# jina-ai/discoart

🪩 Create Disco Diffusion artworks in one line

Repository: https://github.com/jina-ai/discoart
Canonical: https://ross.abutalabs.com/products/discoart
Language: Python
License: NOASSERTION
License Family: other
Topics: creative-ai, disco-diffusion, cross-modal, dalle, generative-art, multimodal, diffusion, prompts, midjourney, imgen, discodiffusion, creative-art, clip-guided-diffusion, latent-diffusion, stable-diffusion
Last push: 2023-05-16T09:48:00+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1525, "days_push": 1205, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3826, forks 241 (observed 2026-08-28T04:08:22.569080+00:00)

## What it is
DiscoArt is a Python library that wraps Disco Diffusion (CLIP-guided diffusion) so generative artists and developers can create AI artworks with a one-line create() call. It adds result persistence, post-analysis, and optional gRPC/HTTP serving built on Jina and DocArray.

## Use cases
- generate images from text prompts with diffusion models
- run disco diffusion locally instead of a colab notebook
- serve a text-to-image model as an API
- explore diffusion parameters efficiently with saved initial states
- integrate generative art into a larger multimodal application

## When to choose
- you want Disco Diffusion's quality with a clean Python API and self-hosting
- you need to serve image generation over gRPC/HTTP with cloud-native scaling
- you work in IPython/Colab and want recoverable, persistent generation results

## When to avoid
- you want the newest latent diffusion or Stable Diffusion pipelines with active development
- you need a maintained project - the last release was 2023 and development has stalled
- you want a GUI-first image generation tool

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, image-processing, llm-inference, http-server, rpc
- domain: artificial-intelligence, image-processing, graphics, deep-learning
- platform: python, cli, self-hosted
- tags: diffusion-models, generative-art, clip-guided-diffusion, text-to-image, disco-diffusion, serving, docker

## Member repositories
- jina-ai/discoart (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:22.569080+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 2026-08-29T18:26:21.519954+00:00, confidence not recorded.
  - readme: https://github.com/jina-ai/discoart (fetched 2026-08-28T04:08:22.569080+00:00, sha c0ef7d569292)
  - registry_pypi: https://pypi.org/pypi/discoart/json (fetched 2026-08-29T09:21:06.969576+00:00, sha 5e04f4e37eab)
- Data as of 2026-08-30T08:39:29.467469+00:00.