We introduce LongCat-Image, a pioneering open-source and bilingual (Chinese-English) foundation model for image generation, designed to address core challenges in multilingual text rendering, photorealism, deployment efficiency, and developer accessibility prevalent in current leading models.

• 🌟 Exceptional Efficiency and Performance: With only 6B parameters, LongCat-Image surpasses numerous open-source models that are several times larger across multiple benchmarks, demonstrating the immense potential of efficient model design.
• 🌟 Superior Editing Performance: LongCat-Image-Edit model achieves state-of-the-art performance among open-source models, delivering leading instruction-following and image quality with superior visual consistency.
• 🌟 Powerful Chinese Text Rendering: LongCat-Image demonstrates superior accuracy and stability in rendering common Chinese characters compared to existing SOTA open-source models and achieves industry-leading coverage of the Chinese dictionary.
• 🌟 Remarkable Photorealism: Through an innovative data strategy and training framework, LongCat-Image achieves remarkable photorealism in generated images.
• 🌟 Comprehensive Open-Source Ecosystem: We provide a complete toolchain, from intermediate checkpoints to full training code, significantly lowering the barrier for further research and development.

• 🔥 [2025-12-16] LongCat-Image is now fully supported in Diffusers!
• 🔥 [2025-12-09] T2I-CoreBench results are out! LongCat-Image ranks 2nd among all open-source models in comprehensive performance, surpassed only by the 32B-parameter Flux2.dev.
• 🔥 [2025-12-08] We released our Technical Report on arXiv!
• 🔥 [2025-12-05] We released the weights for LongCat-Image, LongCat-Image-Dev, and LongCat-Image-Image on Hugging Face and ModelScope.

# create conda environment
conda create -n longcat-image python=3.10
conda activate longcat-image

# install requirements for model inference
pip install -r infer_requirements.txt
pip install git+https://github.com/huggingface/diffusers

import torch
from diffusers import LongCatImagePipeline

if __name__ == '__main__':
    device = torch.device('cuda')

    pipe = LongCatImagePipeline.from_pretrained("meituan-longcat/LongCat-Image", torch_dtype= torch.bfloat16 )
    # pipe.to(device, torch.bfloat16)  # Uncomment for high VRAM devices (Faster inference)
    pipe.enable_model_cpu_offload()  # Offload to CPU to save VRAM (Required ~17 GB); slower but prevents OOM

    prompt = '一个年轻的亚裔女性，身穿黄色针织衫，搭配白色项链。她的双手放在膝盖上，表情恬静。背景是一堵粗糙的砖墙，午后的阳光温暖地洒在她身上，营造出一种宁静而温馨的氛围。镜头采用中距离视角，突出她的神态和服饰的细节。光线柔和地打在她的脸上，强调她的五官和饰品的质感，增加画面的层次感与亲和力。整个画面构图简洁，砖墙的纹理与阳光的光影效果相得益彰，突显出人物的优雅与从容。'
    
    image = pipe(
        prompt,
        height=768,
        width=1344,
        guidance_scale=4.0,
        num_inference_steps=50,
        num_images_per_prompt=1,
        generator=torch.Generator("cpu").manual_seed(43),
        enable_cfg_renorm=True,
        enable_prompt_rewrite=True
    ).images[0]
    image.save('./t2i_example.png')

import torch
from PIL import Image
from diffusers import LongCatImageEditPipeline

if __name__ == '__main__':
    device = torch.device('cuda')

    pipe = LongCatImageEditPipeline.from_pretrained("meituan-longcat/LongCat-Image-Edit", torch_dtype= torch.bfloat16 )
    # pipe.to(device, torch.bfloat16)  # Uncomment for high VRAM devices (Faster inference)
    pipe.enable_model_cpu_offload()  # Offload to CPU to save VRAM (Required ~18 GB); slower but prevents OOM

    img = Image.open('assets/test.png').convert('RGB')
    prompt = '将猫变成狗'
    image = pipe(
        img,
        prompt,
        negative_prompt='',
        guidance_scale=4.5,
        num_inference_steps=50,
        num_images_per_prompt=1,
        generator=torch.Generator("cpu").manual_seed(43)
    ).images[0]

    image.save('./edit_example.png')

The quantitative evaluation results on public benchmarks demonstrate LongCat-Image's competitive performance:

cd LongCat-Image
# for training, install other requirements
pip install -r train_requirements.txt
python setup.py develop

We provide training code that enables advanced development of our LongCat‑Image‑Dev and model, including SFT, LoRA, DPO, and Image Editing training.

See TRAINING.md for detailed instructions.

Community works are welcome! Please PR or inform us in Issue to add your work.

• [LoRA Adapters] Fine-tuned models for specific styles and domains
• [ComfyUI Integration] Native support for ComfyUI workflow
• [Diffusers Pipeline] HuggingFace Diffusers integration
• ComfyUI Longcat Image - Custom node extension for ComfyUI workflow.

LongCat-Image is licensed under Apache 2.0. See the LICENSE file for the full license text.

This model has not been specifically designed or comprehensively evaluated for every possible downstream application.

Developers should take into account the known limitations of large language models, including performance variations across different languages, and carefully assess accuracy, safety, and fairness before deploying the model in sensitive or high-risk scenarios. It is the responsibility of developers and downstream users to understand and comply with all applicable laws and regulations relevant to their use case, including but not limited to data protection, privacy, and content safety requirements.

Nothing in this Model Card should be interpreted as altering or restricting the terms of the Apache License 2.0 under which the model is released.

We kindly encourage citation of our work if you find it useful.

@article{LongCat-Image,
      title={LongCat-Image Technical Report},
      author={Meituan LongCat Team and  Hanghang Ma and Haoxian Tan and Jiale Huang and Junqiang Wu and Jun-Yan He and Lishuai Gao and Songlin Xiao and Xiaoming Wei and Xiaoqi Ma and Xunliang Cai and Yayong Guan and Jie Hu},
	    journal={arXiv preprint arXiv:2512.07584},
      year={2025}
}

We would like to thank the contributors to the FLUX.1, Qwen2.5-VL, Diffusers and HuggingFace repositories, for their open research.

Please contact us at longcat-team@meituan.com or join our WeChat Group if you have any questions.