[2605.11061] HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer
[Submitted on 11 May 2026]
Title:HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer
View a PDF of the paper titled HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer, by Qi Cai and Jingwen Chen and Chengmin Gao and Zijian Gong and Yehao Li and Yingwei Pan and Yi Peng and Zhaofan Qiu and Kai Yu and Yiheng Zhang and Hao Ai and Siying Bai and Yang Chen and Zhihui Chen and Fengbin Gao and Ying Guo and Dong Li and Zhen Shen and Leilei Shi and Jing Wang and Siyu Wang and Yimeng Wang and Rui Zheng and Ting Yao and Tao Mei
View PDF HTML (experimental)
Abstract:The evolution of visual generative models has long been constrained by fragmented architectures relying on disjoint text encoders and external VAEs. In this report, we present HiDream-O1-Image, a natively unified generative foundation model via pixel-space Diffusion Transformer, that pioneers a paradigm shift from modular architectures to an end-to-end in-context visual generation engine. By mapping raw image pixels, text tokens, and task-specific conditions into a single shared token space, HiDream-O1-Image achieves a structural unification of multimodal inputs within an Unified Transformer (UiT) architecture. This native encoding paradigm eliminates the need for separate VAEs or disjoint pre-trained text encoders, allowing the model to treat diverse generation and editing tasks as a consistent in-context reasoning process. Extensive experiments show that HiDream-O1-Image excels across various generation tasks, including text-to-image generation, instruction-based editing, and subject-driven personalization. Notably, with only 8B parameters, HiDream-O1-Image (8B) achieves performance parity with or even surpasses established state-of-the-art models with significantly larger parameters (e.g., 27B Qwen-Image). Crucially, to validate the immense scalability of this paradigm, we successfully scale the architecture up to over 200B parameters. Experimental results demonstrate that this massive-scale version HiDream-O1-Image-Pro (200B+) unlocks unprecedented generative capabilities and superior performance, establishing new state-of-the-art benchmarks. Ultimately, HiDream-O1-Image highlights the immense potential of natively unified architectures and charts a highly scalable path toward next-generation multimodal AI.
Comments: Source codes and models are available at Github: this https URL and Huggingface: this https URL
Subjects:
Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)
Cite as: arXiv:2605.11061 [cs.CV]
(or arXiv:2605.11061v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2605.11061
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Ting Yao [view email] [v1] Mon, 11 May 2026 17:59:09 UTC (9,051 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer, by Qi Cai and Jingwen Chen and Chengmin Gao and Zijian Gong and Yehao Li and Yingwei Pan and Yi Peng and Zhaofan Qiu and Kai Yu and Yiheng Zhang and Hao Ai and Siying Bai and Yang Chen and Zhihui Chen and Fengbin Gao and Ying Guo and Dong Li and Zhen Shen and Leilei Shi and Jing Wang and Siyu Wang and Yimeng Wang and Rui Zheng and Ting Yao and Tao Mei
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CV
new | recent | 2026-05
Change to browse by:
cs cs.MM
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)