Model
FLUX 3 x mimic: Next-Generation Video Action Model
Black Forest Labs released the multimodal foundation model FLUX 3, jointly training images, video, and audio, with video prediction accounting for over 95% of training compute. In collaboration with robotics company mimic, they launched FLUX-mimic, which has been tested and deployed on Audi's production lines. After adding action prediction, video generation quality initially dropped by up to 10%, but recovered to original levels after 3,500 steps of training.
Read the original (opens in a new tab)
News stream data aggregated by AI HOT