lllyasviel / lllyasviel/ControlNet

Question about semantic segmentation conditioning

Open
#144 1 comment 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

Thanks for the awesome work! I have one small question regarding the semantic segmentation conditioning. Does the network only take the segmentation mask image as input, while ignoring the label for each mask? For example, with prompt "a dog and a cat", I cannot use a segmentation mask of two animals to accurately control which animal is a dog? 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

Read the semantic segmentation conditioning documentation and trace how the segmentation mask and text prompt are handled. Check whether labels for individual masks are represented, using the stated dog-and-cat example as the behavior to evaluate; the issue does not specify a concrete implementation or test location.

Written by the indexing model from the issue text.

Assessment

Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.