Is One GPU Enough? Pushing Image Generation at Higher-Resolutions with Foundation Models

TL;DR

Pixelsmith is a novel framework enabling high-resolution, gigapixel image generation from text prompts using a single GPU, by cascading diffusion models and a tunable guidance mechanism to enhance quality and efficiency.

Contribution

It introduces a scalable, zero-shot text-to-image generation method that can produce gigapixel images with minimal hardware, a significant advancement over existing techniques.

Findings

Achieves 1000x scaling of diffusion model outputs.

Produces higher quality and more diverse images.

Reduces sampling time and artifacts.

Abstract

In this work, we introduce Pixelsmith, a zero-shot text-to-image generative framework to sample images at higher resolutions with a single GPU. We are the first to show that it is possible to scale the output of a pre-trained diffusion model by a factor of 1000, opening the road for gigapixel image generation at no additional cost. Our cascading method uses the image generated at the lowest resolution as a baseline to sample at higher resolutions. For the guidance, we introduce the Slider, a tunable mechanism that fuses the overall structure contained in the first-generated image with enhanced fine details. At each inference step, we denoise patches rather than the entire latent space, minimizing memory demands such that a single GPU can handle the process, regardless of the image's resolution. Our experimental results show that Pixelsmith not only achieves higher quality and diversity compared to existing techniques, but also reduces sampling time and artifacts. The code for our work is available at https://github.com/Thanos-DB/Pixelsmith.