Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.
Awesome Lists | Featured Topics | Projects
https://github.com/john-rocky/CoreML-Models

Converted CoreML Model Zoo.
https://github.com/john-rocky/CoreML-Models
coreml coreml-framework coremltools deep-learning gan gans image-classification ios machine-learning object-detection semantic-segmentation style-gan super-resolution swift
Last synced: about 1 month ago
JSON representation
Converted CoreML Model Zoo.
Host: GitHub
URL: https://github.com/john-rocky/CoreML-Models
Owner: john-rocky
Created: 2020-08-12T02:41:43.000Z (about 4 years ago)
Default Branch: master
Last Pushed: 2024-06-16T23:17:13.000Z (3 months ago)
Last Synced: 2024-07-18T17:54:32.777Z (about 2 months ago)
Topics: coreml, coreml-framework, coremltools, deep-learning, gan, gans, image-classification, ios, machine-learning, object-detection, semantic-segmentation, style-gan, super-resolution, swift
Homepage:
Size: 57.5 MB
Stars: 1,227
Watchers: 46
Forks: 111
Open Issues: 29
Metadata Files:
- Readme: README.md
Awesome Lists containing this project

README

        # CoreML-Models

Converted Core ML Model Zoo.



Core ML is a machine learning framework by Apple.

If you are iOS developer, you can easly use machine learning models in your Xcode project. 

# How to use

Take a look this model zoo, and if you found the CoreML model you want,

download the model from google drive link and bundle it in your project.

Or if the model have sample project link, try it and see how to use the model in the project.

You are free to do or not.

**If you like this repository, please give me a star so I can do my best.**

# Section Link

- [**Image Classifier**](#image-classifier)

  - [Efficientnetb0](#efficientnetb0)

  - [Efficientnetv2](#efficientnetv2)

  - [VisionTransformer](#visiontransformer)

  - [Conformer](#conformer)

  - [DeiT](#deit)

  - [RepVGG](#repvgg)

  - [RegNet](#regnet)

  - [MobileViTv2](#mobilevitv2)

  

- [**Object Detection**](#object-detection)

  - [YOLOv5s](#yolov5s)

  - [YOLOv7](#yolov7)

  - [YOLOv8](#yolov8)

- [**Segmentation**](#segmentation)

  - [U2Net](#u2net)

  - [IS-Net](#is-net)

  - [RMBG1.4](#rmbg14)

  - [face-parsing](#face-parsing)

  - [Segformer](#segformer)

  - [BiseNetv2](#bisenetv2)

  - [DNL](#dnl)

  - [ISANet](#isanet)

  - [FastFCN](#fastfcn)

  - [GCNet](#gcnet)

  - [DANet](#danet)

  - [Semantic FPN](#semantic-fpn)

  - [cloths_segmentation](#cloths_segmentation)

  - [easyportrait](#easyportrait)

- [**Super Resolution**](#super-resolution)

  - [Real ESRGAN](#real-esrgan)

  - [GFPGAN](#gfpgan)

  - [BSRGAN](#bsrgan)

  - [A-ESRGAN](#a-esrgan)

  - [Beby-GAN](#beby-gan)

  - [RRDN](#rrdn)

  - [Fast-SRGAN](#fast-srgan)

  - [ESRGAN](#esrgan)

  - [UltraSharp](#ultrasharp)

  - [SRGAN](#srgan)

  - [SRResNet](#srresnet)

  - [LESRCNN](#lesrcnn)

  - [MMRealSR](#mmrealsr)

  - [DASR](#dasr)

      

- [**Low Light Enhancement**](#low-light-enhancement)

  - [StableLLVE](#stablellve)

  - [Zero-DCE](#zero-dce)

  - [Retinexformer](#retinexformer)

- [**Image Restoration**](#image-restroration)

  - [MPRNet](#mprnet)

  - [MIRNetv2](#mirnetv2)

  

- [**Image Generation**](#image-generation)

  - [MobileStyleGAN](#mobilestylegan)

  - [DCGAN](#dcgan)

- [**Image2Image**](#image2image)

  - [Anime2Sketch](#anime2sketch)

  - [AnimeGAN2Face_Paint_512_v2](#animegan2face_paint_512_v2)

  - [Photo2Cartoon](#photo2cartoon)

  - [AnimeGANv2_Hayao](#animeGANv2_hayao)

  - [AnimeGANv2_Paprika](#animeGANv2_paprika)

  - [WarpGAN Caricature](#warpgancaricature)

  - [UGATIT_selfie2anime](#ugatit_selfie2anime)

  - [Fast-Neural-Style-Transfer](#fast-neural-style-transfer)

  - [White_box_Cartoonization](#white_box_cartoonization)

  - [FacialCartoonization](#facialcartoonization)

- [**Inpainting**](#inpainting)

  - [AOT-GAN-for-Inpainting](#aot-gan-for-inpainting)

  - [Lama](#lama)

- [**Monocular Depth Estimation**](#monocular-depth-estimation)

  - [MiDaS](#midas)

  

- [**Stable Diffusion**](#stable-diffusion) **:text2image**

  - [stable-diffusion-v1-5](#stable-diffusion-v1-5)

  - [pastel-mix](#pastel-mix)

  - [Orange Mix](#orange-mix)

  - [Counterfeit-V2.5](#counterfeit)

  - [anything-v4.5](#anything-v4)

  - [Openjourney](#openjourney)

  - [dreamlike-photoreal-2.0](#dreamlike-photoreal-2)

# How to get the model

You can get the model converted to CoreML format from the link of Google drive.

See the section below for how to use it in Xcode.

The license for each model conforms to the license for the original project.

# Image Classifier

### Efficientnet



| Google Drive Link | Size | Dataset |Original Project | License |

| ------------- | ------------- | ------------- |------------- |------------- |

| [Efficientnetb0](https://drive.google.com/file/d/1mJq8SMuDaCQHW77ui3fAfe5o3Qu2GKMi/view?usp=sharing) | 22.7 MB | ImageNet | [TensorFlowHub](https://tfhub.dev/tensorflow/efficientnet/b0/classification/1)  |[Apache2.0](https://opensource.org/licenses/Apache-2.0)|

### Efficientnetv2



| Google Drive Link | Size | Dataset |Original Project | License | Year|

| ------------- | ------------- | ------------- |------------- |------------- |------------- |

| [Efficientnetv2](https://drive.google.com/file/d/12JiGwXh8pX3yjoG_GsJOKAnPd3lbVrrn/view?usp=sharing) | 85.8 MB | ImageNet | [Google/autoML](https://github.com/google/automl/tree/master/efficientnetv2)  | [Apache2.0](https://github.com/google/automl/blob/master/LICENSE)|2021|

### VisionTransformer

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.



| Google Drive Link | Size | Dataset |Original Project | License |Year|

| ------------- | ------------- | ------------- |------------- |------------- |------------- |

| [VisionTransformer-B16](https://drive.google.com/file/d/1VPo8Cjv7dyicM4lcJ6TgxnD4AN3ldMQp/view?usp=sharing) | 347.5 MB | ImageNet | [google-research/vision_transformer](https://github.com/google-research/vision_transformer)  | [Apache2.0](https://github.com/google-research/vision_transformer/blob/main/LICENSE)|2021|

### Conformer

Local Features Coupling Global Representations for Visual Recognition.



| Google Drive Link | Size | Dataset |Original Project | License |Year|

| ------------- | ------------- | ------------- |------------- |------------- |------------- |

| [Conformer-tiny-p16](https://drive.google.com/file/d/1-4qVbuTYr4r4o08656iGtV8KKblAVVyr/view?usp=sharing) | 94.1 MB | ImageNet | [pengzhiliang/Conformer](https://github.com/pengzhiliang/Conformer)  | [Apache2.0](https://github.com/google-research/vision_transformer/blob/main/LICENSE)|2021|

### DeiT

Data-efficient Image Transformers



| Google Drive Link | Size | Dataset |Original Project | License |Year|

| ------------- | ------------- | ------------- |------------- |------------- |------------- |

| [DeiT-base384](https://drive.google.com/file/d/1-7J-b0fTjmZi2VDPrDCWKBsCYGxYP5yW/view?usp=sharing) | 350.5 MB | ImageNet | [facebookresearch/deit](https://github.com/facebookresearch/deit)  | [Apache2.0](https://github.com/facebookresearch/deit/blob/main/LICENSE)|2021|

### RepVGG

Making VGG-style ConvNets Great Again



| Google Drive Link | Size | Dataset |Original Project | License |Year|

| ------------- | ------------- | ------------- |------------- |------------- |------------- |

| [RepVGG-A0](https://drive.google.com/file/d/1i8mDvRGn2_OjzIG9ioVJyQrefVliKsh_/view?usp=sharing) | 33.3 MB | ImageNet | [DingXiaoH/RepVGG](https://github.com/DingXiaoH/RepVGG)  | [MIT](https://github.com/DingXiaoH/RepVGG/blob/main/LICENSE)|2021|

### RegNet

Designing Network Design Spaces



| Google Drive Link | Size | Dataset |Original Project | License |Year|

| ------------- | ------------- | ------------- |------------- |------------- |------------- |

| [regnet_y_400mf](https://drive.google.com/file/d/16jbUJ4gHSzdxxbYb99rOQe0FiKCuLyDB/view?usp=sharing) | 16.5 MB | ImageNet | [TORCHVISION.MODELS](https://pytorch.org/vision/stable/models.html#torchvision-models)  | [MIT](https://github.com/facebookresearch/pycls/blob/main/LICENSE)|2020|

### MobileViTv2

CVNets: A library for training computer vision networks



| Google Drive Link | Size | Dataset |Original Project | License |Year|Conversion Script|

| ------------- | ------------- | ------------- |------------- |------------- |------------- |------------- |

| [MobileViTv2](https://drive.google.com/file/d/1__aG67p6o5-NIchkHpfFJBszCpIhI0uf/view?usp=share_link) | 18.8 MB | ImageNet | [apple/ml-cvnets](https://github.com/apple/ml-cvnets)  | [apple](https://github.com/apple/ml-cvnets/blob/main/LICENSE)|2022|[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)]([https://colab.research.google.com/drive/1QiTlFsN948Xt2e4WgqUB8DnGgwWwtVZS?usp=sharing](https://colab.research.google.com/drive/1UQwhFpVP_4Q9I6LXPdBSS0VDhIRdUBQA?usp=sharing)) |

# Object Detection

### YOLOv5s



| Google Drive Link | Size | Output | Original Project | License | Note | Sample Project |

| ------------- | ------------- | ------------- | ------------- |------------- |------------- |------------- |

|[YOLOv5s](https://drive.google.com/file/d/1KT-9eKO4F-LYIJVYJg7dy2LEW_hVUq0M/view?usp=sharing)|29.3MB| Confidence(MultiArray (Double 0 × 80)), Coordinates (MultiArray (Double 0 × 4)) |[ultralytics/yolov5](https://github.com/ultralytics/yolov5)|[GNU](https://github.com/ultralytics/yolov5/blob/master/LICENSE)|Non Maximum Suppression has been added.| [CoreML-YOLOv5](https://github.com/john-rocky/CoreML-YOLOv5) |

### YOLOv7



| Google Drive Link | Size | Output | Original Project | License | Note | Sample Project | Conversion Script |

| ------------- | ------------- | ------------- | ------------- |------------- |------------- |------------- |------------- |

|[YOLOv7](https://drive.google.com/file/d/1EKBC7tiwP1tDvXUm_ldD1Nq7hW8HofLe/view?usp=sharing)|147.9MB| Confidence(MultiArray (Double 0 × 80)), Coordinates (MultiArray (Double 0 × 4)) |[WongKinYiu/yolov7](https://github.com/WongKinYiu/yolov7)|[GNU](https://github.com/WongKinYiu/yolov7/blob/main/LICENSE.md)|Non Maximum Suppression has been added.| [CoreML-YOLOv5](https://github.com/john-rocky/CoreML-YOLOv5) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1QiTlFsN948Xt2e4WgqUB8DnGgwWwtVZS?usp=sharing) |

### YOLOv8



| Google Drive Link | Size | Output | Original Project | License | Note | Sample Project | 

| ------------- | ------------- | ------------- | ------------- |------------- |------------- |------------- |

|[YOLOv8s](https://drive.google.com/file/d/1pLRh1Y37KLEMpQn3v8qH-A12swakoHbI/view?usp=share_link)|45.1MB| Confidence(MultiArray (Double 0 × 80)), Coordinates (MultiArray (Double 0 × 4)) |[ultralytics/ultralytics](https://github.com/ultralytics/ultralytics)|[GNU](https://github.com/ultralytics/ultralytics/blob/main/LICENSE)|Non Maximum Suppression has been added.| [CoreML-YOLOv5](https://github.com/john-rocky/CoreML-YOLOv5) |

# Segmentation

### [U2Net](https://drive.google.com/file/d/1cpm-x12Ih7Cqd_kOjfTvtt4ipGS3BpCx/view?usp=sharing)

 

| Google Drive Link | Size | Output |Original Project | License |

| ------------- | ------------- | ------------- | ------------- |------------- |

| [U2Net](https://drive.google.com/file/d/1cpm-x12Ih7Cqd_kOjfTvtt4ipGS3BpCx/view?usp=sharing) | 175.9 MB | Image(GRAYSCALE 320 × 320)| [xuebinqin/U-2-Net](https://github.com/xuebinqin)  | [Apache](https://github.com/john-rocky/CoreML-Models/blob/master/Apache-LICENSE)|

| [U2Netp](https://drive.google.com/file/d/1D-quPGy33PzSEC6A7EBNv7mCyuiBlO08/view?usp=sharing) | 4.6 MB | Image(GRAYSCALE 320 × 320) | [xuebinqin/U-2-Net](https://github.com/xuebinqin)  |  [Apache](https://github.com/john-rocky/CoreML-Models/blob/master/Apache-LICENSE)|

### [IS-Net](https://drive.google.com/drive/folders/13CkOTBCYc3FjGTU26lmCsRYsOkeHnAMA?usp=sharing)

 

 

| Google Drive Link | Size | Output |Original Project | License | Year | Conversion Script |

| ------------- | ------------- | ------------- | ------------- |------------- | ------------- |------------- |

| [IS-Net](https://drive.google.com/drive/folders/13CkOTBCYc3FjGTU26lmCsRYsOkeHnAMA?usp=sharing) | 176.1 MB | Image(GRAYSCALE 1024 × 1024)| [xuebinqin/DIS](https://github.com/xuebinqin/DIS)  | [Apache](https://github.com/xuebinqin/DIS/blob/main/LICENSE.md)| 2022 |[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1xWD7LZbI-_09LXmiYMdhA28V2qujvOlZ?usp=sharing)|

| [IS-Net-General-Use](https://drive.google.com/file/d/1Vglh1zPwTglroMvycnkLdFP6nCHf_GuH/view?usp=sharing) | 176.1 MB | Image(GRAYSCALE 1024 × 1024)| [xuebinqin/DIS](https://github.com/xuebinqin/DIS)  | [Apache](https://github.com/xuebinqin/DIS/blob/main/LICENSE.md)| 2022 |[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1xWD7LZbI-_09LXmiYMdhA28V2qujvOlZ?usp=sharing)|

### RMBG1.4

RMBG1.4 - The IS-Net enhanced with our unique training scheme and proprietary dataset. 

 

| Google Drive Link | Size | Output |Original Project | License | year  |Conversion Script |

| ------------- | ------------- | ------------- |------------- | ------------- | ------------- |------------- |

| [RMBG.mlpackage](https://drive.google.com/drive/folders/1-33OTxUoO6en8sVsFEvt3Vt_FQ-hwJ3m?usp=sharing)/[RMBG.mlmodel](https://drive.google.com/file/d/1-_O7uLioAvi9q0wbJOiis0dqa8ho4A4o/view?usp=drive_link) | 176 MB | Image(GrayScale 1024x1024) |[briaai/RMBG-1.4](https://huggingface.co/briaai/RMBG-1.4) | [Creative Commons](https://huggingface.co/briaai/RMBG-1.4) |2024|[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1KUTREfLbDklnKhaaJU2Q444TLxjmIXwN?usp=sharing)|

### face-Parsing

 

| Google Drive Link | Size | Output |Original Project | License | Sample Project |

| ------------- | ------------- | ------------- | ------------- | ------------- | ------------- |

| [face-Parsing](https://drive.google.com/file/d/1I_cu8x0k6d1AEV_VPLyMu3Pqg3hwmo7g/view?usp=sharing) | 53.2 MB | MultiArray(1 x 512 × 512)| [zllrunning/face-parsing.PyTorch](https://github.com/zllrunning/face-parsing.PyTorch)  | [MIT](https://github.com/zllrunning/face-parsing.PyTorch/blob/master/LICENSE)|[CoreML-face-parsing](https://github.com/john-rocky/CoreML-Face-Parsing) |

### Segformer

Simple and Efficient Design for Semantic Segmentation with Transformers

 

| Google Drive Link | Size | Output |Original Project | License | year |

| ------------- | ------------- | ------------- | ------------- | ------------- | ------------- |

| [SegFormer_mit-b0_1024x1024_cityscapes](https://drive.google.com/file/d/1-lcNjJM85DZh5-xQv4jlKL6I1ZMBk2uu/view?usp=sharing) | 14.9 MB | MultiArray(512 × 1024)| [NVlabs/SegFormer](https://github.com/NVlabs/SegFormer)  | [NVIDIA](https://github.com/NVlabs/SegFormer/blob/master/LICENSE)|2021|

### BiSeNetV2	

Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation

 

| Google Drive Link | Size | Output |Original Project | License | year |

| ------------- | ------------- | ------------- | ------------- | ------------- | ------------- |

| [BiSeNetV2_1024x1024_cityscapes](https://drive.google.com/file/d/1-20x0-TP8zqXCzDhH06TyL03SJRFYY9n/view?usp=sharing) | 12.8 MB | MultiArray | [ycszen/BiSeNet](https://github.com/ycszen/BiSeNet)  | Apache2.0 |2021|

### DNL

Disentangled Non-Local Neural Networks

 

| Google Drive Link | Size | Output |Dataset|Original Project | License | year |

| ------------- | ------------- | ------------- |------------- | ------------- | ------------- | ------------- |

| [dnl_r50-d8_512x512_80k_ade20k](https://drive.google.com/file/d/1DOnPGocotsjXknBuNqikgpFVpmH6s_E3/view?usp=sharing) | 190.8 MB | MultiArray[512x512] |ADE20K| [yinmh17/DNL-Semantic-Segmentation](https://github.com/yinmh17/DNL-Semantic-Segmentation)  | [Apache2.0](https://github.com/yinmh17/DNL-Semantic-Segmentation/blob/master/LICENSE) |2020|

### ISANet

Interlaced Sparse Self-Attention for Semantic Segmentation

 

| Google Drive Link | Size | Output |Dataset|Original Project | License | year |

| ------------- | ------------- | ------------- |------------- | ------------- | ------------- | ------------- |

| [isanet_r50-d8_512x512_80k_ade20k](https://drive.google.com/file/d/114ypGU9S1BOT2otl7P_gsmZbA3bCmz5K/view?usp=sharing) | 141.5 MB | MultiArray[512x512] |ADE20K| [openseg-group/openseg.pytorch](https://github.com/openseg-group/openseg.pytorch) | [MIT](https://github.com/openseg-group/openseg.pytorch/blob/master/LICENSE) |ArXiv'2019/IJCV'2021|

### FastFCN

Rethinking Dilated Convolution in the Backbone for Semantic Segmentation

 

| Google Drive Link | Size | Output |Dataset|Original Project | License | year |

| ------------- | ------------- | ------------- |------------- | ------------- | ------------- | ------------- |

| [fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k](https://drive.google.com/file/d/1-2CUR1M-a4xzUxdf5enU_9cUdxONmFbT/view?usp=sharing) | 326.2 MB | MultiArray[512x512] |ADE20K| [wuhuikai/FastFCN](https://github.com/wuhuikai/FastFCN) | [MIT](https://github.com/wuhuikai/FastFCN/blob/master/LICENSE) |ArXiv'2019|

### GCNet

Non-local Networks Meet Squeeze-Excitation Networks and Beyond

 

| Google Drive Link | Size | Output |Dataset|Original Project | License | year |

| ------------- | ------------- | ------------- |------------- | ------------- | ------------- | ------------- |

| [gcnet_r50-d8_512x512_20k_voc12aug](https://drive.google.com/file/d/1-DfjorbUDFXOVasSPoGk7GP1XC_OnNVT/view?usp=sharing) | 189 MB | MultiArray[512x512] |PascalVOC| [xvjiarui/GCNet](https://github.com/xvjiarui/GCNet) | [Apache License 2.0](https://github.com/xvjiarui/GCNet/blob/master/LICENSE) |ICCVW'2019/TPAMI'2020|

### DANet

Dual Attention Network for Scene Segmentation(CVPR2019)

 

| Google Drive Link | Size | Output |Dataset|Original Project | License | year |

| ------------- | ------------- | ------------- |------------- | ------------- | ------------- | ------------- |

| [danet_r50-d8_512x1024_40k_cityscapes](https://drive.google.com/file/d/1A45r_725V7edPTSrjA4T-T03rPD6Sj2z/view?usp=sharing) | 189.7 MB | MultiArray[512x1024] |CityScapes| [junfu1115/DANet](https://github.com/junfu1115/DANet/) | [MIT](https://github.com/junfu1115/DANet/blob/master/LICENSE) |CVPR2019|

### Semantic-FPN

Panoptic Feature Pyramid Networks

 

| Google Drive Link | Size | Output |Dataset|Original Project | License | year |

| ------------- | ------------- | ------------- |------------- | ------------- | ------------- | ------------- |

| [fpn_r50_512x1024_80k_cityscapes](https://drive.google.com/file/d/1_IVhCnJ--54P7qVGLo8-ks_LRGXJQXht/view?usp=sharing) | 108.6 MB | MultiArray[512x1024] |CityScapes| [facebookresearch/detectron2](https://github.com/facebookresearch/detectron2) | [Apache License 2.0](https://github.com/facebookresearch/detectron2/blob/main/LICENSE) |2019|

### cloths_segmentation

Code for binary segmentation of various cloths.

 

| Google Drive Link | Size | Output |Dataset|Original Project | License | year |

| ------------- | ------------- | ------------- |------------- | ------------- | ------------- | ------------- |

| [clothSegmentation](https://drive.google.com/file/d/1-2AydEgkth6UTD5bu13R0fJYoqZZMG3e/view?usp=sharing) | 50.1 MB | Image(GrayScale 640x960) |[fashion-2019-FGVC6](https://www.kaggle.com/c/imaterialist-fashion-2019-FGVC6)| [facebookresearch/detectron2](https://github.com/facebookresearch/detectron2) | [MIT](https://github.com/ternaus/cloths_segmentation/blob/main/LICENSE) |2020|

### easyportrait

EasyPortrait - Face Parsing and Portrait Segmentation Dataset.

 

| Google Drive Link | Size | Output |Original Project | License | year | Swift sample |Conversion Script |

| ------------- | ------------- | ------------- |------------- | ------------- | ------------- |------------- |------------- |

| [easyportrait-segformer512-fp](https://drive.google.com/drive/folders/13BUhNpQHodAgcj6eJaPbzuSUaFn3JuU-?usp=sharing) | 7.6 MB | Image(GrayScale 512x512) * 9 |[hukenovs/easyportrait](https://github.com/hukenovs/easyportrait) | [Creative Commons](https://github.com/hukenovs/easyportrait/tree/main/license) |2023|[easyportrait-coreml](https://github.com/john-rocky/easyportrait-coreml)|[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/11a3XWFA8fa8V0a2zgWFqOMUaZgF4O1qt?usp=sharing)|

# Super Resolution

### [Real ESRGAN](https://drive.google.com/file/d/1cpm-x12Ih7Cqd_kOjfTvtt4ipGS3BpCx/view?usp=sharing)

  

| Google Drive Link | Size | Output |Original Project | License | year |

| ------------- | ------------- | ------------- | ------------- | ------------- |------------- |

| [Real ESRGAN4x](https://drive.google.com/file/d/16JEWh48fgQc8az7avROePOd-PYda0Yi2/view?usp=sharing) | 66.9 MB | Image(RGB 2048x2048)| [xinntao/Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN)  | [BSD 3-Clause License](https://github.com/xinntao/Real-ESRGAN/blob/master/LICENSE) |2021|

| [Real ESRGAN Anime4x](https://drive.google.com/file/d/1qXdLx46Lpqya7Txc5Wvgkd2Dqlnqm3Qm/view?usp=sharing) | 66.9 MB | Image(RGB 2048x2048)| [xinntao/Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN)  | [BSD 3-Clause License](https://github.com/xinntao/Real-ESRGAN/blob/master/LICENSE) |2021|

### [GFPGAN](https://drive.google.com/file/d/1-3fF4aPnh8ygUOmKItIrZ318xI9JGmQx/view?usp=sharing)

Towards Real-World Blind Face Restoration with Generative Facial Prior

  

| Google Drive Link | Size | Output |Original Project | License |year |

| ------------- | ------------- | ------------- | ------------- | ------------- |------------- |

| [GFPGAN](https://drive.google.com/file/d/1-3fF4aPnh8ygUOmKItIrZ318xI9JGmQx/view?usp=sharing) | 337.4 MB | Image(RGB 512x512)| [TencentARC/GFPGAN](https://github.com/TencentARC/GFPGAN)  | [Apache2.0](https://github.com/TencentARC/GFPGAN/blob/master/LICENSE) |2021|

### [BSRGAN](https://drive.google.com/file/d/1-3K89vJZ5OUAh4xdSAifgnL52jbl2fVf/view?usp=sharing)

  

| Google Drive Link | Size | Output |Original Project | License |year |

| ------------- | ------------- | ------------- | ------------- | ------------- |------------- |

| [BSRGAN](https://drive.google.com/file/d/1-3K89vJZ5OUAh4xdSAifgnL52jbl2fVf/view?usp=sharing) | 66.9 MB | Image(RGB 2048x2048)| [cszn/BSRGAN](https://github.com/cszn/BSRGAN)  |  |2021|

### [A-ESRGAN](https://drive.google.com/file/d/1-0rKVQtFXNWfIBIpvyemjuO3O00GZBeb/view?usp=sharing)

  

| Google Drive Link | Size | Output |Original Project | License |year |Conversion Script|

| ------------- | ------------- | ------------- | ------------- | ------------- |------------- |------------- |

| [A-ESRGAN](https://drive.google.com/file/d/1-0rKVQtFXNWfIBIpvyemjuO3O00GZBeb/view?usp=sharing) | 63.8 MB | Image(RGB 1024x1024)| [aesrgan/A-ESRGANN](https://github.com/aesrgan/A-ESRGAN)  | [BSD 3-Clause License](https://github.com/aesrgan/A-ESRGAN/blob/main/LICENSE) |2021|[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1UxtSXnVYOXEfTVdIeoP7HQEjsyVbqOKa?usp=sharing)|

### [Beby-GAN](https://drive.google.com/file/d/1bJ7_NgR2KXI46JiFk5hH_6IdCHMyhN05/view?usp=sharing)

Best-Buddy GANs for Highly Detailed Image Super-Resolution

  

| Google Drive Link | Size | Output |Original Project | License |year |

| ------------- | ------------- | ------------- | ------------- | ------------- |------------- |

| [Beby-GAN](https://drive.google.com/file/d/1bJ7_NgR2KXI46JiFk5hH_6IdCHMyhN05/view?usp=sharing) | 66.9 MB | Image(RGB 2048x2048)| [dvlab-research/Simple-SR](https://github.com/dvlab-research/Simple-SR)  | [MIT](https://github.com/dvlab-research/Simple-SR/blob/master/LICENSE) |2021|

### [RRDN](https://drive.google.com/file/d/1-M30vR0xMuYDn2p5O4KZrUnUXy4SNThF/view?usp=sharing)

The Residual in Residual Dense Network for image super-scaling.

 

| Google Drive Link | Size | Output |Original Project | License |year |

| ------------- | ------------- | ------------- | ------------- | ------------- |------------- |

| [RRDN](https://drive.google.com/file/d/1-M30vR0xMuYDn2p5O4KZrUnUXy4SNThF/view?usp=sharing) | 16.8 MB | Image(RGB 2048x2048)| [idealo/image-super-resolution](https://github.com/idealo/image-super-resolution)  | [Apache2.0](https://github.com/idealo/image-super-resolution/blob/master/LICENSE) |2018|

### [Fast-SRGAN](https://drive.google.com/file/d/1gYXbhcSUm5rhcCAmwLruonAhu8jvyDL8/view?usp=sharing)

Fast-SRGAN.

 

| Google Drive Link | Size | Output |Original Project | License |year |

| ------------- | ------------- | ------------- | ------------- | ------------- |------------- |

| [Fast-SRGAN](https://drive.google.com/file/d/1gYXbhcSUm5rhcCAmwLruonAhu8jvyDL8/view?usp=sharing) | 628 KB | Image(RGB 1024x1024)| [HasnainRaz/Fast-SRGAN](https://github.com/HasnainRaz/Fast-SRGAN)  | [MIT](https://github.com/HasnainRaz/Fast-SRGAN/blob/master/LICENSE) |2019|

### [ESRGAN](https://drive.google.com/file/d/1fkRbh_gckuFlgr357OIdOrEJK4T_2Xkz/view?usp=sharing)

Enhanced-SRGAN.

 

| Google Drive Link | Size | Output |Original Project | License |year |

| ------------- | ------------- | ------------- | ------------- | ------------- |------------- |

| [ESRGAN](https://drive.google.com/file/d/1fkRbh_gckuFlgr357OIdOrEJK4T_2Xkz/view?usp=sharing) | 66.9 MB | Image(RGB 2048x2048)| [xinntao/ESRGAN](https://github.com/xinntao/ESRGAN)  | [Apache 2.0](https://github.com/xinntao/ESRGAN/blob/master/LICENSE) |2018|

### [UltraSharp](https://drive.google.com/drive/folders/1-Q1SdS8iHWTfTs7FE39pUTEubPks30Ca?usp=drive_link)

Pretrained: 4xESRGAN

 

| Google Drive Link | Size | Output |Original Project | License |year |

| ------------- | ------------- | ------------- | ------------- | ------------- |------------- |

| [UltraSharp](https://drive.google.com/drive/folders/1-Q1SdS8iHWTfTs7FE39pUTEubPks30Ca?usp=drive_link) | 34 MB | Image(RGB 1024x1024)| [Kim2019/](https://openmodeldb.info/models/4x-UltraSharp)  | [CC-BY-NC-SA-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/deed.ja) |2021|

### [SRGAN](https://drive.google.com/file/d/1-076W2o0wCtoODptikX1eOnlFBx2s3qK/view?usp=sharing)

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network.

 

| Google Drive Link | Size | Output |Original Project | License |year |

| ------------- | ------------- | ------------- | ------------- | ------------- |------------- |

| [SRGAN](https://drive.google.com/file/d/1-076W2o0wCtoODptikX1eOnlFBx2s3qK/view?usp=sharing) | 6.1 MB | Image(RGB 2048x2048)| [dongheehand/SRGAN-PyTorch](https://github.com/dongheehand/SRGAN-PyTorch)  |  |2017|

### [SRResNet](https://drive.google.com/file/d/1-2kYZgF_Z6vntrRsHmRiwyHJg5TC1PSW/view?usp=sharing)

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network.

 

| Google Drive Link | Size | Output |Original Project | License |year |

| ------------- | ------------- | ------------- | ------------- | ------------- |------------- |

| [SRResNet](https://drive.google.com/file/d/1-2kYZgF_Z6vntrRsHmRiwyHJg5TC1PSW/view?usp=sharing) | 6.1 MB | Image(RGB 2048x2048)| [dongheehand/SRGAN-PyTorch](https://github.com/dongheehand/SRGAN-PyTorch)  |  |2017|

### [LESRCNN](https://drive.google.com/file/d/1-0zgxURZwqX0mAAVy69K-owE7QP-7NfJ/view?usp=sharing)

Lightweight Image Super-Resolution with Enhanced CNN.

 

| Google Drive Link | Size | Output |Original Project | License |year | Conversion Script |

| ------------- | ------------- | ------------- | ------------- | ------------- |------------- |------------- |

| [LESRCNN](https://drive.google.com/file/d/1-0zgxURZwqX0mAAVy69K-owE7QP-7NfJ/view?usp=sharing) | 4.3 MB | Image(RGB 512x512)| [hellloxiaotian/LESRCNN](https://github.com/hellloxiaotian/LESRCNN)  |  |2020|[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1Q6piAJvXSmb-DcdFipcRUEYuHi9fnTm7?usp=sharing)|

### [MMRealSR](https://drive.google.com/file/d/1-HwMLvOy_hHycHNhojob6uT8t6tRyWqb/view?usp=sharing)

Metric Learning based Interactive Modulation for Real-World Super-Resolution

 

| Google Drive Link | Size | Output |Original Project | License |year | Conversion Script |

| ------------- | ------------- | ------------- | ------------- | ------------- |------------- |------------- |

| [MMRealSRGAN](https://drive.google.com/file/d/1-HwMLvOy_hHycHNhojob6uT8t6tRyWqb/view?usp=sharing) | 104.6 MB | Image(RGB 1024x1024)| [TencentARC/MM-RealSR](https://github.com/TencentARC/MM-RealSR)  | [BSD 3-Clause](https://github.com/TencentARC/MM-RealSR/blob/main/LICENSE) |2022|[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1zhUhQhdtP02N2pFIxsO5lin7tDOExZCo?usp=sharing)|

| [MMRealSRNet](https://drive.google.com/file/d/1-77P8AtHFh5kca2kYZ6X7GaUueoa3el_/view?usp=sharing) | 104.6 MB | Image(RGB 1024x1024)| [TencentARC/MM-RealSR](https://github.com/TencentARC/MM-RealSR)  | [BSD 3-Clause](https://github.com/TencentARC/MM-RealSR/blob/main/LICENSE) |2022|[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1zhUhQhdtP02N2pFIxsO5lin7tDOExZCo?usp=sharing)|

### [DASR](https://drive.google.com/drive/folders/10J2ehHewK2ppS5ToDqmtJ2Ei5k8vcdL0?usp=sharing)

Pytorch implementation of "Unsupervised Degradation Representation Learning for Blind Super-Resolution", CVPR 2021

 

| Google Drive Link | Size | Output |Original Project | License |year|

| ------------- | ------------- | ------------- | ------------- | ------------- |------------- |

| [DASR](https://drive.google.com/drive/folders/10J2ehHewK2ppS5ToDqmtJ2Ei5k8vcdL0?usp=sharing) | 12.1 MB | Image(RGB 1024x1024)| [The-Learning-And-Vision-Atelier-LAVA/DASR](https://github.com/The-Learning-And-Vision-Atelier-LAVA/DASR)  | [MIT](https://github.com/The-Learning-And-Vision-Atelier-LAVA/DASR/blob/main/LICENSE) |2022|

# Low Light Enhancement

### StableLLVE

Learning Temporal Consistency for Low Light Video Enhancement from Single Images.

  

| Google Drive Link | Size | Output |Original Project | License |Year|

| ------------- | ------------- | ------------- | ------------- | ------------- | ------------- |

| [StableLLVE](https://drive.google.com/file/d/1-9xry7XeCJYsZadxcfTscjGi_Sna5NhM/view?usp=sharing) | 17.3 MB | Image(RGB 512x512)| [zkawfanx/StableLLVE](https://github.com/zkawfanx/StableLLVE)  | [MIT](https://github.com/zkawfanx/StableLLVE/blob/main/LICENSE) |2021|

### Zero-DCE

Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement

  

| Google Drive Link | Size | Output |Original Project | License |Year|Conversion Script|

| ------------- | ------------- | ------------- | ------------- | ------------- | ------------- | ------------- |

| [Zero-DCE](https://drive.google.com/file/d/1-0lxlBNFm8E_y9ImhS2wxq0p1ZJlXyoA/view?usp=sharing) | 320KB | Image(RGB 512x512)| [Li-Chongyi/Zero-DCE](https://github.com/Li-Chongyi/Zero-DCE)  | [See Repo](https://github.com/Li-Chongyi/Zero-DCE) |2021|[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1sh3O-4EvYv49Rlm59beH6koHe0sYxc2r?usp=sharing)|

### Retinexformer

Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement

  

| Google Drive Link | Size | Output |Original Project | License |Year|Conversion Script|

| ------------- | ------------- | ------------- | ------------- | ------------- | ------------- | ------------- |

| [ZRetinexformer FiveK](https://drive.google.com/drive/folders/1ea6vBuLG-z4TAK4iU6vrgABAAlHuDdhy?usp=drive_link) | 3.4MB | Image(RGB 512x512)| [caiyuanhao1998/Retinexformer](https://github.com/caiyuanhao1998/Retinexformer)  | [MIT](https://github.com/caiyuanhao1998/Retinexformer?tab=MIT-1-ov-file#readme) |2023|[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/10PtPI4V72Pp6PQZcrah-vClGzjKLaGGK?usp=sharing)|

| [ZRetinexformer NTIRE](https://drive.google.com/drive/folders/14piyZVwzu4Abpfgwh2HIKoubeeE-3qoq?usp=drive_link) | 3.4MB | Image(RGB 512x512)| [caiyuanhao1998/Retinexformer](https://github.com/caiyuanhao1998/Retinexformer)  | [MIT](https://github.com/caiyuanhao1998/Retinexformer?tab=MIT-1-ov-file#readme) |2023|[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/10PtPI4V72Pp6PQZcrah-vClGzjKLaGGK?usp=sharing)|

# Image Restoration

### MPRNet

Multi-Stage Progressive Image Restoration.

Debluring

  

Denoising

  

Deraining

  

| Google Drive Link | Size | Output |Original Project | License |Year|

| ------------- | ------------- | ------------- | ------------- | ------------- | ------------- |

| [MPRNetDebluring](https://drive.google.com/file/d/1--5L6BxxbyYGY9ey5WCIrl7g1yYBN27U/view?usp=sharing) | 137.1 MB | Image(RGB 512x512)| [swz30/MPRNet](https://github.com/swz30/MPRNet)  | [MIT](https://github.com/swz30/MPRNet/blob/main/LICENSE.md) |2021|

| [MPRNetDeNoising](https://drive.google.com/file/d/1-04xou-UgoflZb7MqTBycCpuLWKUAj0i/view?usp=sharing) | 108 MB | Image(RGB 512x512)| [swz30/MPRNet](https://github.com/swz30/MPRNet)  | [MIT](https://github.com/swz30/MPRNet/blob/main/LICENSE.md) |2021|

| [MPRNetDeraining](https://drive.google.com/file/d/1tGvjj49yaDym24vGdGqr1VKOtGd7ALKB/view?usp=sharing) | 24.5 MB | Image(RGB 512x512)| [swz30/MPRNet](https://github.com/swz30/MPRNet)  | [MIT](https://github.com/swz30/MPRNet/blob/main/LICENSE.md) |2021|

### MIRNetv2

Learning Enriched Features for Fast Image Restoration and Enhancement.

Denoising

  

Super Resolution

  

Contrast Enhancement

  

Low Light Enhancement

  

| Google Drive Link | Size | Output |Original Project | License |Year|Conversion Script|

| ------------- | ------------- | ------------- | ------------- | ------------- | ------------- | ------------- |

| [MIRNetv2Denoising](https://drive.google.com/file/d/1-HY2AhQV84LUZMadsbIi4TGBhEntAOaF/view?usp=sharing) | 42.5 MB | Image(RGB 512x512)| [swz30/MIRNetv2](https://github.com/swz30/MIRNetv2)  | [ACADEMIC PUBLIC LICENSE](https://github.com/swz30/MIRNetv2/blob/main/LICENSE.md) |2022|[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1lSWCn0et08hdS3sgKc40c7VXUvKcqCSi?usp=sharing)|

| [MIRNetv2SuperResolution](https://drive.google.com/file/d/1-BLfJj8xK_bw-GsGLfRR9uMvuA2VOqsh/view?usp=sharing) | 42.5 MB | Image(RGB 512x512)| [swz30/MIRNetv2](https://github.com/swz30/MIRNetv2)  | [ACADEMIC PUBLIC LICENSE](https://github.com/swz30/MIRNetv2/blob/main/LICENSE.md) |2022|[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1lSWCn0et08hdS3sgKc40c7VXUvKcqCSi?usp=sharing)|

| [MIRNetv2ContrastEnhancement](https://drive.google.com/file/d/1--q9Decpy1ZZbSifiE26SkpXstoadpM8/view?usp=sharing) | 42.5 MB | Image(RGB 512x512)| [swz30/MIRNetv2](https://github.com/swz30/MIRNetv2)  | [ACADEMIC PUBLIC LICENSE](https://github.com/swz30/MIRNetv2/blob/main/LICENSE.md) |2022|[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1lSWCn0et08hdS3sgKc40c7VXUvKcqCSi?usp=sharing)|

| [MIRNetv2LowLightEnhancement](https://drive.google.com/file/d/1Yh3FCogRfQ8k7Hh_UIZAnGwwhXHX6k6P/view?usp=sharing) | 42.5 MB | Image(RGB 512x512)| [swz30/MIRNetv2](https://github.com/swz30/MIRNetv2)  | [ACADEMIC PUBLIC LICENSE](https://github.com/swz30/MIRNetv2/blob/main/LICENSE.md) |2022|[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1lSWCn0et08hdS3sgKc40c7VXUvKcqCSi?usp=sharing)|

# Image Generation

### [MobileStyleGAN](https://drive.google.com/drive/folders/1rUV6AXwp8JhPPmkog-0r0AUGzUvN9DmW?usp=sharing)

  

| Google Drive Link | Size | Output | Original Project | License | Sample Project |

| ------------- | ------------- | ------------- | ------------- |  ------------- |  ------------- | 

| [MobileStyleGAN](https://drive.google.com/drive/folders/1rUV6AXwp8JhPPmkog-0r0AUGzUvN9DmW?usp=sharing) | 38.6MB  | Image(Color 1024 × 1024)| [bes-dev/MobileStyleGAN.pytorch](https://github.com/bes-dev/MobileStyleGAN.pytorch)  | [Nvidia Source Code License-NC](https://github.com/bes-dev/MobileStyleGAN.pytorch/blob/develop/LICENSE-NVIDIA) | [CoreML-StyleGAN](https://github.com/john-rocky/CoreML-StyleGAN) |

### [DCGAN](https://drive.google.com/file/d/132GrmmuETSLTml1zWyLUnIksclP-8vGw/view?usp=sharing)



| Google Drive Link | Size | Output | Original Project | 

| ------------- | ------------- | ------------- | ------------- | 

| [DCGAN](https://drive.google.com/file/d/132GrmmuETSLTml1zWyLUnIksclP-8vGw/view?usp=sharing)　| 9.2MB | MultiArray | [TensorFlowCore](https://www.tensorflow.org/tutorials/generative/dcgan)|

# Image2Image

### [Anime2Sketch](https://drive.google.com/file/d/1-52NnZ1kajZI5Rk0tn3DegpU38la_jYk/view?usp=sharing)

 

| Google Drive Link | Size | Output | Original Project | License | Usage |

| ------------- | ------------- | ------------- | ------------- | ------------- |  ------------- | 

| [Anime2Sketch](https://drive.google.com/file/d/1-52NnZ1kajZI5Rk0tn3DegpU38la_jYk/view?usp=sharing) | 217.7MB  | Image(Color 512 × 512)| [Mukosame/Anime2Sketch](https://github.com/Mukosame/Anime2Sketch)  | [MIT](https://github.com/Mukosame/Anime2Sketch/blob/master/LICENSE)| Drop an image to preview|

### [AnimeGAN2Face_Paint_512_v2](https://drive.google.com/file/d/1phSgcAz3LNbk2v2RoSESmr7PFxTAHcxb/view?usp=sharing)

 

| Google Drive Link | Size | Output | Original Project | Conversion Script |

| ------------- | ------------- | ------------- | ------------- |  ------------- | 

| [AnimeGAN2Face_Paint_512_v2](https://drive.google.com/file/d/1phSgcAz3LNbk2v2RoSESmr7PFxTAHcxb/view?usp=sharing) | 8.6MB  | Image(Color 512 × 512)| [bryandlee/animegan2-pytorch](https://github.com/bryandlee/animegan2-pytorch#additional-model-weights)  |[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1WGAxMaikjNIfqdGRndEOmNyeVf33nGNh?usp=sharing) |

### [Photo2Cartoon](https://drive.google.com/file/d/1xFWZ9Rf1o_LtwBpmSw2zSwPGk2FY6Wya/view?usp=sharing)

 

| Google Drive Link | Size | Output | Original Project | License | Note |

| ------------- | ------------- | ------------- | ------------- | ------------- | ------------- | 

| [Photo2Cartoon](https://drive.google.com/file/d/1xFWZ9Rf1o_LtwBpmSw2zSwPGk2FY6Wya/view?usp=sharing) | 15.2 MB  | Image(Color 256 × 256)| [minivision-ai/photo2cartoon](https://github.com/minivision-ai/photo2cartoon) | [MIT](https://github.com/minivision-ai/photo2cartoon/blob/master/LICENSE) | The output is little bit different from the original model. It cause some operations were converted replaced　manually. |

### [AnimeGANv2_Hayao](https://drive.google.com/file/d/1G53oZ1hiMcLJs1loN_fe_VmBVfegh9ha/view?usp=sharing)

 

| Google Drive Link | Size | Output | Original Project | Sample |

| ------------- | ------------- | ------------- | ------------- | ------------- |

| [AnimeGANv2_Hayao](https://drive.google.com/file/d/1G53oZ1hiMcLJs1loN_fe_VmBVfegh9ha/view?usp=sharing)　| 8.7MB | Image(256 x 256) | [TachibanaYoshino/AnimeGANv2](https://github.com/TachibanaYoshino/AnimeGANv2)|[AnimeGANv2-iOS](https://github.com/john-rocky/AnimeGANv2-iOS)|

### [AnimeGANv2_Paprika](https://drive.google.com/file/d/10drMcmF67iREUK8NY8ekMHrsyVirs5XT/view?usp=sharing)

 

| Google Drive Link | Size | Output | Original Project | 

| ------------- | ------------- | ------------- | ------------- | 

| [AnimeGANv2_Paprika](https://drive.google.com/file/d/10drMcmF67iREUK8NY8ekMHrsyVirs5XT/view?usp=sharing)　| 8.7MB | Image(256 x 256) | [TachibanaYoshino/AnimeGANv2](https://github.com/TachibanaYoshino/AnimeGANv2)|

### [WarpGAN Caricature](https://drive.google.com/file/d/1HE3qvfjuXZMFelRcmmGsLzoO5dV8lnaQ/view?usp=sharing)

 

| Google Drive Link | Size | Output | Original Project | 

| ------------- | ------------- | ------------- | ------------- | 

| [WarpGAN Caricature](https://drive.google.com/file/d/1HE3qvfjuXZMFelRcmmGsLzoO5dV8lnaQ/view?usp=sharing)　| 35.5MB | Image(256 x 256) | [seasonSH/WarpGAN](https://github.com/seasonSH/WarpGAN)|

### [UGATIT_selfie2anime](https://drive.google.com/file/d/1o15OO0Kn0tq79fFkmBm3PES93IRQOxB-/view?usp=sharing)

 

| Google Drive Link | Size | Output | Original Project | 

| ------------- | ------------- | ------------- | ------------- | 

| [UGATIT_selfie2anime](https://drive.google.com/file/d/1o15OO0Kn0tq79fFkmBm3PES93IRQOxB-/view?usp=sharing) | 266.2MB(quantized) | Image(256x256) | [taki0112/UGATIT](https://github.com/taki0112/UGATIT)  |

### CartoonGAN

| Google Drive Link | Size | Output | Original Project | 

| ------------- | ------------- | ------------- | ------------- | 

| [CartoonGAN_Shinkai](https://drive.google.com/file/d/1j9bvHFBX5yctSeaE8FEvUv-r-hEVvXwi/view?usp=sharing)　| 44.6MB | MultiArray | [mnicnc404/CartoonGan-tensorflow](https://github.com/mnicnc404/CartoonGan-tensorflow)|

| [CartoonGAN_Hayao](https://drive.google.com/file/d/1-2dTGge4fza-TTBI9actkg_xp91zYT-F/view?usp=sharing)　| 44.6MB | MultiArray | [mnicnc404/CartoonGan-tensorflow](https://github.com/mnicnc404/CartoonGan-tensorflow)|

| [CartoonGAN_Hosoda](https://drive.google.com/file/d/1-5VB1g7kRt0KMe6u37fi_t18l-Zn_wr1/view?usp=sharing)　| 44.6MB | MultiArray | [mnicnc404/CartoonGan-tensorflow](https://github.com/mnicnc404/CartoonGan-tensorflow)|

| [CartoonGAN_Paprika](https://drive.google.com/file/d/1-5x3TYugodcnGYiEEDitFqMQPVHsCDs_/view?usp=sharing)　| 44.6MB | MultiArray | [mnicnc404/CartoonGan-tensorflow](https://github.com/mnicnc404/CartoonGan-tensorflow)|

### [Fast-Neural-Style-Transfer](https://drive.google.com/file/d/1o15OO0Kn0tq79fFkmBm3PES93IRQOxB-/view?usp=sharing)

 

 

 

| Google Drive Link | Size | Output |Original Project | License |Year|

| ------------- | ------------- | ------------- | ------------- | ------------- | ------------- |

| [fast-neural-style-transfer-cuphead](https://drive.google.com/file/d/1-LLQF8T6MrcpdiYZkdGZAizkj7c-lJ9e/view?usp=sharing) | 6.4MB | Image(RGB 960x640)| [eriklindernoren/Fast-Neural-Style-Transfer](https://github.com/eriklindernoren/Fast-Neural-Style-Transfer)  | [MIT](https://github.com/eriklindernoren/Fast-Neural-Style-Transfer/blob/master/LICENSE) |2019|

| [fast-neural-style-transfer-starry-night](https://drive.google.com/file/d/1-HLHIrV_WwZJsEkZ34nTfqnlIHIe04Vy/view?usp=sharing) |  6.4MB | Image(RGB 960x640)| [eriklindernoren/Fast-Neural-Style-Transfer](https://github.com/eriklindernoren/Fast-Neural-Style-Transfer)  | [MIT](https://github.com/eriklindernoren/Fast-Neural-Style-Transfer/blob/master/LICENSE) |2019|

| [fast-neural-style-transfer-mosaic](https://drive.google.com/file/d/1-GmnewjDz2Cs7-CfXPSFIgOruQvBbK2X/view?usp=sharing) |  6.4MB | Image(RGB 960x640)| [eriklindernoren/Fast-Neural-Style-Transfer](https://github.com/eriklindernoren/Fast-Neural-Style-Transfer)  | [MIT](https://github.com/eriklindernoren/Fast-Neural-Style-Transfer/blob/master/LICENSE) |2019|

### [White_box_Cartoonization](https://drive.google.com/file/d/1QGNJzEp0fo6oOryTos1dazEKaS34WzZC/view?usp=sharing)

Learning to Cartoonize Using White-box Cartoon Representations

 

| Google Drive Link | Size | Output | Original Project | License |Year|

| ------------- | ------------- | ------------- | ------------- | ------------- | ------------- | 

| [White_box_Cartoonization](https://drive.google.com/file/d/1QGNJzEp0fo6oOryTos1dazEKaS34WzZC/view?usp=sharing) | 5.9MB | Image(1536x1536) | [SystemErrorWang/White-box-Cartoonization](https://github.com/SystemErrorWang/White-box-Cartoonization)  |[creativecommons](https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode)|CVPR2020|

### [FacialCartoonization](https://drive.google.com/file/d/1CJH4tuR3ArKvxrmAE_44lbsAwUzjtyXi/view?usp=sharing)

White-box facial image cartoonizaiton

 

| Google Drive Link | Size | Output | Original Project | License |Year|

| ------------- | ------------- | ------------- | ------------- | ------------- | ------------- | 

| [FacialCartoonization](https://drive.google.com/file/d/1CJH4tuR3ArKvxrmAE_44lbsAwUzjtyXi/view?usp=sharing) | 8.4MB | Image(256x256) | [SystemErrorWang/FacialCartoonization](https://github.com/SystemErrorWang/FacialCartoonization)  |[creativecommons](https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode)|2020|

# Inpainting

### AOT-GAN-for-Inpainting



| Google Drive Link | Size | Output | Original Project | License | Note | Sample Project |

| ------------- | ------------- | ------------- | ------------- |------------- |------------- |------------- |

|[AOT-GAN-for-Inpainting](https://drive.google.com/file/d/16rF46DFcDPherlpgjuL60065xcP2N3nv/view?usp=share_link)|60.8MB| MLMultiArray(3,512,512) |[researchmm/AOT-GAN-for-Inpainting](https://github.com/researchmm/AOT-GAN-for-Inpainting)|[Apache2.0](https://github.com/open-mmlab/mmediting/blob/master/LICENSE)|To use see sample.| [john-rocky/Inpainting-CoreML](https://github.com/john-rocky/Inpainting-CoreML) |

### [Lama](https://drive.google.com/drive/folders/1s_uICJQykFFxgVubpBNeLLDL0JsxgdCd?usp=sharing)



| Google Drive Link | Size | Input | Output | Original Project | License | Note | Sample Project | Conversion Script |

| ------------- | ------------- | ------------- | ------------- |------------- |------------- |------------- |------------- |------------- |

|[Lama](https://drive.google.com/drive/folders/1s_uICJQykFFxgVubpBNeLLDL0JsxgdCd?usp=sharing)|216.6MB| Image (Color 800 × 800), Image (GrayScale 800 × 800)| Image (Color 800 × 800) |[advimman/lama](https://github.com/advimman/lama)|[Apache2.0](https://github.com/advimman/lama/blob/main/LICENSE)|To use see sample.| [john-rocky/lama-cleaner-iOS](https://github.com/john-rocky/lama-cleaner-iOS) | [mallman/CoreMLaMa](https://github.com/mallman/CoreMLaMa)|

# Monocular Depth Estimation

### [MiDaS](https://drive.google.com/file/d/1agGnt5Cq5CGzoNDl9Nb-3u7pB5SrIbN4/view?usp=share_link)

Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer

 

| Google Drive Link | Size | Output | Original Project | License |Year|Conversion Script |

| ------------- | ------------- | ------------- | ------------- | ------------- | ------------- | ------------- | 

| [MiDaS_Small](https://drive.google.com/file/d/1agGnt5Cq5CGzoNDl9Nb-3u7pB5SrIbN4/view?usp=share_link) | 66.3MB | MultiArray(1x256x256) | [isl-org/MiDaS](https://github.com/isl-org/MiDaS)  |[MIT](https://github.com/isl-org/MiDaS/blob/master/LICENSE)|2022|[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/13cVDO6gYdQvbKimcfbgGOfuoQmrTbarU?usp=sharing) |

# Stable Diffusion

### [stable-diffusion-v1-5](https://drive.google.com/file/d/1dqYEdhSPi7y0Dgans-Fk7_ViNviUTUJj/view?usp=share_link)



| Google Drive Link  | Original Model |Original Project | License | Run on mac |Conversion Script |Year|

| ------------- | ------------- | ------------- | ------------- | ------------- | ------------- | ------------- | 

| [stable-diffusion-v1-5](https://drive.google.com/file/d/1dqYEdhSPi7y0Dgans-Fk7_ViNviUTUJj/view?usp=share_link) |[runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5)|[runwayml/stable-diffusion](https://github.com/runwayml/stable-diffusion)  |[Open RAIL M license](https://huggingface.co/runwayml/stable-diffusion-v1-5)|[godly-devotion/MochiDiffusion](https://github.com/godly-devotion/MochiDiffusion)|[godly-devotion/MochiDiffusion](https://github.com/godly-devotion/MochiDiffusion/wiki/How-to-convert-Stable-Diffusion-models-to-Core-ML#requirements) |2022|

### [pastel-mix](https://drive.google.com/file/d/1cp3VoF1R-as8_lScWGUoxl-BNVX3d7vb/view?usp=share_link)

Pastel Mix - a stylized latent diffusion model.This model is intended to produce high-quality, highly detailed anime style with just a few prompts.



| Google Drive Link  | Original Model | License | Run on mac |Conversion Script |Year|

| ------------- | ------------- | ------------- |  ------------- | ------------- | ------------- | 

| [pastelMixStylizedAnime_pastelMixPrunedFP16](https://drive.google.com/file/d/1cp3VoF1R-as8_lScWGUoxl-BNVX3d7vb/view?usp=share_link) |[andite/pastel-mix](https://huggingface.co/andite/pastel-mix)|[Fantasy.ai](https://huggingface.co/andite/pastel-mix)|[godly-devotion/MochiDiffusion](https://github.com/godly-devotion/MochiDiffusion)|[godly-devotion/MochiDiffusion](https://github.com/godly-devotion/MochiDiffusion/wiki/How-to-convert-Stable-Diffusion-models-to-Core-ML#requirements) |2023|

### [Orange Mix](https://drive.google.com/file/d/1ueU-RuZIsl3b3F7uu_gBa_SfAtGTzTI5/view?usp=share_link)



| Google Drive Link  | Original Model | License | Run on mac |Conversion Script |Year|

| ------------- | ------------- | ------------- |  ------------- | ------------- | ------------- | 

| [AOM3_orangemixs](https://drive.google.com/file/d/1ueU-RuZIsl3b3F7uu_gBa_SfAtGTzTI5/view?usp=share_link) |[WarriorMama777/OrangeMixs](https://huggingface.co/WarriorMama777/OrangeMixs)|[CreativeML OpenRAIL-M](https://huggingface.co/WarriorMama777/OrangeMixs)|[godly-devotion/MochiDiffusion](https://github.com/godly-devotion/MochiDiffusion)|[godly-devotion/MochiDiffusion](https://github.com/godly-devotion/MochiDiffusion/wiki/How-to-convert-Stable-Diffusion-models-to-Core-ML#requirements) |2023|

### [Counterfeit](https://drive.google.com/file/d/1Kt_8hnGUGnJAUnuergLki37GKnWjWOJp/view?usp=share_link)



| Google Drive Link  | Original Model | License | Run on mac |Conversion Script |Year|

| ------------- | ------------- | ------------- |  ------------- | ------------- | ------------- | 

| [Counterfeit-V2.5](https://drive.google.com/file/d/1Kt_8hnGUGnJAUnuergLki37GKnWjWOJp/view?usp=share_link) |[gsdf/Counterfeit-V2.5](https://huggingface.co/gsdf/Counterfeit-V2.5)|-|[godly-devotion/MochiDiffusion](https://github.com/godly-devotion/MochiDiffusion)|[godly-devotion/MochiDiffusion](https://github.com/godly-devotion/MochiDiffusion/wiki/How-to-convert-Stable-Diffusion-models-to-Core-ML#requirements) |2023|

### [anything-v4](https://drive.google.com/file/d/1yF55CGy4I3BKom_E70lLkU6N03nSvjDt/view?usp=share_link)



| Google Drive Link  | Original Model | License | Run on mac |Conversion Script |Year|

| ------------- | ------------- | ------------- |  ------------- | ------------- | ------------- | 

| [anything-v4.5](https://drive.google.com/file/d/1yF55CGy4I3BKom_E70lLkU6N03nSvjDt/view?usp=share_link) |[andite/anything-v4.0](https://huggingface.co/andite/anything-v4.0)|[Fantasy.ai](https://huggingface.co/andite/anything-v4.0)|[godly-devotion/MochiDiffusion](https://github.com/godly-devotion/MochiDiffusion)|[godly-devotion/MochiDiffusion](https://github.com/godly-devotion/MochiDiffusion/wiki/How-to-convert-Stable-Diffusion-models-to-Core-ML#requirements) |2023|

### [Openjourney](https://drive.google.com/file/d/1KIhSG7pHjgldg7r2mm1Yuwa85BceFLsk/view?usp=share_link)



| Google Drive Link  | Original Model | License | Run on mac |Conversion Script |Year|

| ------------- | ------------- | ------------- |  ------------- | ------------- | ------------- | 

| [Openjourney](https://drive.google.com/file/d/1KIhSG7pHjgldg7r2mm1Yuwa85BceFLsk/view?usp=share_link) |[prompthero/openjourney](https://huggingface.co/prompthero/openjourney)|-|[godly-devotion/MochiDiffusion](https://github.com/godly-devotion/MochiDiffusion)|[godly-devotion/MochiDiffusion](https://github.com/godly-devotion/MochiDiffusion/wiki/How-to-convert-Stable-Diffusion-models-to-Core-ML#requirements) |2023|

### [dreamlike-photoreal-2](https://drive.google.com/file/d/1D5RXYE52wyXPq6TdCHM8DIkP4dxHafwt/view?usp=share_link)



| Google Drive Link  | Original Model | License | Run on mac |Conversion Script |Year|

| ------------- | ------------- | ------------- |  ------------- | ------------- | ------------- | 

| [dreamlike-photoreal-2.0](https://drive.google.com/file/d/1D5RXYE52wyXPq6TdCHM8DIkP4dxHafwt/view?usp=share_link) |[dreamlike-art/dreamlike-photoreal-2.0](https://huggingface.co/dreamlike-art/dreamlike-photoreal-2.0)|[CreativeML OpenRAIL-M](https://huggingface.co/dreamlike-art/dreamlike-photoreal-2.0)|[godly-devotion/MochiDiffusion](https://github.com/godly-devotion/MochiDiffusion)|[godly-devotion/MochiDiffusion](https://github.com/godly-devotion/MochiDiffusion/wiki/How-to-convert-Stable-Diffusion-models-to-Core-ML#requirements) |2023|

## Models converted by someone other than me.

### [Stable Diffusion](https://github.com/apple/ml-stable-diffusion)

[apple/ml-stable-diffusion](https://github.com/apple/ml-stable-diffusion)

## How to use in a xcode project.

### Option 1,implement Vision request.

```swift:

import Vision

lazy var coreMLRequest:VNCoreMLRequest = {

   let model = try! VNCoreMLModel(for: modelname().model)

   let request = VNCoreMLRequest(model: model, completionHandler: self.coreMLCompletionHandler)

   return request

   }()

let handler = VNImageRequestHandler(ciImage: ciimage,options: [:])

   DispatchQueue.global(qos: .userInitiated).async {

   try? handler.perform([coreMLRequest])

}

```

If the model has Image type output:

```swift

let result = request?.results?.first as! VNPixelBufferObservation

let uiimage = UIImage(ciImage: CIImage(cvPixelBuffer: result.pixelBuffer))

```

Else the model has Multiarray type output:

For visualizing multiArray as image, Mr. Hollance’s “CoreML Helpers” are very convenient.

[CoreML Helpers](https://github.com/hollance/CoreMLHelpers)

[Converting from MultiArray to Image with CoreML Helpers.](https://medium.com/@rockyshikoku/converting-from-multiarray-to-image-with-coreml-helpers-59fdc34d80d8)

```swift:

func coreMLCompletionHandler（request：VNRequest？、error：Error？）{

   let = coreMLRequest.results？.first as！VNCoreMLFeatureValueObservation

   let multiArray = result.featureValue.multiArrayValue

   let cgimage = multiArray？.cgImage（min：-1、max：1、channel：nil）

```

### Option 2,Use [CoreGANContainer](https://github.com/john-rocky/CoreGANContainer). You can use models with dragging&dropping into the container project. 

# Make the model lighter

You can make the model size lighter with Quantization if you want.

https://coremltools.readme.io/docs/quantization

>The lower the number of bits, more the chances of degrading the model accuracy. The loss in accuracy varies with the model.

```python

import coremltools as ct

from coremltools.models.neural_network import quantization_utils

# load full precision model

model_fp32 = ct.models.MLModel('model.mlmodel')

model_fp16 = quantization_utils.quantize_weights(model_fp32, nbits=16)

# nbits can be 16(half size model), 8(1/4), 4(1/8), 2, 1

```

##### quantized sample (U2Net)

##### InputImage / nbits=32(original) / nbits=16 / nbits=8 / nbits=4

    

# Thanks

Cover image was taken from Ghibli free images. 

On YOLOv5 convertion, [dbsystel/yolov5-coreml-tools](https://github.com/dbsystel/yolov5-coreml-tools) give me the super inteligent convert script. 

And all of original projects

# Auther

Daisuke Majima

Freelance engineer. iOS/MachineLearning/AR

I can work on mobile ML projects and AR project.

Feel free to contact: [email protected]

[GitHub](https://github.com/john-rocky)

[Twitter](https://twitter.com/JackdeS11)

[Medium](https://rockyshikoku.medium.com/)