MiniMax-H3
MiniMax-H3 video model API documentation, supporting text-to-video, image-to-video (first/last frame), multi-modal reference-to-video, direct 2K output, and video regeneration.
- Create Video Generation Task
- Query Video Generation Task
- Create H3-Context-IR Task
- Create Video Regeneration Task
Input material (first-frame image / reference image / reference video / reference audio) can be uploaded via the File Upload API first, then referenced as
mm_file://{file_id}.