lllyasviel / lllyasviel/ControlNet

just a finding of generating human faces or half-body image using canny, hed, etc...

Open
#180 5 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
34.1k
Forks
3k
PR merge metrics
No merged PRs in 30d

Description

Hi,

Firstly i would like to say many thanks to the developers of ControlNet. Great work!

I've been using ControlNet to generate human-related stuff, e.g. faces, half-body portrait, etc...
One interesting issue i found would be the model tends to generate grayscale (white and black) image when canny/hed conditions is being added and idk why. I have to say this phenomenon is indeed different from other stable diffusion models that i've used.

One feasible solution to alleviate this issue is simply add "grayscale, monochrome" to the negative prompt if you don't want grayscale effects.

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 with human-face or half-body prompts while applying canny or hed conditioning, and compare the outputs with other Stable Diffusion models if available. Since the issue names no files or tests, done would require determining whether the grayscale result is an expected behavior or a reproducible defect and documenting the finding.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 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.