Work

Layered Diffusion Model for One-Shot High Resolution Text-to-Image Synthesis

Year: 2024

Type: preprint

Abstract: We present a one-shot text-to-image diffusion model that can generate high-resolution images from natural language descriptions. Our model employs a layered U-Net architecture that simultaneously synthesizes images at multiple resolution scales. We show that this method outperforms the baseline of synthesizing images only at the target resolution, while reducing the computational cost per step. We demonstrate that higher resolution synthesis can be achieved by layering convolutions at additional resolution scales, in contrast to other methods which require additional models for super-resolution synthesis.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2407.06079

Authors: Khwaja, Emaad, Rashwan, Abdullah, Chen, Ting, Wang, Oliver, Kothawade, Suraj, Li, Yeqing

Language: English

Topic: Generative Adversarial Networks and Image Synthesis

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4400488369

Cites:

Cited by:

Related to: 10