lucidrains/imagen-pytorch

Health v2 · maintenance only

Adoption not part of the score

8424 stars · 795 forks observed · 2026-08-28

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

A PyTorch implementation of Imagen, Google's text-to-image neural network based on cascading DDPMs conditioned on T5 text embeddings. It provides the model architecture and training/sampling tooling for text-to-image synthesis research.

Use cases

• generate images from text prompts in pytorch
• train a cascading diffusion model on my own image dataset
• replicate Google's Imagen text-to-image model
• experiment with classifier-free guidance in diffusion models
• build a text-to-image research project without CLIP

When to choose

• you want an open PyTorch codebase of Imagen for research or experimentation
• you need a cascading DDPM implementation with T5 text conditioning
• you want to train or fine-tune a text-to-image diffusion model yourself

When to avoid

• you need a production-ready text-to-image service with pretrained checkpoints at full quality
• you have no GPU or ML training experience and just want to generate images easily
• you need a stable inference library with long-term support guarantees

Facets

library · maturity active

deep-learning machine-learning image-processing artificial-intelligence deep-learning machine-learning image-processing python text-to-image diffusion-models pytorch imagen generative-ai ddpm t5-encoder gpu

Member repositories

For agents

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