Hao AI Lab's FastH3 Slashes MiniMax Video Generation by 14x
FastVideo distilled MiniMax's 33B video-and-audio diffusion transformer from 50 denoising steps down to four, with open weights and 90% sparse attention.
Source
AlphaSignal
Published
Author
AlphaSignal Newsroom
Read
1 min read
FastVideo distilled MiniMax's 33B video-and-audio diffusion transformer from 50 denoising steps down to four, with open weights and 90% sparse attention.
Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.
