lllyasviel / lllyasviel/LayerDiffuse_DiffusersCLI

replicated paper and training code but..

Open
#9 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
425
Forks
40
PR merge metrics
No merged PRs in 30d

Description

hi @lllyasviel amazing work, i tried replicating the paper, and was able to get a model working, but the results i see are cloudy and have artifacts sometimes, lack consistency across seeds. did you regularize using any additional losses other than regular diffusion objective in latent space while training the Unet?

did you use any additional tricks not mentioned in paper?

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

Compare the paper with the referenced training code, focusing on the latent-space diffusion objective, U-Net training, and any regularization or additional losses. Determine whether the cloudy artifacts and seed inconsistency come from an undocumented training detail or a replication problem; the issue is resolved when the expected training procedure is clarified.

Written by the indexing model from the issue text.

Assessment

Tech stack
machine-learning, python
Domain
machine-learning
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.