Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

No file or directory for latent-diffusion #34

Closed
Marcus-Arcadius opened this issue Sep 6, 2022 · 7 comments
Closed

No file or directory for latent-diffusion #34

Marcus-Arcadius opened this issue Sep 6, 2022 · 7 comments
Labels
bug Something isn't working

Comments

@Marcus-Arcadius
Copy link

Marcus-Arcadius commented Sep 6, 2022

image

stable-diffusion-webui-docker-model-1  | /docker/mount.sh: line 25: /latentdiffusion/experiments/pretrained_models/project.yaml: No such file or directory 
stable-diffusion-webui-docker-model-1 exited with code 1

EDIT: Fixed the issue in the hlky mount.sh file by removing the # from the project.yaml line but now facing this issue

image

stable-diffusion-webui-docker-model-1  |  Error loading LDSR
stable-diffusion-webui-docker-model-1  |  Loading model from /models/model.ckpt
stable-diffusion-webui-docker-model-1  |  Traceback (most recent call last):
stable-diffusion-webui-docker-model-1  |  File "scripts/webui.py", line 382, in try_loading_LDSR
stable-diffusion-webui-docker-model-1  |  LDSR = load_LDSR(checking=True) # TODO: Should try to load both models before giving up
stable-diffusion-webui-docker-model-1  |  File "scripts/webui.py", line 297, in load_LDSR
stable-diffusion-webui-docker-model-1  |  raise Exception("LDSR model not found at path "+model_path)
stable-diffusion-webui-docker-model-1  |  Exception: LDSR model not found at path /latent diffusion/experiments/pretrained_models/model.ckpt  

stable-diffusion-webui-docker-model-1  | Global Step: 470000
stable-diffusion-webui-docker-model-1  | UNet: Running in eps-prediction mode
stable-diffusion-webui-docker-model-1 exited with code 137
@Marcus-Arcadius Marcus-Arcadius added the bug Something isn't working label Sep 6, 2022
@AbdBarho
Copy link
Owner

AbdBarho commented Sep 6, 2022

@Marcus-Arcadius did you download the LDSR model and its configuration as written in the readme? or you don't want to use LDSR?

If you don't want LDSR try git pull and docker compose up --build, then its normal to see an error in the console:

+ /docker/mount.sh
Mounted RealESRGAN_x4plus_anime_6B.pth
Mounted RealESRGAN_x4plus.pth
Skipping LDSR.ckpt
Mounted GFPGANv1.3.pth
+ python3 -u scripts/webui.py --outdir /output --ckpt /models/model.ckpt --ldsr-dir /latent-diffusion --extra-models-cpu --optimized-turbo
Found GFPGAN
Found RealESRGAN
Error loading LDSR:
Traceback (most recent call last):
  File "scripts/webui.py", line 382, in try_loading_LDSR
    LDSR = load_LDSR(checking=True) # TODO: Should try to load both models before giving up
  File "scripts/webui.py", line 297, in load_LDSR
    raise Exception("LDSR model not found at path "+model_path)
Exception: LDSR model not found at path /latent-diffusion/experiments/pretrained_models/model.ckpt
Loading model from /models/model.ckpt
Global Step: 470000
UNet: Running in eps-prediction mode
CondStage: Running in eps-prediction mode
FirstStage: Running in eps-prediction mode
making attention of type 'vanilla' with 512 in_channels
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
making attention of type 'vanilla' with 512 in_channels
/opt/conda/lib/python3.8/site-packages/gradio/deprecation.py:43: UserWarning: You have unused kwarg parameters in File, please remove them: {'source': 'upload'}
  warnings.warn(
Running on local URL:  http://localhost:7860/
To create a public link, set `share=True` in `launch()`.

@AbdBarho AbdBarho added the awaiting-response Waiting for the issuer to respond label Sep 6, 2022
@Marcus-Arcadius
Copy link
Author

@AbdBarho I did download the model and configuration file and renamed them, but the docker container for some reason couldn't find them in the model's folder?

@AbdBarho
Copy link
Owner

AbdBarho commented Sep 6, 2022

@Marcus-Arcadius this is very weird, can you show me the contents of the models folder?
ls -l models or tree models/?

the mount script is saying

Skipping LDSR.ckpt

which means it cannot find the model

@Marcus-Arcadius
Copy link
Author

@AbdBarho this is whats inside the models folder which should be correct?
image

@Marcus-Arcadius
Copy link
Author

@AbdBarho so I got it to work with wsl2 Ubuntu but I'm encountering an error where it just randomly exits?

image

@AbdBarho
Copy link
Owner

AbdBarho commented Sep 6, 2022

@Marcus-Arcadius how did you manage to get it running in wsl?
can you tell me your system specification? os / ram / gpu / vram? I assume the model is taking too much memory and crashing?

@Marcus-Arcadius
Copy link
Author

@AbdBarho I got it to eventually work by using a .wslconfig file and increasing the resources, my specs are the nvidia 2060 super, 16GB RAM, 8GB VRAM, and windows 11

@AbdBarho AbdBarho removed the awaiting-response Waiting for the issuer to respond label Sep 6, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

2 participants