lllyasviel / lllyasviel/stable-diffusion-webui-forge

[Bug]: ip-adapter seems not work on text2image, image2image works fine

Open
#425 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
13k
Forks
1.7k
PR merge metrics
No merged PRs in 30d

Description

### Checklist

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

### What happened?

I try to use ip-adapter face id model to make sure the generated image has the same face as reference image on text2image. The result seems ip-adapter does work take effect at all. image2image works fine though

### Steps to reproduce the problem

1 select text2image
2 add ip-adpter from controlnet, and upload reference image, then generate

### What should have happened?

face should be the same as reference image

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

Google Chrome, Microsoft Edge

### Sysinfo

.

### Console logs

```Shell
.
```

### Additional information

_No response_

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reproducing the issue from the text2image entry point with ControlNet's IP-Adapter Face ID and the supplied reference image, then compare the result with image2image, which reportedly works. Done means text2image preserves the face from the reference image; no source file or test is identified in the issue.

Written by the indexing model from the issue text.

Assessment

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.