OmniGen: Unified Image Generation paper code

OmniGen is a unified image generation model that you can use to perform various tasks, including but not limited to text-to-image generation, subject-driven generation, Identity-Preserving Generation, and image-conditioned generation. For multi-modal to image generation, you should pass a string as prompt, and a list of image paths as input_images. The placeholder in the prompt should be in the format of <img><|image_*|></img> (for the first image, the placeholder is <|image_1|>. for the second image, the the placeholder is <|image_2|>). For example, use an image of a woman to generate a new image: prompt = "A woman holds a bouquet of flowers and faces the camera. Thw woman is <img><|image_1|></img>." Tips:

  • For image editing task and controlnet task, we recommend setting the height and width of output image as the same as input image. For example, if you want to edit a 512x512 image, you should set the height and width of output image as 512x512. You also can set the use_input_image_size_as_output to automatically set the height and width of output image as the same as input image.
  • For out-of-memory or time cost, you can set offload_model=True or refer to ./docs/inference.md#requiremented-resources to select a appropriate setting.
  • If inference time is too long when inputting multiple images, please try to reduce the max_input_image_size. For more details please refer to ./docs/inference.md#requiremented-resources.
  • Oversaturated: If the image appears oversaturated, please reduce the guidance_scale.
  • Low-quality: More detailed prompts will lead to better results.
  • Animate Style: If the generated images are in animate style, you can try to add photo to the prompt`.
  • Edit generated image. If you generate an image by omnigen and then want to edit it, you cannot use the same seed to edit this image. For example, use seed=0 to generate image, and should use seed=1 to edit this image.
  • For image editing tasks, we recommend placing the image before the editing instruction. For example, use <img><|image_1|></img> remove suit, rather than remove suit <img><|image_1|></img>.

HF Spaces often encounter errors due to quota limitations, so recommend to run it locally.
128 2048
128 2048
1 5
1 2
1 100
0 2147483647
128 2048

Whether to use separate inference process for different guidance. This will reduce the memory cost.

Offload model to CPU, which will significantly reduce the memory cost but slow down the generation speed. You can cancel separate_cfg_infer and set offload_model=True. If both separate_cfg_infer and offload_model are True, further reduce the memory, but slowest generation

Automatically adjust the output image size to be same as input image size. For editing and controlnet task, it can make sure the output image has the same size as input image leading to better performance
Examples
Enter your prompt, use <img><|image_i|></img> to represent i-th input image <img><|image_1|></img> <img><|image_2|></img> <img><|image_3|></img> Height Width Guidance Scale img_guidance_scale Seed max_input_image_size Randomize seed use_input_image_size_as_output
Pages:

Citation
If you find this repository useful, please consider giving a star ⭐ and a 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}
}

Contact
If you have any questions, please feel free to open an issue or directly reach us out via email.