lucidrains/DALLE-pytorch

Health v2 · maintenance only

Adoption not part of the score

5627 stars · 642 forks observed · 2026-08-28

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

A PyTorch implementation/replication of OpenAI's DALL-E, a text-to-image transformer, including a discrete VAE and optional CLIP for ranking generations. It is a research library for training and experimenting with DALL-E-style generative models.

Use cases

• train a DALL-E text-to-image model on my own image-caption dataset
• generate images from text prompts in pytorch
• replicate the DALL-E paper for research
• experiment with transformer-based image generation
• train a small text-to-image model on a custom dataset
• use CLIP to rank generated images

When to choose

• you want an open-source, hackable PyTorch implementation of DALL-E for research or experimentation
• you want to train a text-to-image transformer on your own dataset
• you want to study or modify the DALL-E architecture

When to avoid

• you want state-of-the-art text-to-image generation out of the box - newer models like Stable Diffusion are far better
• you need a production-ready image generation service with pretrained large-scale checkpoints
• you don't have GPU resources for training

Facets

library · maturity maintenance

deep-learning machine-learning transformers llm-training artificial-intelligence deep-learning image-processing python text-to-image dall-e pytorch generative-models multi-modal clip vq-vae natural-language-processing gpu

Member repositories

For agents

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