MiniMax H3 Dropped: T2V, I2V, and Reference-to-Video with Audio
multimodalart · x · 2026-08-03
MiniMax has officially released the H3 video generation model. With 33 billion parameters, it supports text-to-video, image-to-video, and reference-to-video capabilities, complete with synchronized audio generation.
The model weights are now available on Hugging Face. It has been integrated into the 🧨 Diffusers and ComfyUI ecosystems, making it ready for deployment and experimentation on consumer-grade GPUs.
Related event: MiniMax open-sources 33B multimodal video model H3(35 posts)→
More from Multimodal
- Surreal AI-generated landscape hides "another landscape inside the measurements" — piotrbinkowski · 2026-10-16
- Fan animation made in Blender with Claude Code (Opus 5.5) — Icy-Appointment3583 · 2026-10-16
- Making Blender animations with Opus, Astra and Argon: how you prompt still matters — chongdashu · 2026-10-16
- Tessellation-free geometric queries on displaced surfaces cut caustics variance 10x — ssh4net · 2026-10-16
- Complex multi-link CAD mechanism finally animates, dev celebrates the breakthrough — zetalyrae · 2026-10-16
- OpenMOSS releases MOSS-Image-SFT: Apache 2.0 text-to-image model on Hugging Face — bdsqlsz · 2026-10-16