Patrick Esser
Co-first author of Taming Transformers (VQGAN) and co-author of Latent Diffusion Models
Patrick Esser is co-first author, with Robin Rombach, of "Taming Transformers for High-Resolution Image Synthesis" (CVPR 2021), whose code Esser, Rombach, and Björn Ommer released under an MIT-style license. Esser is a co-author of "High-Resolution Image Synthesis with Latent Diffusion Models" (CVPR 2022), on which Esser is listed with Runway ML, and the latent-diffusion code is MIT-licensed. Esser is also first author of "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis" (2024).1235467
Work
Taming Transformers (VQGAN) (external site: github.com)Open-source code
Co-first author with Robin Rombach, with Björn Ommer, of the CVPR 2021 paper; the CompVis repository's license names Esser, Rombach, and Ommer as copyright holders under MIT-style terms.123
Latent Diffusion Models (external site: github.com)Open-source code
Co-author, with Robin Rombach, Andreas Blattmann, Dominik Lorenz, and Björn Ommer, of "High-Resolution Image Synthesis with Latent Diffusion Models" (CVPR 2022), listed with Runway ML in the proceedings version; the CompVis/latent-diffusion repository is released under the MIT License.456
Scaling Rectified Flow Transformers (external site: arxiv.org)Published research
First author of "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis" (2024) with Sumith Kulal, Andreas Blattmann, Robin Rombach, and others.7
Other documented roles
Roles the sources document but that are not confirmed as current.
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.