BFL launches FLUX 3 as a unified model for image, video, audio, and action prediction
umesh_ai · x · 2026-07-24
FLUX 3 debuts as a unified multimodal model
BFL announces FLUX 3, a single model for image, video, audio, and action prediction.
- FLUX 3 Video is already in early access.
- The company says the model is trained in a unified architecture.
- It can be extended to predict actions for robotics, and the thread points to work with Mimic and Audi.
The repost includes an example video test: a hyper-realistic, continuous 15-second action shot of a rally car outrunning an avalanche.
Related event: BFL Releases FLUX 3: A Unified Multimodal Model for Image, Video, and Audio(3 posts)→
More from Embodied
- OpenAI’s Codex keyboard ships, and early users say it’s pricey but fun — APPSO · 2026-07-24
- An $8 ESP32-S3 now runs a 28.9M-parameter model fully offline — brianrkelly · 2026-07-24
- TIME Features Unitree's GD01, the World's First Mass-Produced Transformable Mecha Robot — whurley · 2026-07-24
- OpenBMB opens up MiniCPM-Robot as its first embodied AI model family at WAIC — CyberRobooo · 2026-07-24
- Robot skins made by industrial knitting could enable scalable tactile sensing — mynkgoel · 2026-07-24
- Unitree shows Super Athlete AS2-W with 16 kg payload and 30+ km range — Scobleizer · 2026-07-24