Black Forest Labs Releases FLUX 3 Multimodal Model
The model unifies image, video, audio generation and action prediction for robotics.
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 available in early access (link below). Jointly trained in one unified architecture, our model can be extended to…
Reactions
29 postsMW 
Markus Wulfmeier@m_wulfmeier- likes: 0
- replies: 0
- bookmarks: 0
- reposts: 0
CP Chris Paxton@chris_j_paxtonVideo models are really changing things for robotics https://twitter.com/bfl_ai/status/2080308988961554582
- likes: 80
- replies: 2
- bookmarks: 19
- reposts: 5
LB Lucas Beyer (bl16)@giffmanaI really like BFL folks, so pretty happy to see this progress from them! https://twitter.com/bfl_ai/status/2080308988961554582
- likes: 262
- replies: 13
- bookmarks: 38
- reposts: 2
LB Lucas Beyer (bl16)@giffmanaNotice the robot hand at the end, a nice nod to https://x.com/mimicrobotics/status/2080307032746336367?s=20
- likes: 4
- replies: 0
- bookmarks: 0
- reposts: 0
AC Andrew Curran@AndrewCurran_@giffmana Great team, I think people forgot how great the FLUX image model was when it came out because two years ago is centuries in AI time, but it was world class.
- likes: 13
- replies: 0
- bookmarks: 0
- reposts: 0
EM Emad@EMostaque~4 years ago @robrombach & @pess_r had just finished the first training runs for stable diffusion (!) Now FLUX 3 is unifying modalities & state of the art again Amazing team (& lovely chaps), where will be 4 years from now 👀…
- likes: 505
- replies: 16
- bookmarks: 88
- reposts: 20