lllyasviel / lllyasviel/ControlNet

Multiple masks cause confused output

Open
#370 3 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,
Thanks for providing this amazing capability for SD!

I had a question for multiple objects placed in the image. Sometimes I'm finding if two masks are provided for the image inpainting (via canny or segments) it causes confused output. For example, a canny outline for an apple and a canny outline for a succulent plant is given. Once inpainting is done it will at times try to squeeze the green plant into the apple. At times it may not draw the second object at all.

Was training done with multiple objects provided? And is there a way to better achieve this?
Thanks!

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

No files, tests, or entry points are identified. Start by locating the inpainting path for canny or segment masks, then check whether multiple-object inputs are covered by training or tests. Done would require a reproducible determination of the limitation and either an agreed fix or documented guidance.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.