MiniMax open-sources H3 omni-modal video model weights

MiniMax

Video official + media 4 src. ~1 min

MiniMax released the open weights of its H3 (Hailuo 3.0) omni-modal video model on Hugging Face on August 3, 2026, three days after its API-only debut. The 33B-parameter release includes FL2VA (text/first-last-frame) and Ref2VA (reference-to-video) checkpoints, generating up to 2K, 15-second clips with native stereo audio, and shipped with day-zero native ComfyUI support.

Why it matters

One of the largest open-weight video-generation releases to date with native synchronized audio, though its community license explicitly excludes the US, EU, UK, and South Korea from running the weights locally.

Importance: 4/5

Major open-weight release for a leading video-gen lab, corroborated by 4 independent sources (official + 2 primary-media).

text-to-video image-to-video open-weights audio-video-generation video-editing

Sources

official Open General Intelligence: MiniMax H3 Is Now Open Source

official MiniMax-H3 model card

media MiniMax H3 Open Weights Exclude US, EU, UK, and Korea From Local Deployment

media MiniMax H3 Open Weights Land With Native ComfyUI Support