lllyasviel / lllyasviel/ControlNet

Canny y depth

Open
#347 0 comments 1 reaction 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

Canny began to behave differently, now the processed image appears inverted, if I check the "Invert Input Color" option it seems to be solved but the results are no longer the same.

On the other hand depth no longer exists now there are depth_leres, depth_midas and depth_zoe, with none I get the results of before.

What I can do?

Thank you!

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 Canny behavior with and without the "Invert Input Color" option, then compare the depth_leres, depth_midas, and depth_zoe results with the earlier behavior described. Done means identifying whether the changed preprocessing or depth models explains the discrepancy and documenting a confirmed path to equivalent results.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision
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.