返回
原文
MiniMax (official)@MiniMax_AI
67AI 编辑部评分，满分 100
2026-08-03 11:12· 45分钟前
跳到正文
AI 摘要

MiniMax H3 权重正式开源，并在发布当天（Day 0）原生集成到 ComfyUI，支持文本生视频、图像生视频、首尾帧控制、参考视频及就地编辑五种工作流。H3 以多模态上下文理解为核心，可同时处理图像、音频和视频，并依据提示词解析其关联。

The weights are here. The nodes are native. The rest is up to your graph. 👀 H3 is in @ComfyUI on Day 0！！

one model， five workflows， endless ways to wire it. 😌

#MiniMaxH3 #OpenWeights

ComfyUIMiniMax H3 is native in ComfyUI, day zero with the weights. Model highlights: → Text-to-video, prompt only → Image-to-video → First-and-last-frame - control the...
MCP/工具多模态开源生态模型发布
在 X 查看原推导出 Markdown
返回精选列表
67导出 Markdown
MiniMax (official) · @MiniMax_AI · X·2026-08-03 11:12·45分钟前
在 X 看原推· x.com
AI 摘要

MiniMax H3 权重正式开源，并在发布当天（Day 0）原生集成到 ComfyUI，支持文本生视频、图像生视频、首尾帧控制、参考视频及就地编辑五种工作流。H3 以多模态上下文理解为核心，可同时处理图像、音频和视频，并依据提示词解析其关联。

The weights are here. The nodes are native. The rest is up to your graph. 👀 H3 is in @ComfyUI on Day 0！！

one model， five workflows， endless ways to wire it. 😌

#MiniMaxH3 #OpenWeights

ComfyUIMiniMax H3 is native in ComfyUI, day zero with the weights. Model highlights: → Text-to-video, prompt only → Image-to-video → First-and-last-frame - control the...
MCP/工具多模态开源生态模型发布视频
在 X 查看原推x.com