FLUX 3 Review 2026: Black Forest Labs' Multimodal Video Model, Priced Per Second

Automated excerpt

FLUX 3 is Black Forest Labs’ first multimodal foundation model — video with native audio, images, and action prediction for robotics — built on a new Self-Flow architecture and sold per second of output. Black Forest Labs pitches FLUX 3 as “one multimodal model” — video with native audio now, images soon, action prediction for robotics. FLUX 3 is a diffusion-transformer foundation model trained jointly across images, video and audio.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.