lucidrains/DALLE2-pytorch

Health v2 · maintenance only

Adoption not part of the score

11306 stars · 1070 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A PyTorch implementation of OpenAI's DALL-E 2 text-to-image synthesis model, focusing on the diffusion prior network that predicts image embeddings from CLIP text embeddings. It provides training scripts and model components for researchers replicating the architecture.

Use cases

• generate images from text descriptions
• train a diffusion prior for CLIP embeddings
• replicate DALL-E 2 architecture in PyTorch
• research text-to-image synthesis models
• build a CLIP-to-StyleGAN text-to-image pipeline
• experiment with diffusion-based image generation

When to choose

• you want to study or reproduce the DALL-E 2 architecture in PyTorch
• you need a diffusion prior network for CLIP-based image generation research
• you want a readable reference implementation of the paper

When to avoid

• you need state-of-the-art text-to-image generation - the author recommends Imagen instead
• you want a production-ready model with official OpenAI weights
• you need a simple plug-and-play image generator without training your own models

Facets

library · maturity maintenance

deep-learning machine-learning stable-diffusion image-processing artificial-intelligence deep-learning machine-learning image-processing python text-to-image dalle2 diffusion-models pytorch clip generative-ai research-implementation gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="lucidrains/DALLE2-pytorch")