Any-to-Any
Diffusers
Safetensors
Diffusion Large Language Model
Multi-Modal Generation and Understanding
Instructions to use kr-cen/OmniGen2-MICo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kr-cen/OmniGen2-MICo with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("kr-cen/OmniGen2-MICo", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
metadata
license: apache-2.0
pipeline_tag: any-to-any
tags:
- Diffusion Large Language Model
- Multi-Modal Generation and Understanding
💡 OmniGen2-MICo • OmniGen2-Variant finetuned on Multi-Image Composition Dataset (MICo-150K)
🎨 Demo
Since OmniGen2 naturally supports multi-reference generation, here we give some comparisons against OmniGen2.
✍️ Citation
If you find this work useful, please cite:
@article{wei2025mico,
title={MICo-150K: A Comprehensive Dataset Advancing Multi-Image Composition},
author={Wei, Xinyu and Cen, Kangrui and Wei, Hongyang and Guo, Zhen and Li, Bairui and Wang, Zeqing and Zhang, Jinrui and Zhang, Lei},
journal={arXiv preprint arXiv:2512.07348},
year={2025}
}
License
OmniGen2-MICo is licensed under Apache License 2.0



