Text-to-video · audio evaluated · all categories
95% CI 1,139.56–1,171.56 · n=5,440
Uses native 480P/768P generation or 1080P latent refinement; supports supplied soundtracks and selectable prompt expansion.
fal's H3 Max is a post-trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics while co-optimized with our custom inference stack for higher throughput with no compromises on output quality
Text-to-video · audio evaluated · all categories
95% CI 1,139.56–1,171.56 · n=5,440
Text-to-video · silent evaluation · all categories
95% CI 1,101.75–1,135.75 · n=5,734
minimax/h3-max/text-to-video75aebebb-6692-4bca-8c59-54336e4da6a3Updated Oct 20, 2026
Relight any video with H3 Max from a lighting sphere image, while preserving the source subjects, motion, camera and audio.
Extend an existing video with H3 Max Turbo: add 1 to 15 seconds of prompt-guided footage, with optional audio references and output resolutions from 480p to 2K.
Replaces people across shots from reference photos in 5–30 second videos, retaining the source soundtrack.
Insert a new scene into an existing video with H3 Max. Guide the scene with a prompt, reference images, or reference videos, then return to the original footage.