🌟 July 16, 2025: We've open-sourced the updated image editing model HiDream-E1.1.
📝 May 28, 2025: We've released our technical report HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer. Please use the Bibtex below to cite the paper.
🚀 April 28, 2025: We've open-sourced the image editing model HiDream-E1.

Quick Start

Please make sure you have installed Flash Attention and latest Diffusers. We recommend CUDA versions 12.4 for the manual installation.

pip install -r requirements.txt
pip install -U flash-attn --no-build-isolation
pip install -U git+https://github.com/huggingface/diffusers.git

Then you can run the inference scripts to generate images:

python ./inference_e1_1.py

[!NOTE] The inference script will try to automatically download meta-llama/Llama-3.1-8B-Instruct model files. You need to agree to the license of the Llama model on your HuggingFace account and login using huggingface-cli login in order to use the automatic downloader.

Gradio Demo

We also provide a Gradio demo for interactive image editing. You can run the demo with:

python gradio_demo_1_1.py

Evaluation Metrics

Evaluation results on EmuEdit and ReasonEdit Benchmarks. Higher is better.

Model	EmuEdit Global	EmuEdit Add	EmuEdit Text	EmuEdit BG	EmuEdit Color	EmuEdit Style	EmuEdit Remove	EmuEdit Local	EmuEdit Average	ReasonEdit
OmniGen	1.37	2.09	2.31	0.66	4.26	2.36	4.73	2.10	2.67	7.36
MagicBrush	4.06	3.54	0.55	3.26	3.83	2.07	2.70	3.28	2.81	1.75
UltraEdit	5.31	5.19	1.50	4.33	4.50	5.71	2.63	4.58	4.07	2.89
Gemini-2.0-Flash	4.87	7.71	6.30	5.10	7.30	3.33	5.94	6.29	5.99	6.95
HiDream-E1	5.32	6.98	6.45	5.01	7.57	6.49	5.99	6.35	6.40	7.54
HiDream-E1.1	7.47	7.97	7.49	7.32	7.97	7.84	7.51	6.80	7.57	7.70

License Agreement

The Transformer models in this repository are licensed under the MIT License. The VAE is from FLUX.1 [schnell], and the text encoders from google/t5-v1_1-xxl and meta-llama/Meta-Llama-3.1-8B-Instruct. Please follow the license terms specified for these components. You own all content you create with this model. You can use your generated content freely, but you must comply with this license agreement. You are responsible for how you use the models. Do not create illegal content, harmful material, personal information that could harm others, false information, or content targeting vulnerable groups.

Acknowledgements

The VAE component is from FLUX.1 [schnell], licensed under Apache 2.0.
The text encoders are from google/t5-v1_1-xxl (licensed under Apache 2.0) and meta-llama/Meta-Llama-3.1-8B-Instruct (licensed under the Llama 3.1 Community License Agreement).

Citation

bibtex

@article{hidreami1technicalreport,
  title={HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer},
  author={Cai, Qi and Chen, Jingwen and Chen, Yang and Li, Yehao and Long, Fuchen and Pan, Yingwei and Qiu, Zhaofan and Zhang, Yiheng and Gao, Fengbin and Xu, Peihan and others},
  journal={arXiv preprint arXiv:2505.22705},
  year={2025}
}

RedbeardNZ/HiDream-E1-1

Project Updates