H3 Max Text to Video
H3 Max is a post-trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics while co-optimized with our custom inference stack for higher throughput with no compromises on output quality
Model Catalog
Search image, video, audio, and avatar models available in Plotspace.
H3 Max is a post-trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics while co-optimized with our custom inference stack for higher throughput with no compromises on output quality
H3 Max is a post-trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics while co-optimized with our custom inference stack for higher throughput with no compromises on output quality
Generate 768p video with audio in an automatically applied 16-bit pixel-art style.
Generate 768p video with audio in an automatically applied hand-drawn animation style.
Generate 768p video with audio in an automatically applied retro low-poly 3D style.
Generate 768p video with audio in an automatically applied retro 1970s hand-painted animation style.
Generate 768p VHS-style video with audio and adjustable tape wear and distortion.
Generate a talking video from an image and supplied audio, with synchronized mouth movements.
Animate an image with precise keyframe control over camera orbit, elevation, and distance.
Generate video with audio from a prompt, optionally conditioned on first- and last-frame images.
Generate video with synchronized audio from a text prompt using the faster MiniMax H3 Max Turbo model.
FLUX 3 is Black Forest Labs' frontier video model. This endpoint animates a single still image into video, extending one frame into coherent, natural motion.