GLIGEN: Open-Set Grounded Text-to-Image Generation

Large-scale text-to-image diffusion models have made amazing advances. However, the status quo is to use text input alone, which can impede controllability. In this work, we propose GLIGEN, Grounded-Language-to-Image Generation, a novel approach that builds upon and extends the functionality of exis...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 22511 - 22521
Main Authors: Li, Yuheng, Liu, Haotian, Wu, Qingyang, Mu, Fangzhou, Yang, Jianwei, Gao, Jianfeng, Li, Chunyuan, Lee, Yong Jae
Format: Conference Proceeding
Language:English
Published: IEEE 01.06.2023
Subjects:
Computational modeling
Computer vision
Graphics
Grounding
Image and video synthesis and generation
Image edge detection
Logic gates
Training data
ISSN:1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Large-scale text-to-image diffusion models have made amazing advances. However, the status quo is to use text input alone, which can impede controllability. In this work, we propose GLIGEN, Grounded-Language-to-Image Generation, a novel approach that builds upon and extends the functionality of existing pre-trained text-to-image diffusion models by enabling them to also be conditioned on grounding inputs. To preserve the vast concept knowledge of the pre-trained model, we freeze all of its weights and inject the grounding information into new trainable layers via a gated mechanism. Our model achieves open-world grounded text2img generation with caption and bounding box condition inputs, and the grounding ability generalizes well to novel spatial configurations and concepts. GLIGEN's zero-shot performance on COCO and LVIS outperforms existing supervised layout-to-image baselines by a large margin.
ISSN:1063-6919
DOI:10.1109/CVPR52729.2023.02156