Norsk(NO) #1. Not just among open models. SOTA, full stop. 🥇

MiniMax AI 发布开源音乐模型，并在视频编辑基准测试中名列前茅

作者 PulseAugur 编辑部 · [2 个来源] · 2026-08-13 16:25

MiniMax AI 发布了 Minimax Music 3，这是一个开源的音乐生成模型，采用了 8B LLM 和 2.7B Diffusion Transformer。该模型能够根据文本提示和歌词生成完整的歌曲，并通过 diffusers 和 Comfy 等库在消费级 GPU 上运行。此外，MiniMax AI 还宣布其 H3 模型 MiniMax-H3 在 Video Edit Arena 中取得了最高排名，获得 1390 分，超越了 Dreamina Seedance 2.0 和 Gemini Omni Flash 等竞争对手。 AI

影响为开源音乐生成和视频编辑基准测试设定了新的 SOTA，可能加速这些功能的采用。

排序理由该集群报道了前沿 AI 实验室 (MiniMax AI) 发布新开源模型 (Minimax Music 3) 和取得顶级基准测试成就 (MiniMax-H3)。[lever_c_demoted from frontier_release: ic=2 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Significant; 该集群报道了前沿 AI 实验室 (MiniMax AI) 发布新开源模型 (Minimax Music 3) 和取得顶级基准测试成就 (MiniMax-H3)。[lever_c_demoted from frontier_release: ic=2 ai=1.0]
Source corroboration: 2 independent sources; Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics: model release, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 47 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

X — MiniMax AI TIER_1 English(EN) · MiniMax_AI · 2026-08-13 16:30

感谢 Huggingface 团队 @multimodalart，开放权重音乐模型已支持！

Thanks for Huggingface team @multimodalart , day 0 support open weight music model!
X — MiniMax AI TIER_1 Norsk(NO) · MiniMax_AI · 2026-08-13 16:25

不仅在开源模型中领先。SOTA，仅此而已。🥇

#1. Not just among open models. SOTA, full stop. 🥇 H3 just took the crown on Video Edit Arena. Drop in your footage, prompt the impossible, and let H3 reimagine every frame. Show us your wildest edit. 🔥