minimaxListed 1 day ago
H3 Max Reference Director
Direct a continuous world in real time with image references and text prompts.
No reported score
No reported score
Direct continuous, realtime video streams with live prompts while preserving characters, settings, and story continuity.
Scores appear here when an evaluation matches this exact model.
Direct a continuous world in real time with image references and text prompts.
Train a MiniMax H3 LoRA with reference conditioning, so different modalities animate into video with audio; captions optional.
Train a MiniMax H3 LoRA on your own captioned clips for pure text-to-video generation with matching audio.
Train a MiniMax H3 LoRA on first/last/both keyframe signatures, teaching it to generate video with audio that starts on one image and lands on another.