lllyasviel / lllyasviel/FramePack
Stochastic generation
- Dominant language
- Python
- Stars
- 17.3k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
Hi @lllyasviel
Thank you publicly sharing the code. I think this is a really great work.
It seems like the default sampler is deterministic. Have you also tried stochastic sampling (SDE) like DDIM with eta > 0 or DDPM sampler?
If so could anyone please share the implementation?
Thanks!
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue names no files, tests, or entry points. Start by locating the default sampler and the generation path, then compare their behavior with the requested DDIM eta > 0 and DDPM approaches; done would mean a documented, working stochastic-sampling implementation.
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
- 20/100