lllyasviel / lllyasviel/FramePack
How to make a video follow your PROMPT better? FINITE vs INFINITE
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17.3k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
@lllyasviel i read a post about you mention to someone that INFINITE generations cannot have FINITE prompts,,,, my prompt seems it has a couple of MOVEMENTS, but the video NEVER showed the man standing up....
even at 20 seconds....
how can i do better prompt to make a person like him follow the prompt...
I think 20 seconds is enough time for the AI to do that.,......
The prompt was
A FAT MAN EATING AT A FOOD FESTIVAL, THE MAN STANDS UP AND THROWS FOOD AT PEOPLE, THEN SITS BACK DOWN.
Movements expected: Eat, Stand up, throw food, sit down.
ONLY EATING was seen.
https://github.com/user-attachments/assets/de7a6484-eb27-4c9a-be20-e6f08bdafa7a
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, test, or entry point is named. Start by reviewing the prompt and attached video alongside the project’s existing guidance on multi-action generation; done would require a documented, reproducible explanation of whether the requested sequence is supported and how users should phrase or configure it.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- machine-learning
- Domain
- ai, machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 18/100