Hacker News · 1 min read

Show HN: We compressed a 31B video+audio diffusion model to 14B, 6 steps, INT8

Show HN: We compressed a 31B video+audio diffusion model to 14B, 6 steps, INT8

Article URL: https://github.com/Video-Rebirth/hyperflow-h3-flash Comments URL: https://news.ycombinator.com/item?id=50405263 Points: 18 # Comments: 7

This is a summary aggregated from Hacker News. Read the complete article on the original site:

Read full article at Hacker News

More AI & Machine Learning News