First Hands-on with MiniMax H3: Supports 12 References for Video Generation
TomLikesRobots · x · 2026-07-30
Reviewer @TomLikesRobots shared their first generation using the new MiniMax H3 video model. The omni model accepts up to 12 references (audio or video, up to 15 seconds each) and outputs up to 15 seconds of 2K resolution video.
Related event: MiniMax H3 Tested for Native Multimodal Generation(2 posts)→
More from Multimodal
- MiniMax H3 Demo: High-Precision Lip Sync from Single Image and Audio — AIandDesign · 2026-07-30
- Higgsfield vs. Artlist ToS: Are Your AI Video Inputs Used for Training? — theodore_70 · 2026-07-30
- Batch Upscaling Old Game Textures with ComfyUI and ControlNet — MuffDivers2_ · 2026-07-30
- HeyGen's Video Podcast Feels Like a Recorded Show, User Says — hey_abusiddik · 2026-07-30
- Testing AI Video Tool Agent Two: Generating Cinematic Sci-Fi Shorts — LudovicCreator · 2026-07-30
- HeyGen Launches Video Podcast: Turn Docs and Links into Multi-Cam Shows — HeyGen · 2026-07-30