MiniMax H3 community projects speed up open-source video generation
Original titleOpen weights. Shared progress. MiniMax H3 is moving fast.
AISummary
MiniMax highlighted open-source community progress on its H3 video generation model, which it built with native stereo audio and multimodal reference control.
Recent highlights include FastH3's 4-step distillation running on DGX Spark and Apple Silicon, and NVIDIA's Sol-H3 generating 15 seconds of 768p video with audio in 6.6 seconds on 8×B300 in a warm-inference benchmark.
Other releases include VDN's faster-inference attention work with code and weights, and 8-step Acc-LoRAs from Alibaba PAI, with LightX2V offering 4- and 8-step Turbo LoRAs.
Source: MiniMax · x.comPublished · added here