# kuprel/min-dalle

min(DALL·E) is a fast, minimal port of DALL·E Mini to PyTorch

Repository: https://github.com/kuprel/min-dalle
Canonical: https://ross.abutalabs.com/products/min-dalle
Language: Python
License: MIT
License Family: permissive
Topics: artificial-intelligence, deep-learning, pytorch, text-to-image
Last push: 2025-04-28T01:38:43+00:00

## Health v2 (maintenance only)
Score: 31/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 18, release rhythm 8, longevity 100
- inputs: {"age_days": 1528, "days_push": 493, "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 3494, forks 247 (observed 2026-08-28T04:08:07.329723+00:00)

## What it is
min(DALL·E) is a fast, minimal PyTorch port of DALL·E Mini/Mega stripped down for text-to-image inference, with only numpy, requests, pillow, and torch as dependencies. It generates image grids from text prompts on CUDA or CPU GPUs.

## Use cases
- generate images from text prompts in python
- run DALL·E Mini inference locally on a GPU
- text-to-image generation with pytorch
- create a 3x3 grid of images from a caption
- lightweight text-to-image model without heavy dependencies
- reproducible image generation with a fixed seed

## When to choose
- you want minimal-dependency DALL·E Mini/Mega inference in PyTorch
- you need fast text-to-image generation on a single GPU or Colab
- you want programmatic control over sampling parameters like temperature, top_k, and supercondition_factor

## When to avoid
- you need state-of-the-art image quality from modern diffusion models
- you need training or fine-tuning rather than inference
- you need a hosted API rather than running models locally

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

## Member repositories
- kuprel/min-dalle (main) score 31

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:07.329723+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 2026-08-29T18:35:54.923110+00:00, confidence not recorded.
  - readme: https://github.com/kuprel/min-dalle (fetched 2026-08-28T04:08:07.329723+00:00, sha 8be8bbddb190)
  - registry_pypi: https://pypi.org/pypi/min-dalle/json (fetched 2026-08-29T09:29:59.679958+00:00, sha 6fb7924eeef9)
- Data as of 2026-08-30T08:39:29.467469+00:00.