MiniMax H3 pairs 2K video with native stereo audio in China's multimodal AI race
8 Articles
8 Articles
MiniMax has released the weights of its video model H3 and thus for the first time brought an open model to the top of a video ranking. The article MiniMax H3 is the first open video model in the video editing first appeared on The Decoder.
MiniMax H3 Open-Sourced: H3-Omni-Transformer With 33B Parameters Benchmarks Against Seedance 2.0 at One-Third API Price, Runs Locally on Two RTX 5090 Cards
MiniMax released open weights of video generation model H3 on HuggingFace, allowing local deployment and secondary development. Unlike text-to-video and image-to-video models, H3 is a general full-modal generation system: it understands contexts of text, images, video, and audio, then generates video with native stereo audio. Architecturally, H3 is not a serial connection of video and audio models. Its core network, H3-Omni-Transformer, is a den…
MiniMax, a Chinese AI development company, has announced its video generation AI, "MiniMax H3." MiniMax H3 can generate videos with sound up to 15 seconds in length and supports text, video, image, and audio input. The model itself is also scheduled to be released for free soon. Read more...
Coverage Details
Bias Distribution
- 100% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
