modelscope / modelscope/DiffSynth-Studio
QwenImageVAE tiled decode未实现？
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
我看到尽管QwenImagePipeline.__call__有把tiled, tile_size, tile_stride参数传入self.vae.decode，但QwenImageVAE.decode只是用**kwargs接收，并没有实际用到。
https://github.com/modelscope/DiffSynth-Studio/blob/afd101f3452c9ecae0c87b79adfa2e22d65ffdc3/diffsynth/pipelines/qwen_image.py#L444
https://github.com/modelscope/DiffSynth-Studio/blob/afd101f3452c9ecae0c87b79adfa2e22d65ffdc3/diffsynth/models/qwen_image_vae.py#L716
我对模型原理了解有限，想请教一下：请问是 功能暂未实现 还是 QwenImageVAE模型架构本身就无法支持tiled decoding？感谢您的时间和贡献！
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 at the linked QwenImagePipeline.call entry point in diffsynth/pipelines/qwen_image.py and follow the tiled, tile_size, and tile_stride arguments into QwenImageVAE.decode in diffsynth/models/qwen_image_vae.py. Determine whether this VAE supports tiled decoding and whether the unused arguments represent missing functionality; done means the behavior is resolved and covered by an appropriate validation or explanation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100