公开(公告)号：US20240303873A1

公开(公告)日：2024-09-12

申请号：US18333695

申请日：2023-06-13

申请人： Salesforce, Inc.

发明人： Bram Wallace ,  Nikhil Naik

IPC分类号： G06T11/00 ,  G06T5/00

CPC分类号： G06T11/00 ,  G06T5/70 ,  G06T2207/20084

摘要： Embodiments described herein provide a method of generating an image. the method comprises receiving, via a data interface, a natural language prompt, obtaining a noised image vector, and generating a denoised image vector by a first forward pass of a plurality of iterations of a denoising diffusion model with the noised image vector as an input and conditioned on the natural language prompt. The method further includes calculating a gradient of a loss function based on the denoised image vector with respect to the noised image vector, and updating the noised image vector based on the gradient. A final image is generated using a final forward pass of the denoising diffusion model with the updated noised image vector as an input and conditioned on the natural language prompt.

公开(公告)号：US20240161248A1

公开(公告)日：2024-05-16

申请号：US18175156

申请日：2023-02-27

申请人： Salesforce Inc.

发明人： Nikhil Naik ,  Bram Wallace

IPC分类号： G06T5/00 ,  G06T5/30 ,  G06T5/50

CPC分类号： G06T5/002 ,  G06T5/30 ,  G06T5/50 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20216

摘要： Embodiments described herein provide systems and methods for image editing. a first copy and a second copy of an input image are generated; noise is iteratively added to the first copy and the second copy by: updating the first copy based on a first inverted output of a denoising diffusion model (DDM) based on the second copy and a first caption and updating the second copy based on a second inverted output of the DDM based on the first copy and the first caption. A resultant noised image is iteratively denoised by a reverse process using the DDM conditioned on a second caption, thereby producing a final image.