Black Forest Labs

Control every pixel.​​​​‌ ‍ ​‍​‍‌‍ ‌ ​‍‌‍‍‌‌‍‌ ‌‍‍‌‌‍ ‍​‍​‍​ ‍‍​‍​‍‌ ​ ‌‍​‌‌‍ ‍‌‍‍‌‌ ‌​‌ ‍‌​‍ ‍‌‍‍‌‌‍ ​‍​‍​‍ ​​‍​‍‌‍‍​‌ ​‍‌‍‌‌‌‍‌‍​‍​‍​ ‍‍​‍​‍​‍ ‌ ​ ‌ ‌​‌ ‌‌‌‍‌​‌‍‍‌‌‍ ​‍ ‌‍‍‌‌‍ ‍‌ ‌​‌‍‌‌‌‍ ‍‌ ‌​​‍ ‌‍‌‌‌‍‌​‌‍‍‌‌ ‌​​‍ ‌‍ ‌‌‍ ‌‍‌​‌‍‌‌​ ‌‌ ​​‌ ​‍‌‍‌‌‌ ​ ‌‍‌‌‌‍ ‍‌ ‌​‌‍​‌‌ ‌​‌‍‍‌‌‍ ‌‍ ‍​ ‍ ‌‍‍‌‌‍‌​​ ‌‌‍‌‍‌‍ ​‌ ‌‌‌ ‍​​ ​ ‌​‍‌‌‍ ‌‌‍​‌‌‍‌ ‌‍‌‌‌​ ​‌‍​‌‌‍ ‍‌‍‌​‌‍‍‌‌‍ ‍‌‍‌ ​ ‍ ‌ ‌​‌ ‍‌‌ ​​‌‍‌‌​ ‌‌‍‌‍‌‍ ​‌ ‌‌‌ ‍​​ ​ ‌​‍‌‌‍ ‌‌‍​‌‌‍‌ ‌‍‌‌‌​ ​‌‍​‌‌‍ ‍‌‍‌​‌‍‍‌‌‍ ‍‌‍‌ ​ ‍ ‌ ​​‌‍​‌‌ ‌​‌‍‍​​ ‌‌‍‍​‌‍‌‌‌ ​‍‌‍ ​‍ ‍‌ ‌​‌‍‍‌‌ ‌​‌‍ ​‌‍‌‌‌​‌​‌‍‍‌‌‍ ‌​ ‌‍​‍‌‍​‌‌ ​ ‌‍‌‌‌‌‌‌‌ ​‍‌‍ ​​ ‌​‍‌‌​ ​‍‌​‌‍‌ ​ ‌ ‌​‌ ‌‌‌‍‌​‌‍‍‌‌‍ ​‍‌‍‌‍‍‌‌‍‌​​ ‌‌‍‌‍‌‍ ​‌ ‌‌‌ ‍​​ ​ ‌​‍‌‌‍ ‌‌‍​‌‌‍‌ ‌‍‌‌‌​ ​‌‍​‌‌‍ ‍‌‍‌​‌‍‍‌‌‍ ‍‌‍‌ ​‍‌‍‌ ‌​‌ ‍‌‌ ​​‌‍‌‌​ ‌‌‍‌‍‌‍ ​‌ ‌‌‌ ‍​​ ​ ‌​‍‌‌‍ ‌‌‍​‌‌‍‌ ‌‍‌‌‌​ ​‌‍​‌‌‍ ‍‌‍‌​‌‍‍‌‌‍ ‍‌‍‌ ​‍‌‍‌ ​​‌‍​‌‌ ‌​‌‍‍​​ ‌‌‍‍​‌‍‌‌‌ ​‍‌‍ ​‍ ‍‌ ‌​‌‍‍‌‌ ‌​‌‍ ​‌‍‌‌‌​‌​‌‍‍‌‌‍ ‌​‍‌‍‌ ​​‌‍‌‌‌ ​‍‌ ​ ‌ ​​‌‍‌‌‌‍​ ‌ ‌​‌‍‍‌‌ ‌‍‌‍‌‌​ ‌‌ ​​‌ ‌‌‌‍​‍‌‍ ​‌‍‍‌‌ ​ ‌‍‍​‌‍‌‌‌‍‌​​‍​‍‌ ‌ Stylistically diverse beyond just cinematic, with native audio and up to 20 second clips in a single generation. Start from text, an image, or keyframes, and get multiple shots in one take. Optional audio. Multilingual speech, effects and ambience generated with the frames. Images grounded in the real world. A wide variety of styles, highly-accurate text rendering, and the ability to handle complex prompts. Unifies perception, simulation and execution for robotics. Takes visual observations and text instructions as input to predict the desired physical outcome visually and as robot control actions. Learn more Whether you're scaling through API, running open weights on your infrastructure, or just experimenting – our models work wherever you do.