SkyworkAI / SkyworkAI/Skywork-R1V
请问有没有支持视频输入的脚本
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.2k
- Forks
- 282
- PR merge metrics
- No merged PRs in 30d
Description
你好，目前的inference脚本中只有单图或者多图concat的模板，请问有没有视频专属的模板（prefix）。另外，我注意到inference中的预处理形式和internvl一致，那么能否直接沿用internvl的模板呢
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 the inference script and its existing single-image and multi-image concatenation templates, then compare its preprocessing with the InternVL template mentioned in the issue. Determine whether video input and a video-specific prefix are supported or whether the InternVL template can be reused; done means establishing the project's agreed video-input approach.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100