正在加载视频...

视频加载失败

Self-Refining Video Sampling: inference-time method using a video generator as its own refiner to correct physics and motion. no retraining needed; scores >70% human preference; is validated on Wan2.2 & Cosmos.

32,230 次观看 • 9 个月前 •via X (Twitter)

3 条评论

Dustin Hollywood 的头像
Dustin Hollywood9 个月前

💯🔥

nooooob 的头像
nooooob9 个月前

Pipeline level RL-ish impl is a trend

Cube 的头像
Cube9 个月前

well damn, gonna have to try this out

相关视频