Skip to main navigation Skip to search Skip to main content

Shifted Diffusion for Text-to-image Generation

  • SUNY Buffalo
  • ByteDance Ltd.

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

58 Scopus citations

Abstract

We present Corgi, a novel method for text-to-image generation. Corgi is based on our proposed shifted diffusion model, which achieves better image embedding generation from input text. Unlike the baseline diffusion model used in DALL-E 2, our method seamlessly encodes prior knowledge of the pre-trained CLIP model in its diffusion process by designing a new initialization distribution and a new transition step of the diffusion. Compared to the strong DALL-E 2 baseline, our method performs better in generating image embedding from the text in terms of both efficiency and effectiveness, resulting in better text-to-image generation. Extensive large-scale experiments are conducted and evaluated in terms of both quantitative measures and human evaluation, indicating a stronger generation ability of our method compared to existing ones. Furthermore, our model enables semi-supervised and language-free training for text-to-image generation, where only part or none of the images in the training dataset have an associated caption. Trained with only 1.7% of the images being captioned, our semi-supervised model obtains FID results comparable to DALL-E 2 on zero-shot text-to-image generation evaluated on MS-COCO. Corgi also achieves new state-of-the-art results across different datasets on downstream language-free text-to-image generation tasks, outperforming the previous method, Lafite, by a large margin.

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
PublisherIEEE Computer Society
Pages10157-10166
Number of pages10
ISBN (Electronic)9798350301298
ISBN (Print)9798350301298
DOIs
StatePublished - 2023
Event2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 - Vancouver, Canada
Duration: Jun 18 2023Jun 22 2023

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2023-June
ISSN (Print)1063-6919

Conference

Conference2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
Country/TerritoryCanada
CityVancouver
Period06/18/2306/22/23

Keywords

  • Image and video synthesis and generation

Fingerprint

Dive into the research topics of 'Shifted Diffusion for Text-to-image Generation'. Together they form a unique fingerprint.

Cite this