Generating and editing images from open domain text prompts is a challenging task that heretofore has required expensive and specially trained models. We demonstrate a novel methodology for both tasks which is capable of producing images of high visual quality from text prompts of significant semantic complexity without any training by using a multimodal encoder to guide image generations. We demonstrate on a variety of tasks how using CLIP [37] to guide VQGAN [11] produces higher visual quality outputs than prior, less flexible approaches like DALL-E [38], GLIDE [33] and Open-Edit [24], despite not being trained for the tasks presented. Our code is available in a public repository.
@article{arxiv.2204.08583,
title = {VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance},
author = {Katherine Crowson and Stella Biderman and Daniel Kornis and Dashiell Stander and Eric Hallahan and Louis Castricato and Edward Raff},
journal= {arXiv preprint arXiv:2204.08583},
year = {2022}
}
Comments
Accepted for publication at ECCV 2022 Code available at https://github.com/EleutherAI/vqgan-clip/tree/main/notebooks