UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs

TL;DR

UFOGen is a novel hybrid diffusion-GAN model that enables ultra-fast, one-step text-to-image generation, significantly reducing inference time while maintaining high image quality and versatility in applications.

Contribution

UFOGen introduces a diffusion-GAN hybrid framework with a new objective, achieving one-step high-quality text-to-image synthesis using pre-trained diffusion models.

Findings

Achieves high-quality images in a single inference step

Outperforms traditional diffusion models in speed

Versatile in downstream tasks

Abstract

Text-to-image diffusion models have demonstrated remarkable capabilities in transforming textual prompts into coherent images, yet the computational cost of their inference remains a persistent challenge. To address this issue, we present UFOGen, a novel generative model designed for ultra-fast, one-step text-to-image synthesis. In contrast to conventional approaches that focus on improving samplers or employing distillation techniques for diffusion models, UFOGen adopts a hybrid methodology, integrating diffusion models with a GAN objective. Leveraging a newly introduced diffusion-GAN objective and initialization with pre-trained diffusion models, UFOGen excels in efficiently generating high-quality images conditioned on textual descriptions in a single step. Beyond traditional text-to-image generation, UFOGen showcases versatility in applications. Notably, UFOGen stands among the pioneering models enabling one-step text-to-image generation and diverse downstream tasks, presenting a significant advancement in the landscape of efficient generative models.