lllyasviel / lllyasviel/LayerDiffuse

Unofficial diffuser support

Open
#27 4 comments 5 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
No language data
Stars
2.2k
Forks
36
PR merge metrics
No merged PRs in 30d

Description

Appreciated your work on transparent image generation. I've been working on an unofficial implementation of LayerDiffuse mostly forked from forge's extension to my repo: https://github.com/KaustubhPatange/Diffuser-layerdiffuse.

However I've noticed many flaky outputs where the transparent (intermediate) image sometimes does not get generated and has a weird output. I believe it solely depends on the model you use for example choosing Juggernaut XL over Realistic Vision XL tends to provide much cleaner outputs.

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 flaky transparent-image generation in the unofficial implementation at github.com/KaustubhPatange/Diffuser-layerdiffuse. Compare outputs using Juggernaut XL and Realistic Vision XL, then determine whether the failure is model-specific or reproducible across models. Done means the failure conditions and expected transparent output behavior are clearly established.

Written by the indexing model from the issue text.

Assessment

Domain
computer-vision, 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.