AI product Open source
h3-metal is a native plain-C and Metal inference engine for the MiniMax H3 video model on Apple Silicon Macs. It provides a command-line interface and Iris-style interactive session for prompt-to-video and prompt-to-audio generation, including synchronized stereo audio, first- and last-frame conditioning, and ordered Ref2VA image, video, and audio references. The CLI can inspect model layout and the selected Metal device, run prompt-to-media jobs, and retain exact BF16 prompt conditioning, the prepared diffusion transformer, and video decoder in memory so repeated prompts with different seeds avoid reloading and re-encoding them. Configurable controls include denoising passes, transition reuse, transformer layers, frame dimensions, seeds, and output files. The project is developed through incremental vertical slices covering deterministic host and model metadata, portable Metal block parity, prompt encoding, media generation, conditioning, and H3-specific Metal performance and memory optimization.
3 uses taken from transcripts — each links to the moment in the video.
A plain-C and Metal implementation that runs Miniax’s H3 video model on Apple Silicon. It generates video with synchronized stereo audio from prompts, frame anchors, or ordered media references.
A native inference engine for running the Miniax H3 video model on Apple Silicon Macs. It generates short videos with synchronized audio from text and supports image, video, and audio conditioning.
Runs Minimax H3 video generation natively on Apple silicon using C and Metal without a hosted service. It supports prompt-to-video with audio, frame conditioning, media references, interactive sessions, and SSD streaming.
3 in the library.