Deedy@deedydasBlack Forest Labs 发布 Flux 3，一个统一架构的多模态模型，覆盖图像、视频、音频和动作预测。其视频生成能力达到 Seedance 2 / Gemini Omni 级别，可生成约 20 秒带音频的视频，并已开放早期访问。Flux 3 还可扩展用于机器人动作预测，是当前唯一达到视频生成前沿水平的初创公司。
Flux 3 is a frontier video gen model at Seedance 2 / Gemini Omni caliber. It can do ~20s of video， with audio.
And it seems to be the only startup to be at the frontier of video.
Deedy@deedydas · XBlack Forest Labs 发布 Flux 3，一个统一架构的多模态模型，覆盖图像、视频、音频和动作预测。其视频生成能力达到 Seedance 2 / Gemini Omni 级别，可生成约 20 秒带音频的视频，并已开放早期访问。Flux 3 还可扩展用于机器人动作预测，是当前唯一达到视频生成前沿水平的初创公司。
Flux 3 is a frontier video gen model at Seedance 2 / Gemini Omni caliber. It can do ~20s of video， with audio.
And it seems to be the only startup to be at the frontier of video.