OmniGen: Unified Image Generation
Paper • 2409.11340 • Published • 115
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Shitao/OmniGen-v0.5", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Github Repo: https://github.com/VectorSpaceLab/OmniGen
This is an early version of OmniGen, which we further fine-tuned to obtain OmniGen-v1. The test results in the first version of our paper are based on this model.
Citation
If you find this repository useful, please consider giving a star ⭐ and citation
@article{xiao2024omnigen,
title={Omnigen: Unified image generation},
author={Xiao, Shitao and Wang, Yueze and Zhou, Junjie and Yuan, Huaying and Xing, Xingrun and Yan, Ruiran and Wang, Shuting and Huang, Tiejun and Liu, Zheng},
journal={arXiv preprint arXiv:2409.11340},
year={2024}
}
- Downloads last month
- 10
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support