# Flux 3 视频生成达前沿水平，支持音频与机器人动作预测

- 来源：Deedy (@deedydas)
- 发布时间：2026-07-23 23:45
- AIHOT 分数：54
- AIHOT 链接：https://aihot.virxact.com/items/cmrxp0b4h016yroxpkmotvfgb
- 原文链接：https://x.com/deedydas/status/2080318330913869943

## AI 摘要

Black 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。

## 正文

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.

### 引用推文

> Black Forest Labs：Introducing FLUX 3. One multi-modal model for Image, Video, Audio and Action-Prediction. Creations are truer to life in every kind of style. FLUX 3 Video is now...