# VectorSpaceLab/OmniGen

OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

Repository: https://github.com/VectorSpaceLab/OmniGen
Canonical: https://ross.abutalabs.com/products/omnigen
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: diffusion, image, image-generation, multi-modal, image-edit, multi-task
Last push: 2025-12-04T15:59:12+00:00

## Health v2 (maintenance only)
Score: 47/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 55, release rhythm 35, longevity 51
- inputs: {"age_days": 716, "days_push": 272, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4340, forks 362 (observed 2026-08-28T04:08:46.091093+00:00)

## What it is
OmniGen is a unified diffusion-based image generation model that produces and edits images from multi-modal prompts without auxiliary modules like ControlNet or IP-Adapter. The repository provides inference and fine-tuning code, with the model also available via Hugging Face Diffusers and Replicate.

## Use cases
- generate images from text prompts
- edit images with natural language instructions
- generate images conditioned on reference images
- do subject-driven generation without extra adapters
- fine-tune an image generation model on custom data
- run unified image generation in Diffusers

## When to choose
- you want one model for generation and editing without loading ControlNet or IP-Adapter
- you need multi-modal (text plus image) prompting for image synthesis
- you want a MIT-licensed model you can fine-tune yourself

## When to avoid
- you need the absolute highest fidelity from specialized state-of-the-art models like SDXL or Flux
- you have no GPU and need fast cheap inference
- you only need a hosted API with no local setup

## Facets
- artifact type: library
- maturity: active
- function: image-processing, machine-learning, deep-learning
- domain: image-processing, artificial-intelligence, computer-vision
- platform: python, cross-platform
- tags: diffusion-model, text-to-image, image-editing, multi-modal, unified-model, diffusers, gpu

## Member repositories
- VectorSpaceLab/OmniGen (main) score 47

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:46.091093+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 2026-08-29T18:21:36.943034+00:00, confidence not recorded.
  - readme: https://github.com/VectorSpaceLab/OmniGen (fetched 2026-08-28T04:08:46.091093+00:00, sha ebb0835c829d)
  - registry_pypi: https://pypi.org/pypi/omnigen/json (fetched 2026-08-29T09:10:41.045863+00:00, sha f90a5c0d6e7c)
- Data as of 2026-08-30T08:39:29.467469+00:00.