MiniMax releases MiniMax-H3 open-weight video model
MiniMax has launched MiniMax-H3, an open-weight omni-modal video generation model capable of producing up to 15-second 2K resolution videos at 24 fps featuring native synchronized stereo audio. The model supports versatile multimodal workflows including text-to-video, image-to-video, video editing, and motion transfer, backed by day-one ComfyUI integration to provide creators with an accessible, less restricted tool for AI video synthesis.
MiniMax-H3 sets a impressive benchmark for open-weight generative media by tightly coupling high-resolution video output with native stereo audio synthesis.
• Delivers up to 15-second 2K videos at 24 fps with native stereo sound.
• Supports comprehensive video workflows including image-to-video, video editing, and motion transfer.
• Provides day-one ComfyUI integration for seamless inclusion in custom local AI workflows.
DISCOVERED
1h ago
2026-08-07
PUBLISHED
1h ago
2026-08-07
RELEVANCE
AUTHOR
AI Samson