modelscope / modelscope/DiffSynth-Studio

When will community support LoRA training for OminiControl based on Qwen-Image?

Open
#747 1 comment 2 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

The newly released text-to-image base model Qwen-Image delivers outstanding performance—surpassing flux-dev in quality and supporting commercial use. The community has already enabled SFT and LoRA fine-tuning. However, image editing tasks are not yet supported.

The OminiControl paradigm (GitHub link) enables LoRA training on text-to-image models and extends them for editing tasks.

When will the DiffSynth-Studio community support LoRA training for OminiControl based on Qwen-Image? I believe this would be highly valuable and impactful. @pengqun @Lupino @calmhawk @co63oc @wenmengzhou

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 reviewing the linked OminiControl project and the repository's existing SFT and LoRA support for Qwen-Image. Define the requirements for image-editing LoRA training based on OminiControl, then verify that the resulting workflow supports the requested training use case.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.