MiniMax H3
Provided by Fal — Learn More — MiniMax H3 on Fuser
MiniMax H3 is MiniMax's frontier video model, generating up to 2K and 4K video from text, a starting image, or multimodal references. In reference mode it accepts subject and style images, motion video clips, and audio clips — cite them in the prompt as Image 1, Video 1, Audio 1, and so on — to steer identity, motion, and sound in a single coherent shot of up to 15 seconds. H3 Max is fal's post-trained variant tuned for stronger prompt adherence and aesthetics at up to 1080p, and adds first, middle, and last frame control that can be combined with references. H3 Max Turbo offers faster text and image generation.
Luma Video
Luma Video is an Open video generation model with high visual quality, motion diversity, text-video alignment, and generation stability.
MiniMax H3 Recast
MiniMax H3 Max Recast replaces the people in an existing video with the people in your reference photos, while preserving the source motion, camera work, cuts, and audio. Provide a 5–30 second video and one photo per new person; by default they replace the main people in the video from left to right, in every shot they appear in. Add an optional prompt to say who becomes whom, or what else to keep or change.