lllyasviel / lllyasviel/stable-diffusion-webui-forge

Flux Text encoder loras don't work, results are either blurry or the clip is not loaded

Open
#1,533 2 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

sample images when training it looks like subject.

when trying in forge it doesn't load. i trained the clip l text encoder along with it. but doesn't work in forge or comfy

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

Reproduce the reported behavior using the provided training sample images, then compare loading and output in Forge and Comfy. Investigate the Flux text-encoder LoRA path and verify that the trained CLIP-L text encoder is loaded and produces results matching the training subject rather than blurry output.

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
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.