modelscope / modelscope/DiffSynth-Studio
wan-animated推理训练数据长度问题
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
- 为什么Wan-animated推理代码和训练代码中的conds的长度都为生成视频长度-4？
https://github.com/modelscope/DiffSynth-Studio/blob/0a1c172a00fb2dd76abedd3b066ddbf62bd4a60d/examples/wanvideo/model_training/validate_lora/Wan2.2-Animate-14B.py#L21
https://github.com/modelscope/DiffSynth-Studio/blob/0a1c172a00fb2dd76abedd3b066ddbf62bd4a60d/diffsynth/pipelines/wan_video_new.py#L1072 - Wan-animated中训练和推理均没有实现论文中的overlap策略？
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 comparing the cited sections in examples/wanvideo/model_training/validate_lora/Wan2.2-Animate-14B.py and diffsynth/pipelines/wan_video_new.py, tracing how conds length is derived in training and inference. Read the referenced Wan-animated paper to check the overlap strategy; done means explaining the length choice and confirming whether both code paths implement the described strategy.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100