modelscope / modelscope/DiffSynth-Studio
为什么qwen-image-edit进入vae的图像的长和宽要限制为32的倍数呢？
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
想请教一下为什么calculate_dimensions中要将图像的长和宽限制为32的倍数 我理解vae下采样率为8 latent进入dit之前patch embed的patch_size是2 那16的倍数应该就可以了吧？
而且比较奇怪的是训练代码中只在QwenImageUnit_EditImageEmbedder中对编辑任务中的condition images做出了32倍数的限制 却并未在QwenImageUnit_InputImageEmbedder对input(target) image做出这一限制
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 by reading calculate_dimensions, QwenImageUnit_EditImageEmbedder, and QwenImageUnit_InputImageEmbedder. Trace how image dimensions pass through the VAE and patch embedding, then compare the edit condition-image restriction with the input-image path. Done means documenting the reason for the 32-pixel constraint or identifying a concrete inconsistency.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100