OmniGen: Unified Image Generation
By Shitao Xiao, Yueze Wang, Junjie Zhou, Huaying Yuan, Xingrun Xing, Ruiran Yan, Shuting Wang, Tiejun Huang, Zheng Liu. Computer Vision and Pattern Recognition, 2024
394 citations recorded by the source corpus.
The emergence of Large Language Models (LLMs) has unified language generation tasks and revolutionized human-machine interaction. However, in the realm of image generation, a unified model capable of handling various tasks within a single framework remains largely unexplored. In this work, we introduce OmniGen, a new diffusion model for unified image generation. OmniGen is characterized by the following features: 1) Unification: OmniGen not only demonstrates text-to-image generation capabilities but also inherently supports various downstream tasks, such as image editing, subject-driven generation, and visual-conditional generation. 2) Simplicity: The architecture of OmniGen is highly simplified, eliminating the need for additional plugins. Moreover, compared to existing diffusion models, it is more user-friendly and can complete complex tasks end-to-end through instructions without the need for extra intermediate steps, greatly simplifying the image generation workflow. 3) Knowledge Transfer: Benefit from learning in a unified format, OmniGen effectively transfers knowledge across different tasks, manages unseen tasks and domains, and exhibits novel capabilities. We also explore the model’s reasoning capabilities and potential applications of the chain-of-thought mechanism. This work represents the first attempt at a general-purpose image generation model, and we will release our resources at https://github.com/VectorSpaceLab/OmniGen to foster future advancements.
Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/99c50f99c86d528e1a545deb9d2cae3bad13b8b8
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Ziang Song
- Xiao-Ping Nie
- Chenhui Gou
- Shi Guang
- Chaorui Deng
- Kunchang Li
- Haoqi Fan
- Deyao Zhu
Citations in the corpus
- FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space (2025, neutral): “Subsequent instruction-driven editors such as Emu Edit [51], OmniGen [56], HiDream-E1[15] and ICEdit [62] – extend these ideas to refined datasets and model architectures.”
- VACE: All-in-One Video Creation and Editing (2025, neutral): “…deploying multiple models, researchers have begun to focus on constructing unified model architectures [12, 63] ( e.g ., ACE [23, 41] and Omni-Gen [71]), aiming to integrate different tasks into a single image model, facilitating the creation of various application workflows while maintaining…”
- Step1X-Edit: A Practical Framework for General Image Editing (2025, neutral): “Based on the GEdit-Bench , we evaluated a diverse range of image editing algorithms, covering state-of-the-art open-source solutions such as Instruct-Pix2Pix [8], MagicBrush [66], AnyEdit [64], OmniGen [61], as well as proprietary algorithms like GPT-4.”
- Emerging Properties in Unified Multimodal Pretraining (2025, positive): “We additionally include open-source image editing datasets as structured interleaved data [3, 22, 32, 80, 88, 101], which teach fine-grained editing behaviors and enhance the model’s ability for precise multimodal reasoning and step-by-step generation.”