9
!sudo apt-get update !sudo apt-get install python3.9 !sudo update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.9 1 !sudo update-alternatives --set python3 /usr/bin/python3.9
!pip install lmdb !pip install torch==2.1.2+cu121 --index-url https://download.pytorch.org/whl/cu121 !pip install -U clean-fid torchaudio torchdata torchvision torchtext !pip install xformers --force --index-url https://download.pytorch.org/whl/cu121 !pip install -U bitsandbytes
Add these line of code just above Start Stable Diffusion. It worked for me, might help others too.
