返回
原文
MiniMax (official)@MiniMax_AI
53AI 编辑部评分，满分 100
2026-08-03 11:06· 51分钟前
跳到正文
AI 摘要

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。

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

vLLM🎉 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 ...
多模态行业动态
在 X 查看原推导出 Markdown
返回精选列表
53导出 Markdown
MiniMax (official) · @MiniMax_AI · X·2026-08-03 11:06·51分钟前
在 X 看原推· x.com
AI 摘要

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。

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

vLLM🎉 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 ...
多模态行业动态
在 X 查看原推x.com