Latent diffusers have gained a lot of traction in generative AI for their efficiency, content diversity, and reasonable footprint. This work presents Latent Painter, which uses the latent as the canvas, and the diffuser predictions as the plan, to generate painting animation. The highly diversed family of latent diffusers can all be animated.

Latent Painter can also transit one image to another, providing additional options to the existing interpolation-based method. In fact, it also transits the generated images from two different sets of checkpoints.