modelscope / modelscope/DiffSynth-Studio
关于 Flux-Kontext 支持多张 kontext_images 输入的设计疑问
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
您好,感谢你们开源 DiffSynth-Studio 项目!
我在阅读 flux_image_new.py 中 FluxImageUnit_Kontext 的实现时注意到,当前代码支持输入多张 kontext_images,并将多个 kontext_latent 在非通道维度(dim=1)进行拼接:
kontext_latents = torch.concat(kontext_latents, dim=1)
kontext_image_ids = torch.concat(kontext_image_ids, dim=-2)
这似乎与 Flux-Kontext 官方开源实现(只支持单张图)不完全一致。在我们的测试中,尝试输入多张图像时,输出结果只是简单地将图像融合,整体表现并不协调。
因此我有几个疑问想请教:
- 当前支持多张 kontext_images 的设计初衷是什么?是为后续支持多图编辑、多图融合等扩展功能做准备吗?
- 将多个 latent 在非通道维度拼接是否符合模型结构本身的预期?这种拼接方式是否可能会引起空间布局的错乱或 feature 混淆?
- 若我们希望通过 SFT(Supervised Fine-Tuning)方式提升多图输入的效果,是否有推荐的数据量?你们是否有这方面的经验可以分享?
再次感谢你们的工作,期待解答!
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with diffsynth/pipelines/flux_image_new.py and the FluxImageUnit_Kontext implementation, then compare its multi-image latent concatenation with the official Flux-Kontext behavior described in the issue. There is no concrete change or acceptance criterion yet; a maintainer decision is needed before the work can be scoped or considered done.
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