# openai/DALL-E

PyTorch package for the discrete VAE used for DALL·E.

Repository: https://github.com/openai/DALL-E
Canonical: https://ross.abutalabs.com/products/dall-e
Language: Python
License: NOASSERTION
License Family: other
Archived: true
Last push: 2024-01-31T15:42:28+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2017, "days_push": 945, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 10834, forks 1860 (observed 2026-08-28T04:10:44.463730+00:00)

## What it is
The official PyTorch package for the discrete VAE (dVAE) component of OpenAI's DALL·E model. It does not include the transformer that generates images from text, only the VAE used for image tokenization.

## Use cases
- run the DALL-E discrete VAE in PyTorch
- encode images into discrete tokens for generative models
- reproduce the DALL-E paper's VAE component
- experiment with discrete variational autoencoders
- preprocess images for text-to-image transformer research

## When to choose
- you need the exact official DALL-E dVAE implementation for research or reproducibility
- you want a PyTorch discrete VAE for image tokenization experiments

## When to avoid
- you want full text-to-image generation - the transformer is not included
- you need a maintained, actively updated library
- you want a modern image generation model like Stable Diffusion

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing
- domain: deep-learning, machine-learning, image-processing, artificial-intelligence
- platform: python
- tags: pytorch, dalle, discrete-vae, image-generation, text-to-image, openai, gpu

## Member repositories
- openai/DALL-E (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:44.463730+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:17:30.758059+00:00, confidence not recorded.
  - readme: https://github.com/openai/DALL-E (fetched 2026-08-28T04:10:44.463730+00:00, sha e80836b621fe)
  - registry_pypi: https://pypi.org/pypi/dall-e/json (fetched 2026-08-29T08:16:27.604061+00:00, sha 6641daa168df)
- Data as of 2026-08-30T08:39:29.467469+00:00.