aigc-apps / aigc-apps/VideoX-Fun
WAN FUN Sampler with context options
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2.3k
- Forks
- 188
- Avg merge
- 2d 22h
- Merged PRs (30d)
- 3
Description
If possible, please implement the option for context options like in kijai sampler.
It could open possibility to generate batch videos and fuse them with overlapping frames.
It should use always the input image as reference to generate every next frame but with the overlapping frame it should be able to seamlessly connect generated batch videos.
Similar workflow is made in long videos with SkyReels-A1. It makes smaller videos of 49 frames and connect them with overlapping frames but with WAN it may open more possibilities due to controlnet and comfyui
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 the WAN FUN sampler and a similar kijai sampler, but no files or tests. Start by locating those sampler implementations and comparing how context options are handled; done means batch videos can use the input image as reference and connect through overlapping frames.
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