lllyasviel / lllyasviel/FramePack
feature requests: Models and functions
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17.3k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
I want to request model for wan video as well as a choice.
Funcitons:
Option for sage attention to speed up generations.
"Savestates", where if you generate a 1 second test, and you like it, increase to 2, 3 seconds and so on, and each full "max length per stage" will be saved as a checkpoint locally to easily resume from and load the next day for instance to easily make it as long as you want to. As then each video segment stores in split video files/latent checkpoint.
Possibly an option to add lora's into the mix?
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
The issue names no files, tests, or entry points and combines model support, attention optimization, savestates, and LoRA support. Start by reviewing the existing Python generation workflow and split these into scoped proposals; each proposal needs its own completion criteria.
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
- Needs clarification
- Newbie friendliness
- 20/100