US 12,437,437 B2
Diffusion models having continuous scaling through patch-wise image generation
Yinbo Chen, La Jolla, CA (US); Michaël Gharbi, San Francisco, CA (US); Oliver Wang, Seattle, WA (US); Richard Zhang, Burlingame, CA (US); and Elya Shechtman, Seattle, WA (US)
Assigned to ADOBE INC., San Jose, CA (US)
Filed by ADOBE INC., San Jose, CA (US)
Filed on Nov. 4, 2022, as Appl. No. 18/052,658.
Prior Publication US 2024/0161327 A1, May 16, 2024
Int. Cl. G06T 7/70 (2017.01); G06T 3/40 (2024.01); G06T 5/73 (2024.01); G06T 7/10 (2017.01)
CPC G06T 7/70 (2017.01) [G06T 3/40 (2013.01); G06T 5/73 (2024.01); G06T 7/10 (2017.01); G06T 2207/20084 (2013.01); G06T 2207/20132 (2013.01); G06T 2207/20212 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining a noise map and a global image code encoded from an original image and representing semantic content of the original image;
generating a plurality of image patches based on the noise map and the global image code using a diffusion model, wherein each image patch of the plurality of image patches is generated by denoising a noisy patch of the noise map based on the global image code; and
combining the plurality of image patches to produce an output image including the semantic content.