Self-Trained ref2vid Model Generates 15-Second Video in Seconds

Developer Kyrannio showcased a self-trained ref2vid model that generates a coherent 15-second video from 5 reference images in about 6 seconds, with generation speed as a key optimization focus.

2026-10-30 ~ 2026-10-30 · 2 related posts

• Self-trained ref2vid model generates 15s clips with reference images in ~6.9s — Kyrannio · 2026-10-30
• Dev's posttrained ref2vid model turns 5 reference images into 15s video in ~6 seconds — Kyrannio · 2026-10-30