# jd-opensource/JoyAI-Image

JoyAI-Image is the unified multimodal foundation model for image understanding, text-to-image generation, and instruction-guided image editing.

Repository: https://github.com/jd-opensource/JoyAI-Image
Canonical: https://ross.abutalabs.com/products/joyai-image
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-08-05T02:56:40+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 96, release rhythm 35, longevity 11
- inputs: {"age_days": 155, "days_push": 28, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2148, forks 162 (observed 2026-08-28T04:06:18.919159+00:00)

## What it is
JoyAI-Image is a unified multimodal foundation model for image understanding, text-to-image generation, and instruction-guided image editing, with an emphasis on spatial intelligence. It ships pretrained checkpoints for Diffusers and ComfyUI, demo spaces, and an associated OpenSpatial-3M training dataset.

## Use cases
- generate images from text prompts
- edit images with natural language instructions
- run image editing workflows in ComfyUI
- integrate image generation into a diffusers pipeline
- understand image content with a multimodal model
- train or fine-tune models on spatially-aware image data

## When to choose
- you need a single unified model for image understanding, generation, and editing
- you want instruction-based image editing with strong spatial reasoning
- you use Diffusers or ComfyUI and want native integration
- you need an Apache-2.0 licensed image editing model

## When to avoid
- you only need lightweight image processing without deep learning
- you have no GPU or limited compute resources
- you need video editing rather than image editing
- you require a fully managed hosted API rather than self-hosted weights

## Facets
- artifact type: library
- maturity: active
- function: image-processing, machine-learning, deep-learning, llm-inference
- domain: artificial-intelligence, computer-vision, image-processing, large-language-models, deep-learning
- platform: python
- tags: text-to-image, image-editing, multimodal, diffusers, comfyui, foundation-model, spatial-intelligence, gpu, docker

## Member repositories
- jd-opensource/JoyAI-Image (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:18.919159+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 2026-08-30T02:51:06.930898+00:00, confidence not recorded.
  - readme: https://github.com/jd-opensource/JoyAI-Image (fetched 2026-08-28T04:06:18.919159+00:00, sha 7bd78555d02f)
- Data as of 2026-08-30T08:39:29.467469+00:00.