Official PyTorch implementation of ICCV 2023 Paper "DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders".

Xiaoyang Kang, Tao Yang, Wenqi Ouyang, Peiran Ren, Lingzhi Li, Xuansong Xie
DAMO Academy, Alibaba Group

🪄 DDColor can provide vivid and natural colorization for historical black and white old photos.

🎲 It can even colorize/recolor landscapes from anime games, transforming your animated scenery into a realistic real-life style! (Image source: Genshin Impact)

• [2024-01-28] Support inference via 🤗 Hugging Face! Thanks @Niels for the suggestion and example code and @Skwara for fixing bug.
• [2024-01-18] Add Replicate demo and API! Thanks @Chenxi.
• [2023-12-13] Release the DDColor-tiny pre-trained model!
• [2023-09-07] Add the Model Zoo and release three pretrained models!
• [2023-05-15] Code release for training and inference!
• [2023-05-05] The online demo is available!

Try our online demos at ModelScope and Replicate.

In short: DDColor uses multi-scale visual features to optimize learnable color tokens (i.e. color queries) and achieves state-of-the-art performance on automatic image colorization.

• Python >= 3.7
• PyTorch >= 1.7

conda create -n ddcolor python=3.9
conda activate ddcolor
pip install torch==2.2.0 torchvision==0.17.0 --index-url https://download.pytorch.org/whl/cu118

pip install -r requirements.txt

# For training, install the following additional dependencies and basicsr
pip install -r requirements.train.txt
python3 setup.py develop

1. Download the pretrained model:

from modelscope.hub.snapshot_download import snapshot_download

model_dir = snapshot_download('damo/cv_ddcolor_image-colorization', cache_dir='./modelscope')
print('model assets saved to %s' % model_dir)

2. Run inference with

python scripts/infer.py --model_path ./modelscope/damo/cv_ddcolor_image-colorization/pytorch_model.pt --input ./assets/test_images

or

sh scripts/inference.sh

Load the model via Hugging Face Hub:

from huggingface_hub import PyTorchModelHubMixin
from ddcolor import DDColor

class DDColorHF(DDColor, PyTorchModelHubMixin):
    def __init__(self, config=None, **kwargs):
        if isinstance(config, dict):
            kwargs = {**config, **kwargs}
        super().__init__(**kwargs)

ddcolor_paper_tiny = DDColorHF.from_pretrained("piddnad/ddcolor_paper_tiny")
ddcolor_paper      = DDColorHF.from_pretrained("piddnad/ddcolor_paper")
ddcolor_modelscope = DDColorHF.from_pretrained("piddnad/ddcolor_modelscope")
ddcolor_artistic   = DDColorHF.from_pretrained("piddnad/ddcolor_artistic")

Or directly perform model inference by running:

python scripts/infer.py --model_name ddcolor_modelscope --input ./assets/test_images
# model_name: [ddcolor_paper | ddcolor_modelscope | ddcolor_artistic | ddcolor_paper_tiny]

1. Install modelscope:

pip install modelscope

2. Run inference:

import cv2
from modelscope.outputs import OutputKeys
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

img_colorization = pipeline(Tasks.image_colorization, model='damo/cv_ddcolor_image-colorization')
result = img_colorization('https://modelscope.oss-cn-beijing.aliyuncs.com/test/images/audrey_hepburn.jpg')
cv2.imwrite('result.png', result[OutputKeys.OUTPUT_IMG])

This code will automatically download the ddcolor_modelscope model (see ModelZoo) and performs inference. The model file pytorch_model.pt can be found in the local path ~/.cache/modelscope/hub/damo.

Install the gradio and other required libraries:

pip install gradio gradio_imageslider

Then, you can run the demo with the following command:

python demo/gradio_app.py

We provide several different versions of pretrained models, please check out Model Zoo.

1. Dataset Preparation: Download the ImageNet dataset or create a custom dataset. Use this script to obtain the dataset list file:

python scripts/get_meta_file.py

2. Download the pretrained weights for ConvNeXt and InceptionV3 and place them in the pretrain folder.

3. Specify 'meta_info_file' and other options in options/train/train_ddcolor.yml.

4. Start training:

sh scripts/train.sh

Support for ONNX model exports is available.

1. Install dependencies:

pip install onnx==1.16.1 onnxruntime==1.19.2 onnxsim==0.4.36

2. Usage example:

python scripts/export_onnx.py --model_path pretrain/ddcolor_paper_tiny.pth --export_path weights/ddcolor-tiny.onnx

Demo of ONNX export using a ddcolor_paper_tiny model is available here.

If our work is helpful for your research, please consider citing:

@inproceedings{kang2023ddcolor,
  title={DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders},
  author={Kang, Xiaoyang and Yang, Tao and Ouyang, Wenqi and Ren, Peiran and Li, Lingzhi and Xie, Xuansong},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={328--338},
  year={2023}
}

We thank the authors of BasicSR for the awesome training pipeline.

Xintao Wang, Ke Yu, Kelvin C.K. Chan, Chao Dong and Chen Change Loy. BasicSR: Open Source Image and Video Restoration Toolbox. https://github.com/xinntao/BasicSR, 2020.

Some codes are adapted from ColorFormer, BigColor, ConvNeXt, Mask2Former, and DETR. Thanks for their excellent work!