Papers
arxiv:2301.07093

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

Published on Jan 17, 2023
Authors:
,
,
,
,
,
,
,

Abstract

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 that of existing supervised layout-to-image baselines by a large margin.

Community

Sign up or log in to comment

Models citing this paper 4

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2301.07093 in a dataset README.md to link it from this page.

Spaces citing this paper 11

Collections including this paper 26