FLUX 3

by Black Forest Labs model

Black Forest Labs' current model, and no longer just an image generator: FLUX 3 is described as "one multimodal model" covering image, video, audio and action-prediction for robotics, with video up to 20 seconds. The line's reputation was built on accurate text rendering inside images and handling complex prompts — still the reason to pick it over a general image model. FLUX.2, FLUX.2 Max and the smaller FLUX.2 Klein remain available, with open weights for self-hosting.

Visit site

Good at