CVApr 18, 2022

VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance

arXiv:2204.08583v2466 citationsh-index: 32Has Code
AI Analysis

It enables flexible image creation and editing for users without expensive specialized models, though it builds on existing components.

The paper tackles open-domain image generation and editing from text prompts by using CLIP to guide VQGAN without training, achieving higher visual quality than prior methods like DALL-E and GLIDE.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes