Black Forest Labs launches FLUX 3, a multimodal model for image, video and audio
3scorciav · x · 2026-07-24
- Black Forest Labs introduced FLUX 3, a single multimodal model for image, video, audio, and action prediction.
- The company says FLUX 3 Video is already in early access.
- FLUX 3 is trained in one unified architecture, and the team says the same model family can be extended toward robotics action prediction.
- The post also points to work with Mimic and Audi, framing FLUX 3 as more than a media generator and closer to a general multimodal foundation.
Related event: BFL Launches FLUX 3: A Unified Multimodal Model for Video and Robotics(12 posts)→
More from Embodied
- DONIC hits 86.79% on bimanual dexterous tracking, crushing prior SOTA's 9.43% — liuziwei7 · 2026-10-27
- Bedrock Robotics raises $600M as its fully autonomous excavators do paid work on live job sites — Sethwinterroth · 2026-10-27
- AW-0 hits 80.8% on RoboTwin tasks, beating strongest baseline by 16 points — trevordarrell · 2026-10-27
- AW-0's code stream fixes world model prediction: picks mango where baseline grabs apple — trevordarrell · 2026-10-27
- AW-0 runs at 230ms on a single RTX 5090, 2.4x faster than autoregressive code planning — trevordarrell · 2026-10-27
- AW-0 debuts: one generative world action model plans in code, predicts, and controls robots — trevordarrell · 2026-10-27