# borisdayma/dalle-mini

DALL·E Mini - Generate images from a text prompt

Repository: https://github.com/borisdayma/dalle-mini
Canonical: https://ross.abutalabs.com/products/dalle-mini
Homepage: https://www.craiyon.com
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2023-11-09T09:20:46+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1887, "days_push": 1028, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 14740, forks 1217 (observed 2026-08-28T04:11:07.582789+00:00)

## What it is
DALL·E Mini is a Python library and model that generates images from a text prompt, available via pip and hosted on Hugging Face Model Hub. It powers the Craiyon web app and includes training and inference pipelines built on JAX/FLAX.

## Use cases
- generate images from a text prompt
- run text-to-image generation in Python
- train a small DALL-E style model
- experiment with an inference pipeline notebook
- self-host a text-to-image model

## When to choose
- you want a lightweight open text-to-image model you can run or fine-tune yourself
- you want to study or extend a DALL-E style architecture in JAX/FLAX

## When to avoid
- you need state-of-the-art image quality from modern diffusion models
- you want a maintained turnkey product rather than a research codebase

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, llm-inference
- domain: artificial-intelligence, machine-learning, image-processing, deep-learning
- platform: python, cloud
- tags: text-to-image, image-generation, dalle, jax, huggingface, generative-ai, gpu

## Member repositories
- borisdayma/dalle-mini (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:07.582789+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 2026-08-29T17:07:13.058015+00:00, confidence not recorded.
  - readme: https://github.com/borisdayma/dalle-mini (fetched 2026-08-28T04:11:07.582789+00:00, sha 421b3e9f1ffe)
  - registry_pypi: https://pypi.org/pypi/dalle-mini/json (fetched 2026-08-29T08:05:17.763698+00:00, sha 367dfe0c9d5d)
- Data as of 2026-08-30T08:39:29.467469+00:00.