← sources

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

source: hackernewspublished 2026-11-07 15:16ingested 2026-11-08 02:43

extract

Points: 58 | Comments: 12 Author: jiant Link: https://github.com/Video-Rebirth/hyperflow-h3-flash Show HN: We compressed a 31B video+audio diffusion model to 14B, 6 steps, INT8

retained text

Points: 84 | Comments: 14
Author: jiant
Link: https://github.com/Video-Rebirth/hyperflow-h3-flash
Show HN: We compressed a 31B video+audio diffusion model to 14B, 6 steps, INT8

document fetched 2026-11-14 02:59