lllyasviel / lllyasviel/FramePack
The scene of the video has not changed much
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17.3k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
Hello, there is no doubt that this is a great project and effect in the application of objects. But after conducting case tests, I also discovered a limitation of it, which is that the scenario will not change much, no matter how my prompt words are modified. It should be related to the implementation technology processing method, because it generates and splices 1-second and 1-second videos, and splices 5-second and 5-second videos, resulting in almost no changes in the scene.
I hope the author can make further breakthroughs. Thank you very much for this great work
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
No file or test is identified in the issue. Start by reproducing the limited scene changes with different prompts, then inspect the implementation that generates and splices the one-second and five-second video segments. Done means the generated video shows substantially greater scene variation across prompts.
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