chiprook
← AI
AIOctober 7, 2026, 22:49

Black Forest Labs launches FLUX 3, a multimodal video model with native audio

FLUX 3 is Black Forest Labs' first multimodal foundation model, built on the Self-Flow architecture: it generates video with native audio, images, and action prediction for robotics. Video ships now with up to 20-second generations at 720p–4K, billed per second from $0.17/s in HD to $0.80/s in 4K.

Black Forest Labs launches FLUX 3, a multimodal video model with native audio
#BlackForestLabs#FLUX
Read next
AI

Black Forest Labs launches Flux 3 Image with JSON bounding boxes and pixel-locked edits

AI

Black Forest Labs releases FLUX 3 Action, a 7B robot control model

AI

Shanghai AI Lab releases Intern-S2-397B science multimodal model

Software

Vercel Labs open-sources ScriptC, a native TypeScript compiler