Efficient-Large-Model/Open-H3-Regenerate-2K
video-to-video · ♥ 140 · ↓ 0
- Taskvideo-to-video
- Downloads414k
- Likes196
- Licenseother
video-to-video · ♥ 140 · ↓ 0
An open replacement for the closed H3-Regenerate-2K API: a three-step MiniMax-H3 refinement pass that regenerates a 768P H3 draft (1344×768, 121 frames) at 2560×1440.
One 5 s clip, 768P latent → 2560×1440 video: latent upscale + 3-step refine + VAE decode, warm, median of 3 runs:
Excerpt from the model card on Hugging Face ↗.
Efficient-Large-Model/Open-H3-Regenerate-2K was first seen on Hugging Face · Trending models on Oct 31, 2026. Since then it has appeared in 77 checks on 5 different days. Its best position was #24 of 30, reached on Nov 4, 04:42 UTC. It dropped off the list after Nov 4, 22:42 UTC.
Position on Hugging Face · Trending models at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 4, 22:42 UTC, after 5 days of trending.
#24 on Hugging Face · Trending models, on Nov 4, 04:42 UTC. Trendoday checks this list every 60 minutes.
It was first seen on Oct 31, 2026 and has been on the list on 5 days (77 checks) since.
It is tagged video-to-video with minimax-h3 on Hugging Face and has 414k downloads under the other license.