MiniMax (official)· @MiniMax_AI · X·· 2026-08-03AI 评分53
AI 导读
MiniMax H3 开源权重，并在 vLLM-Omni 中获得 Day 0 支持，提供兼容 OpenAI 的视频端点。该模型可将文本、图像、视频和音频作为单一上下文处理，支持文生视频、首/尾帧及多参考生成，输出 4-15 秒、最高 2K 24 FPS 的 H.264 视频并自带同步立体声。
正文 · 原文
Open weights are step one. Making them easy to serve is step two. H3 now has Day 0 support in @vllm_project's vLLM-Omni, complete with an OpenAI-compatible video endpoint.
Huge thanks to the vLLM team for bringing H3 into the open inference stack. ⚡
#MiniMaxH3 #OpenWeights
🎉 Congrats to @MiniMax_AI on releasing the open weights for MiniMax H3! Day-0 support in vLLM-Omni! One model reads text, images, video, and audio as a single context and returns video with native stereo audio. Text-to-video, first/last-frame, and multi-reference generation, 4 to 15 seconds at up to 2K and 24 FPS. The MP4 comes back with H.264 video and a synchronized stereo track already muxed in. It serves over the OpenAI-compatible /v1/videos endpoint, synchronous or async with job polling. 🔊 The video ⬇️ was made with H3, served on vLLM-Omni.在 X 查看被引用的帖子
来源：MiniMax (official) · x.com