2026-10-14 04:55
最后更新于2026-10-16 16:05
AI123
Reactor独家预览开源音视频生成模型FastH3-Omni
Reactor于2026年10月14日宣布推出FastH3-Omni，并将在其API上独家预览至2026年10月20日。FastH3-Omni是基于MiniMax实时H3模型的开源版本，由FastVideo（haoailab）与NuvA Lab参与后训练，官方称其为目前最快且质量最高的H3开源版本。
该模型支持首尾帧条件控制与音频输入，可从单一提示词直接生成带同步音频的视频内容。Reactor用户可以在预览期内通过其API进行体验。
来源
- 2026-10-14 04:26 | X：FastH3-Omni on Reactor - video with synchronized audio, from a single prompt. Your daydreams have a sound department now.阅读原文
FastH3-Omni on Reactor - video with synchronized audio, from a single prompt. Your daydreams have a sound department now. reactor: Introducing FastH3-Omni. The fastest and highest-quality open-source version of realtime H3 by @MiniMax_AI, post-trained by FastVideo @haoailab with @nuvalab. Exclusive ...