HIGH-RESOLUTION IMAGE GENERATION USING DIFFUSION MODELS

Number of patents in Portfolio can not be more than 2000

United States of America Patent

APP PUB NO 20250117968A1
SERIAL NO

18481308

Stats

ATTORNEY / AGENT: (SPONSORED)

Importance

Loading Importance Indicators... loading....

Abstract

See full text

Methods, non-transitory computer readable media, apparatuses, and systems for high-resolution image generation using diffusion models include obtaining a prompt and generating, using a first diffusion model, a predicted denoised image at a first resolution based on the prompt. The predicted denoised image is generated at a first intermediate diffusion step of the first diffusion model. The predicted denoised image is upsampled to obtain an upsampled denoised image at a second resolution that is higher than the first resolution. A second diffusion model then generates an output image at the second resolution based on the prompt and the upsampled denoised image.

Loading the Abstract Image... loading....

First Claim

See full text

Family

Loading Family data... loading....

Patent Owner(s)

Patent OwnerAddress
ADOBE INC345 PARK AVENUE SAN JOSE CA 95110-2704

International Classification(s)

  • [Classification Symbol]
  • [Patents Count]

Inventor(s)

Inventor Name Address # of filed Patents Total Citations
Hinz, Tobias Campbell, US 75 686
Iyer, Siddharth San Francisco, US 4 0

Cited Art Landscape

Load Citation

Patent Citation Ranking

Forward Cite Landscape

Load Citation