Video model · MiniMax
MiniMax H3 Max
Video generation from text, frames, and multimodal references
What is MiniMax H3 Max?
MiniMax H3 Max generates video from text, image frames, or a combination of reference images, video, and audio. Use it for reference-driven scenes and first-to-last-frame transitions at 480P or 768P.
Capabilities
- Generate video from a text prompt
- Animate a still image into video
- Keep characters and products consistent with reference images
MiniMax H3 Max on Melius
Melius runs MiniMax H3 Max alongside every other major image, video, audio, and text model, so you can use it alongside other models in your workflow — all on one infinite canvas. You only pay for what you generate.
Frequently asked questions
What is MiniMax H3 Max?
MiniMax H3 Max generates video from text, image frames, or a combination of reference images, video, and audio. Use it for reference-driven scenes and first-to-last-frame transitions at 480P or 768P.
How do I use MiniMax H3 Max on Melius?
Melius is a node-based canvas: add a video node, pick MiniMax H3 Max from the model picker, and connect it to whatever should feed it or follow it. You only pay for what you generate.