View source for 18481308. HIGH-RESOLUTION IMAGE GENERATION USING DIFFUSION MODELS (ADOBE INC.)

=HIGH-RESOLUTION IMAGE GENERATION USING DIFFUSION MODELS=


==Organization Name==

[[:Category:ADOBE INC.|ADOBE INC.]]


[[Category:ADOBE INC.]]

==Inventor(s)==

[[:Category:Tobias Hinz of Campbell CA US|Tobias Hinz of Campbell CA US]][[Category:Tobias Hinz of Campbell CA US]]

[[:Category:Siddharth Iyer of San Francisco CA US|Siddharth Iyer of San Francisco CA US]][[Category:Siddharth Iyer of San Francisco CA US]]

==HIGH-RESOLUTION IMAGE GENERATION USING DIFFUSION MODELS==


This abstract first appeared for US patent application 18481308 titled 'HIGH-RESOLUTION IMAGE GENERATION USING DIFFUSION MODELS

==Original Abstract Submitted==

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.



[[Category:G06T11/00]]
[[Category:G06T3/40]]
[[Category:CPC_G06T11/00]]