Lakonik/pi-H3
image-text-to-video · ♥ 147 · ↓ 9K
- Taskimage-text-to-video
- Downloads0
- Likes105
- Licenseother
image-text-to-video · ♥ 147 · ↓ 9K
Hansheng Chen1*, Shengqu Cai1, Jiaming Song†, Gordon Wetzstein1, Xinchen Yan†, Leonidas Guibas1 1Stanford University *Part of work done during an internship at Luma AI, †Work done while at Luma AI Blog | Code | ComfyUI | pi-H3 Demo🤗
2-step and 4-step adapters of MiniMax H3, the fastest way to generate MiniMax H3 videos with synchronized audio. pi-H3 combines pi-Flow v2 few-step distillation with DWD (Decoding Without a Decoder), which predicts the video frames directly at the last step, so the video skips the VAE decoder.
Excerpt from the model card on Hugging Face ↗.
Lakonik/pi-H3 was first seen on Hugging Face · Trending models on Nov 22, 2026. Since then it has appeared in 10 checks on 1 different day. Its best position was #18 of 30, reached on Nov 22, 16:45 UTC. It is #18 right now, climbing from #23 to #18 over the last 6 checks.
Position on Hugging Face · Trending models at every check (lower is better).
Best rank per day (UTC).
🔥 as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Yes. As of Nov 22, 16:45 UTC it is #18, climbing from #23 to #18 over the last 6 checks.
#18 on Hugging Face · Trending models, on Nov 22, 16:45 UTC. Trendoday checks this list every 60 minutes.
It was first seen on Nov 22, 2026 and has been on the list on 1 day (10 checks) since.
It is tagged image-text-to-video with diffusers on Hugging Face and has 0 downloads under the other license.