modelscope / modelscope/DiffSynth-Studio

Question about InputImageEmbedder and EditImageEmbedder in FLUX.2

Open
#1,356 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

Thanks for the excellent contributions!
While studying the FLUX.2 model, I noticed some differences between the implementation in this repo and the official one.
There are two separate image input embedder classes in the repo: InputImageEmbedder and EditImageEmbedder.
For single-image editing (in examples/flux2/model_inference/FLUX.2-klein-4B.py) uses the edit_image parameter in the pipeline call function. I would like to clarify: under what circumstances is the input_image parameter intended to be used?
Looking for your reply!

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 with examples/flux2/model_inference/FLUX.2-klein-4B.py and trace the pipeline call using edit_image. Compare the InputImageEmbedder and EditImageEmbedder classes to determine how input_image is intended to differ, then document the circumstances for using each parameter.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Documentation
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.