modelscope / modelscope/DiffSynth-Studio

Flux2 for Inpaint with ControlNet

Open
#1,449 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
13.1k
Forks
1.3k
Avg merge
13h 12m
Merged PRs (30d)
45

Description

Hi! I’m trying to understand the recommended approach for training FLUX.2 Inpainting with ControlNet, specifically for mask-conditioned inpainting.

My goal is to perform inpainting only inside the masked region, while also making the generated content follow an additional mask/control signal provided to ControlNet. In other words, I would like the inpainted region to be structurally guided by the ControlNet conditioning input, not only by the text prompt.

Could you please clarify what is the recommended training setup for this use case?

Any guidance or pointers would be greatly appreciated. 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 named. Start by locating the repository’s existing FLUX.2, inpainting, and ControlNet training guidance, then compare how mask conditioning is handled. Done means a documented, repository-specific training setup that addresses masked-region inpainting and ControlNet structural guidance.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.