Joe Penna — accepted AI-conference papers

2024

SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas Müller +2

ICLR 2024spotlight

We present Stable Diffusion XL (SDXL), a latent diffusion model for text-to-image synthesis. Compared to previous versions of Stable Diffusion, SDXL leverages a three times larger UNet backbone, achieved by significantly increasing the number of attention blocks and including a second text encoder.…

Cited by 2203 Source ↗PDF ↗code ↗Scholar ↗

2023

Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation

Yuval Kirstain, Adam Polyak, Uriel Singer, Shahbuland Matiana, Joe Penna, Omer Levy

NeurIPS 2023poster

The ability to collect a large dataset of human preferences from text-to-image users is usually limited to companies, making such datasets inaccessible to the public. To address this issue, we create a web app that enables text-to-image users to generate images and specify their preferences. Using t…

Cited by 355 Source ↗PDF ↗code ↗Scholar ↗