返回全部动态
MiniMax H3开源模型首次登顶AI视频排名
原标题：China's MiniMax H3 is the first open model to top an AI video ranking
AI 摘要
中国公司MiniMax发布了H3视频模型权重，成为首个在AI视频排名中登顶的开源模型。该模型拥有330亿参数，能处理文本、图像、视频和音频，生成4至15秒带立体声的片段。尽管2K分辨率模块和H3-Context-IR未开源，但开放权重允许微调，商业使用仅限年收入低于2000万美元的公司。同日，字节跳动发布了闭源的Seedance 2.5模型。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
China's MiniMax H3 is the first open model to top an AI video ranking MiniMax releases H3 video model weights, putting an open model at the top of a video ranking for the first time. Artificial Analysis ranks H3 first in Video Editing, second in Text-to-Video, and third in Image-to-Video. The 33-billion-parameter model processes text, images, video, and audio together, generating four- to 15-second clips with stereo sound. According to the model card, a single prompt can include up to nine refer
发布时间：2026-08-03 21:52
抓取时间：2026-08-03 22:55
来源机构：THE DECODER