lllyasviel / lllyasviel/FramePack
Using FramePack to achieve T2V
Open
- Dominant language
- Python
- Stars
- 17.3k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
Fantastic work! I'm wondering if I can use FramePack to achieve T2V. It seems that FramePack needs an image as input. However, both Wan and HunYuan provide T2V models.
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reviewing FramePack's current image-input requirement, then compare it with the T2V capabilities of the Wan and HunYuan models mentioned in the issue. Determine the scope needed for text-only video generation and define completion as a documented, working T2V path or a clear explanation of why it is unsupported.
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