FLUX 3 Max Is Live on Aristotto

FLUX 3 Max is live: video from text or images, with sound, start and end frames, up to 10 keyframes, and up to 20 seconds in 1080p.

FLUX 3 Max is Black Forest Labs' top FLUX 3 video model, and it is now on Aristotto. Text to video, with sound: describe the scene and the sound together, and FLUX 3 Max generates both in one pass. Start and end frame: give it a first image and an optional last image, and it creates the motion between them. Keyframes: pin up to 10 images to points in the clip, and it moves smoothly from one to the next. Up to 20 seconds per generation, at 720p or 1080p, in 16:9, 9:16, 1:1, 21:9 and more. Every shot in the launch film was generated with FLUX 3 Max on Aristotto. Not sure what to test? Slow motion close-up in a sunny cafe: a barista pours steamed milk into an espresso and draws a perfect heart in the latte art, then slides the cup across the counter. Sound: gentle cafe chatter, the hiss of the steam wand, a cup clinking on a saucer.