LaunchAI ModelsJuly 26, 2026

Black Forest Labs releases FLUX 3 multimodal model

FLUX 3 generates video with native audio, images, and robot action predictions from one architecture, with clips up to 20 seconds. Available via early access on BFL and partners like Replicate, Runway, and Together AI; open weights coming soon.

How this story unfolded

2 weeks · 3 reports · 15 community posts · from Jul 26

Jul 26
- Black Forest Labs Releases FLUX 3: A Multimodal Flow Model for Image, Video, Audio and Robot Action Predictionmarktechpost.com
- Flux 3 looks insane. This was 1 prompt
Jul 27
- Flux 3: Black Forest Labs' Open-Source Answer to Sora 2 and Robotics AImindstudio.ai
Jul 29
Jul 30
Jul 31
- FLUX 3 Video Generation Test Reel
Aug 1
- Flxu 3 is GREAT at doing home movies (americas funniest home videos0
Aug 4
Aug 5
Aug 6
- FLUX 3 is now live on Together AI. @bfl_ai’s new multimodal model generates video and synchronized...
Aug 10
- The Ultimate Guide to FLUX 3replicate.com
Aug 11
- Upcoming open-weight Flux 3 video got updated and trails closed-source leader model on benchmarks

Daily brief

Get tomorrow's AI brief in your inbox

Black Forest Labs releases FLUX 3 multimodal model

How this story unfolded

Daily brief

More stories today