
TL;DR
Latent Painter introduces a novel method for generating painting animations by using the latent space as a canvas and diffuser predictions as a plan, enabling transitions between different images and overcoming traditional denoising limitations.
Contribution
This work presents Latent Painter, a new approach that leverages latent space and diffuser predictions for creative painting animation and image transitions.
Findings
Enables animation of paintings using latent space.
Allows transitions between images from different checkpoints.
Provides a new way to animate and morph generated images.
Abstract
Latent diffusers revolutionized the generative AI and inspired creative art. When denoising the latent, the predicted original image at each step collectively animates the formation. However, the animation is limited by the denoising nature of the diffuser, and only renders a sharpening process. This work presents Latent Painter, which uses the latent as the canvas, and the diffuser predictions as the plan, to generate painting animation. Latent Painter also transits one generated image to another, which can happen between images from two different sets of checkpoints.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsComputer Graphics and Visualization Techniques · Generative Adversarial Networks and Image Synthesis · Aesthetic Perception and Analysis
