GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
This work advances photorealistic image generation and editing from text, enabling powerful applications in creative and visual domains.
The paper tackles text-conditional image synthesis by comparing CLIP guidance and classifier-free guidance in diffusion models, finding that classifier-free guidance produces photorealistic images preferred by human evaluators over DALL-E, with a 3.5 billion parameter model achieving this result.
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.