English

GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models

Computer Vision and Pattern Recognition 2022-03-09 v3 Graphics Machine Learning

Abstract

Diffusion models have recently been shown to generate high-quality synthetic images, especially when paired with a guidance technique to trade off diversity for fidelity. We explore diffusion models for the problem of text-conditional image synthesis and compare two different guidance strategies: CLIP guidance and classifier-free guidance. We find that the latter is preferred by human evaluators for both photorealism and caption similarity, and often produces photorealistic samples. Samples from a 3.5 billion parameter text-conditional diffusion model using classifier-free guidance are favored by human evaluators to those from DALL-E, even when the latter uses expensive CLIP reranking. Additionally, we find that our models can be fine-tuned to perform image inpainting, enabling powerful text-driven image editing. We train a smaller model on a filtered dataset and release the code and weights at https://github.com/openai/glide-text2im.

Keywords

Cite

@article{arxiv.2112.10741,
  title  = {GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models},
  author = {Alex Nichol and Prafulla Dhariwal and Aditya Ramesh and Pranav Shyam and Pamela Mishkin and Bob McGrew and Ilya Sutskever and Mark Chen},
  journal= {arXiv preprint arXiv:2112.10741},
  year   = {2022}
}

Comments

20 pages, 18 figures

R2 v1 2026-06-24T08:25:03.627Z