Latent Painter

08/31/2023
by   Shih-Chieh Su, et al.
0

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.

READ FULL TEXT

page 3

page 4

page 5

page 6

research
08/06/2021

ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models

Denoising diffusion probabilistic models (DDPM) have shown remarkable pe...
research
05/04/2022

Joint Image Compression and Denoising via Latent-Space Scalability

When it comes to image compression in digital cameras, denoising is trad...
research
01/24/2019

On the Transformation of Latent Space in Autoencoders

Noting the importance of the latent variables in inference and learning,...
research
04/13/2017

Infinite Sparse Structured Factor Analysis

Matrix factorisation methods decompose multivariate observations as line...
research
08/18/2021

Deep Reparametrization of Multi-Frame Super-Resolution and Denoising

We propose a deep reparametrization of the maximum a posteriori formulat...
research
08/11/2023

Head Rotation in Denoising Diffusion Models

Denoising Diffusion Models (DDM) are emerging as the cutting-edge techno...
research
12/13/2021

Exploring Latent Dimensions of Crowd-sourced Creativity

Recently, the discovery of interpretable directions in the latent spaces...

Please sign up or login with your details

Forgot password? Click here to reset