lllyasviel / lllyasviel/sd-forge-layerdiffuse

Doesn't work with any Illustrious (SDXL) based models

Open
#145 2 comments 3 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
4.1k
Forks
352
PR merge metrics
No merged PRs in 30d

Description

I tested it on base SDXL models and Pony models, those work for both the attention injection and conv. Switching to Illustirous v1.0, NoobXL, or some merged like WAIIllustrious only produces a slight pink hue over the image for either attention injection or conv.

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 reproducing the report with base SDXL and Pony models, then compare them with Illustrious v1.0, NoobXL, and WAIIllustrious. Check both the attention injection and convolution paths and characterize why the latter models produce only a slight pink hue. Done means identifying the compatibility failure and confirming a fix across the named model types.

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
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.