Event ·Multi-source

Flux 3上线Genspark AI视频智能体，支持原生音频

Black Forest Labs发布Flux 3视频模型，现已集成至Genspark AI Video Agent。该模型支持原生音频、文生视频、图生视频和视频续写，可生成多语言对话内容。输出规格最高20秒、1080p分辨率，并提供Draft模式以降低探索成本。2K、4K及开放权重版本计划后续推出。

Current read

黑森林家的Flux 3视频模型来了，Genspark里直接用，带原生音频，最长20秒1080p，还能多语言对话，快去试试。

7 sources76° AI heatLast updated 2026/8/5 01:24:43

Evidence

7 sources

Primary sourceGenspark

2026/8/5 01:24:43View source

Related source 1Justine Moore

2026/8/4 17:56:45View source

Related source 2IT之家

2026/8/6 05:54:25View source

Related source 3OpenRouter

2026/8/4 17:54:06View source

Related source 4Decoder

2026/8/5 13:06:48View source

Related source 5Eric Jing

2026/8/3 14:07:16View source

Related source 6Pika Labs

2026/8/5 18:23:50View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story