Shanghai AI Lab, CUHK & Stanford U Extend Personalized Text-to-Image Diffusion Models Into Animation Generators Without Tuning

In a new paper AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning, a research team presents AnimateDiff, a general and practical framework that is able to generate animated images for any personalized text-to-image (T2I) model, without any extra training and model-specified tuning.

ai animated animation animation generator artificial intelligence computer vision & graphics deep-neural-networks diffusion diffusion model diffusion models extra framework general image image diffusion images lab machine learning machine learning & data science ml paper personalized practical research research team shanghai stanford team technology text text-to-image training