# FLUX 3 统一多模态，视频已开放早期访问

- 来源：Emad (@EMostaque)
- 发布时间：2026-07-24 00:16
- AIHOT 分数：59
- AIHOT 链接：https://aihot.virxact.com/items/cmrxr14pn01mcroxp83i95z28
- 原文链接：https://x.com/EMostaque/status/2080326079131128056

## AI 摘要

Black Forest Labs 发布 FLUX 3，一个统一架构的多模态模型，支持图像、视频、音频和动作预测。FLUX 3 Video 现已开放早期访问，模型还可扩展用于机器人动作预测。

## 正文

~4 years ago @robrombach &amp； @pess_r had just finished the first training runs for stable diffusion （！）

Now FLUX 3 is unifying modalities &amp； state of the art again

Amazing team （&amp； lovely chaps）， where will be 4 years from now 👀

### 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...