MiniMax (official) is the team that develops and publishes the open-source video generation model MiniMax H3 and related tools. Recent coverage covers co-hosting the Japan IP AI Co-Creation Conference with KAGAMI AI (over 150 companies and guests including Yasushi Akimoto), the release of open H3 weights with native stereo audio and multimodal reference control, and community speedups such as VDN-H3/SGLang-Diffusion and FastH3 achieving over 2× real-time denoising on 8× B200 (14.4s of 768p in 9.0s).
The Japan IP AI Co-Creation Conference, co-hosted by KAGAMI AI and MiniMax, has officially concluded. 🇯🇵 🎉 We brought together more than 150 companies from Japan and the U.S., alongside distinguished guests including AKB48 producer Yasushi Akimoto, KAGAMI…
H3 keeps getting faster. ⚡️ @sgl_project + VDN-H3 now push MiniMax H3 beyond 2× real-time denoising on 8× B200 - generating 14.4s of 768p video in 9.0s end-to-end after warmup, with no measured quality regression. Open models compound through open ecosystems.…
Open weights. Shared progress. MiniMax H3 is moving fast. We built H3 for video generation with native stereo audio and multimodal reference control. The open-source community is making that capability faster, more accessible, and easier to build on. Recent h…
The A.I. Daily