mmediting

• Modular design

  We decompose the editing framework into different components and one can easily construct a customized editor framework by combining different modules.

• Support of multiple tasks in editing

  The toolbox directly supports popular and contemporary inpainting, matting, super-resolution and generation tasks.

• State of the art

  The toolbox provides state-of-the-art methods in inpainting/matting/super-resolution/generation.

Note that MMSR has been merged into this repo, as a part of MMEditing.
With elaborate designs of the new framework and careful implementations,
hope MMEditing could provide better experience.

What’s New

MMEditing maintains both master and 1.x branches. See more details in Branch Maintenance Plan.

💎 Stable version

0.16.1 was released in 24/02/2023:

• Support FID and KID metrics.
• Support groups parameter in ResidualBlockNoBN.
• Fix RealESRGAN test dataset.
• Fix dynamic exportable ONNX of pixel-unshuffle.

Please refer to changelog.md for details and release history.

🌟 Preview of 1.x version

A brand new version of MMEditing v1.0.0rc6 was released in 24/02/2023:

• Support all the tasks, models, metrics, and losses in MMGeneration 😍。
• Unifies interfaces of all components based on MMEngine.
• Refactored and more flexible architecture.
• Support well-known text-to-image method Stable Diffusion!
• Support a new text-to-image algorithm GLIDE!
• Support Text2Image Task! Disco-Diffusion!
• Support 3D-aware Generation Task! EG3D!
• Support an efficient image restoration algorithm Restormer!
• Support swin based image restoration algorithm SwinIR!
• Support Image Colorization.
• Projects is opened for the community to add projects to MMEditing.
• Support High-level apis and inferencer.
• Support Gradio gui of Inpainting inference.
• Support patch-based and slider-based image and video comparison viewer.

Find more new features in 1.x branch. Issues and PRs are welcome!

Installation

MMEditing depends on PyTorch and MMCV.
Below are quick steps for installation.

Step 1.
Install PyTorch following official instructions.

Step 2.
Install MMCV with MIM.

pip3 install openmim
mim install mmcv-full

Step 3.
Install MMEditing from source.

git clone https://github.com/open-mmlab/mmediting.git
cd mmediting
pip3 install -e .

Please refer to install.md for more detailed instruction.

Getting Started

Please see getting_started.md and demo.md for the basic usage of MMEditing.

Model Zoo

Supported algorithms:

Please refer to model_zoo for more details.

Contributing

We appreciate all contributions to improve MMEditing. Please refer to our contributing guidelines.

Acknowledgement

MMEditing is an open source project that is contributed by researchers and engineers from various colleges and companies. We appreciate all the contributors who implement their methods or add new features, as well as users who give valuable feedbacks. We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to reimplement existing methods and develop their own new methods.

Branch Maintenance Plan

MMEditing currently has two branches, the master and 1.x branches, which go through the following three phases.

Citation

If MMEditing is helpful to your research, please cite it as below.

@misc{mmediting2022,
    title = {{MMEditing}: {OpenMMLab} Image and Video Editing Toolbox},
    author = {{MMEditing Contributors}},
    howpublished = {\url{https://github.com/open-mmlab/mmediting}},
    year = {2022}
}

License

This project is released under the Apache 2.0 license.

Projects in OpenMMLab

• MMEngine: OpenMMLab foundational library for training deep learning models.
• MMCV: OpenMMLab foundational library for computer vision.
• MMEval: A unified evaluation library for multiple machine learning libraries.
• MIM: MIM installs OpenMMLab packages.
• MMClassification: OpenMMLab image classification toolbox and benchmark.
• MMDetection: OpenMMLab detection toolbox and benchmark.
• MMDetection3D: OpenMMLab’s next-generation platform for general 3D object detection.
• MMRotate: OpenMMLab rotated object detection toolbox and benchmark.
• MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark.
• MMOCR: OpenMMLab text detection, recognition, and understanding toolbox.
• MMPose: OpenMMLab pose estimation toolbox and benchmark.
• MMHuman3D: OpenMMLab 3D human parametric model toolbox and benchmark.
• MMSelfSup: OpenMMLab self-supervised learning toolbox and benchmark.
• MMRazor: OpenMMLab model compression toolbox and benchmark.
• MMFewShot: OpenMMLab fewshot learning toolbox and benchmark.
• MMAction2: OpenMMLab’s next-generation action understanding toolbox and benchmark.
• MMTracking: OpenMMLab video perception toolbox and benchmark.
• MMFlow: OpenMMLab optical flow toolbox and benchmark.
• MMEditing: OpenMMLab image and video editing toolbox.
• MMGeneration: OpenMMLab image and video generative models toolbox.
• MMDeploy: OpenMMLab model deployment framework.