lllyasviel / lllyasviel/stable-diffusion-webui-forge

[Bug]: Unable to use locally stored BLIP models

Open
#843 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
13k
Forks
1.7k
PR merge metrics
No merged PRs in 30d

Description

### Checklist

- [X] The issue exists after disabling all extensions
- [X] The issue exists on a clean installation of webui
- [X] The issue is caused by an extension, but I believe it is caused by a bug in the webui
- [X] The issue exists in the current version of the webui
- [X] The issue has not been reported before recently
- [ ] The issue has been reported before but has not been fixed yet

### What happened?

I use the [clip-interrogator](https://github.com/pharmapsychotic/clip-interrogator-ext) extension in A1111 & by default the models are downloaded & stored at `C:\Users\.cache\huggingface\hub`, but Forge seems to download the models to `stable-diffusion-webui-forge\models\diffusers`. Please help me figure this out because these models are quite big & i can't afford redownloading all the models again. I'm guessing my solution would be to find a metadata file somewhere in Forge folder but i couldn't find anything.

### Steps to reproduce the problem

N/A

### What should have happened?

Forge should use the pre installed BLIP models.

### What browsers do you use to access the UI ?

Google Chrome

### Sysinfo

[sysinfo-2024-07-17-04-48.json](https://github.com/user-attachments/files/16260346/sysinfo-2024-07-17-04-48.json)

### Console logs

```Shell
...
Loading CLIP Interrogator 0.6.0...
Loading caption model blip-base...
D:\AI\stable-diffusion-webui-forge\venv\lib\site-packages\huggingface_hub\file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
warnings.warn(
config.json: 100%|████████████████████████████████████████████████████████████████████████| 4.56k/4.56k [00:00

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by tracing how the clip-interrogator extension loads the BLIP caption model and how huggingface_hub selects its cache, comparing C:\Users\.cache\huggingface\hub with models\diffusers. Done means Forge reuses the existing BLIP files instead of downloading them again; the issue provides no source file or test to run.

Written by the indexing model from the issue text.

Assessment

Tech stack
huggingface, python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.