FLUX 3 Action

Black Forest Labs

FLUX 3 Action is an open weights 7B world action model. It takes camera frames, the robot's state and a text instruction, and returns the next chunk of actions, denoised together with the next video frames.

Specs

Model

Family
FLUX
Variant
3 Action
Parameters
7B
Weights
Open
License
FLUX Kommunity License v1.0

Modalities

Input
Text Image Video

Dates

Released
22 Sept 2026

More from Black Forest Labs

All models

FLUX 3

Black Forest Labs

FLUX 3 is our new multimodal foundation model. It jointly learns from images, videos, and audio within a unified architecture, because what it needs to learn is not any one of these elements in isolation. Instead, a model must learn a representation of the world: how objects hold together, how things move, and how events sound.

—8w ago

Keep up with the tools

An occasional email when notable AI dev tools and models land in the directory. No spam, unsubscribe anytime.