Todos los modelos
generación de video
MiniMax H3
MiniMax H3 is a multimodal 2K video model that combines text, first/last frames, image, video, and audio references with native synchronized sound. It is designed for consistent subjects, voices, motion, and scene identity across generated or continued shots, and supports 5-to-15-second output in six aspect ratios.
From 186 Gobostock credits; surcharges or usage-based pricing may apply where shown in the tool quote. El presupuesto que se muestra en la herramienta es el que pagas.
Team reviewing a product prototype
Generado con IA · MiniMax H3
Ideal para
- Cinematic multi-shot clips with coordinated sound
- Character performance or motion guided by several references
Límites conocidos
- It is expensive per second of output compared with the other video models.
- Frame inputs cannot be combined with the other reference groups in the same request.
Capacidades
- Text, image, video, and audio-guided generation
- First/last-frame interpolation and continuation workflows
- Native synchronized audio at 768p or 2K
Entradas
- Text prompt
- Duration and output format
- Optional supported image, video, or audio references
Salidas
- MP4 video
Comparar