Text-to-Image, Image-to-Image, strong text and editing, detailed realism, and an understanding of motion.

Contact us for Commercial Weights - bfl.ai/contact?interest=flux… Try it - dashboard.bfl.ai/playground?… Learn more - bfl.ai/models/flux-3-image

Introducing FLUX 3 Image. Control every pixel. Make precise multi-turn edits without changing any other pixel. Lay out the image exactly how you want using bounding boxes. Generate in up to 4K to preserve details. Use up to 10 references to compose an image. Commercial Weights available for companies running image generation at scale. Open Weights version of FLUX 3 Image is launching in the coming weeks.

Introducing FLUX 3 Action. An open weights 7B World Action Model that achieves first place on the RoboLab benchmark. It outperforms the previous best open model by 6.1 percentage points while using 56% fewer parameters and running up to 3.95x faster.⁠⁠ FLUX 3 Action removes the usual trade-off between world action model performance and VLA speed: it still predicts video and actions together, but plans more than twice as far ahead and runs faster per second of robot motion than the strongest open VLA. Teams can fine-tune FLUX 3 Action on their own demonstrations to create policies for a particular robot and task. Together with @nvidia, we also integrated FLUX 3 Action natively into @huggingface's LeRobot, with fine-tuning recipes included and edge deployment on NVIDIA Jetson. Beyond robotics, we’re also seeing promising results training task-specific policies for acting in simulated environments like gaming, controlling a vehicle, computer use, and wherever else a model needs to understand a visual environment and then choose what to do next. FLUX 3 Action builds on the same image, video, and audio pretraining as FLUX 3, but uses a smaller architecture designed for practical deployment. In midtraining, we trained the model to predict actions and future frames together. We’re releasing the weights, code, fine-tuning recipe, benchmarks, and reproducible examples so researchers and developers can build on the model with their own robots, environments, and tasks (see below).

FLUX 3 Action controlling a simulated drone to take a specific requested action.

FLUX 3 Video now has fast, precise editing. The fastest and lowest cost video editing model in the world. In our internal benchmarking, it’s also ahead of other leading models in the accuracy and precision of edits. Edit an existing video by: • Adding, removing, or replacing objects and characters • Replacing backgrounds • Editing text • Changing colors, materials, visual effects • Changing or translating dialogue with accurate lip sync • Changing the events of a clip

It’s particularly good at making a specific edit without changing anything else. In testing, we noticed other leading models often alter other parts of your original video — even if you only requested a very specific edit. Not yet supported (but coming soon): • Using a separate video as a reference • Using images or audio as reference