{"id":19672624,"url":"https://github.com/ttop32/arcaneanimegan","last_synced_at":"2026-03-01T03:03:25.982Z","repository":{"id":46098454,"uuid":"441358505","full_name":"ttop32/ArcaneAnimeGAN","owner":"ttop32","description":"AnimeGAN2 trained on Arcane","archived":false,"fork":false,"pushed_at":"2022-01-06T06:42:05.000Z","size":33850,"stargazers_count":25,"open_issues_count":0,"forks_count":3,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-04-29T01:42:15.326Z","etag":null,"topics":["alignment","anime","animegan","animegan2","animeganv2","arcanegan","blending","blur","face-alignment","fastai","fine-tuning","gan","generative-adversarial-network","image2image","pytorch","style-transfer","stylegan","stylegan3","torch","weight"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ttop32.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-12-24T03:46:19.000Z","updated_at":"2025-03-28T11:47:37.000Z","dependencies_parsed_at":"2022-08-12T12:40:34.029Z","dependency_job_id":null,"html_url":"https://github.com/ttop32/ArcaneAnimeGAN","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ttop32/ArcaneAnimeGAN","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ttop32%2FArcaneAnimeGAN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ttop32%2FArcaneAnimeGAN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ttop32%2FArcaneAnimeGAN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ttop32%2FArcaneAnimeGAN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ttop32","download_url":"https://codeload.github.com/ttop32/ArcaneAnimeGAN/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ttop32%2FArcaneAnimeGAN/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29959284,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-01T01:47:18.291Z","status":"online","status_checked_at":"2026-03-01T02:00:07.437Z","response_time":124,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["alignment","anime","animegan","animegan2","animeganv2","arcanegan","blending","blur","face-alignment","fastai","fine-tuning","gan","generative-adversarial-network","image2image","pytorch","style-transfer","stylegan","stylegan3","torch","weight"],"created_at":"2024-11-11T17:12:46.226Z","updated_at":"2026-03-01T03:03:20.913Z","avatar_url":"https://github.com/ttop32.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ArcaneAnimeGAN\n[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1sBnFG9XR0euphD1LLspZOD2hxfyBwooN?usp=sharing)  \nAnimeGAN2 trained on Arcane   \ntrying to follow bryandlee animegan2 training methodology   \n\n  \n# Result   \n![result](doc/result0.2.png)    \n\n# Training Workflow\n- Get video data\n- Split video into frames\n- Align frame image using face-alignment\n- Filter blurry image using opencv Laplacian\n- Zip image dataset for fit into styleGAN\n- Finetune FFHQ pretrained styleGAN using created zip dataset\n- Blend findtuned styleGAN weight and pretrained styleGAN weight \n- Create data pair using blended styleGAN model and pretrained model\n- Train animeGAN using paired data\n  \n# Change log\n- 0.2\n  - use anime-face-detector \n  - add color correction on data preprocessing\n  - add aug_transforms() on batch transform\n  - use l1_loss(vgg(g(x)), vgg(y)) and mse_loss(g(x), y) instead of vgg feature loss and gram matrix loss\n- 0.1\n  - first release\n# To Do\n- Use animegan vgg19[0,255] instead of vgg19_bn[0,1]\n- Add canny edge method to gaussigan blur\n- Background segmentation\n  \n# Required environment to run    \n```python\n!conda install pytorch torchvision cudatoolkit=11.1 -c pytorch -c nvidia -y\n!sudo apt install ffmpeg\n!pip install face-alignment\n!pip install --upgrade psutil\n!pip install kornia\n!pip install fastai==2.5.3\n!pip install opencv-python\n!git clone https://github.com/NVlabs/stylegan3.git\n\n!pip install openmim\n!mim install mmcv-full mmdet mmpose -y\n!pip install anime-face-detector --no-dependencies\n```\n  \n# Acknowledgement and References  \n- [AnimeGAN](https://github.com/TachibanaYoshino/AnimeGAN)  \n- [AnimeGANv2](https://github.com/TachibanaYoshino/AnimeGANv2)  \n- [animegan2-pytorch](https://github.com/bryandlee/animegan2-pytorch)  \n- [animegan2-pytorch-Face-Portrait-v1](https://github.com/bryandlee/animegan2-pytorch/issues/3)  \n- [pytorch-animeGAN](https://github.com/ptran1203/pytorch-animeGAN)  \n- [AnimeGANv2_pytorch](https://github.com/wan-h/AnimeGANv2_pytorch)  \n- [AnimeGAN_in_Pytorch](https://github.com/XuHangkun/AnimeGAN_in_Pytorch)  \n- [AnimeGAN-torch](https://github.com/MrVoid918/AnimeGAN-torch)  \n- [style_transfer_implementation](https://github.com/Snailpong/style_transfer_implementation)  \n- [Anime-Sketch-Coloring](https://github.com/pradeeplam/Anime-Sketch-Coloring-with-Swish-Gated-Residual-UNet)  \n- [CartoonGAN-Tensorflow](https://github.com/taki0112/CartoonGAN-Tensorflow)  \n- [cartoon-gan](https://github.com/FilipAndersson245/cartoon-gan)  \n- [pytorch-implementation-of-perceptual-losses](https://towardsdatascience.com/pytorch-implementation-of-perceptual-losses-for-real-time-style-transfer-8d608e2e9902)  \n- [Artistic-Style-Transfer](https://kyounju.tistory.com/3)  \n-   \n- [animegan2-pytorch-arcane](https://github.com/bryandlee/animegan2-pytorch/issues/17)  \n- [DeepStudio](https://github.com/bryandlee/DeepStudio)  \n- [ArcaneGAN](https://github.com/Sxela/ArcaneGAN)  \n- [stylegan3_blending](https://github.com/Sxela/stylegan3_blending)  \n- [toonify](https://github.com/justinpinkney/toonify)  \n- [BlendGAN](https://github.com/onion-liu/BlendGAN)  \n- [Cartoon-StyleGAN](https://github.com/happy-jihye/Cartoon-StyleGAN)  \n- [FFHQ-Alignment](https://github.com/happy-jihye/FFHQ-Alignment)  \n- [FFHQ-dataset](https://github.com/NVlabs/ffhq-dataset)\n- [face-alignment](https://github.com/1adrianb/face-alignment)  \n- [stylegan3](https://github.com/NVlabs/stylegan3)  \n- [FreezeD](https://github.com/sangwoomo/FreezeD)  \n- [Image-Blur-Detection](https://github.com/priyabagaria/Image-Blur-Detection)  \n- [Classifying_image_blur_nonblur](https://github.com/pranavAL/Classifying_image_blur_nonblur)\n- [arcane](https://www.netflix.com/kr/title/81435684)\n- [JoJoGAN](https://github.com/mchong6/JoJoGAN)\n- [anime-face-detector](https://github.com/hysts/anime-face-detector)\n- [color correction](https://github.com/luftj/MaRE/blob/4284fe2b3307ca407e87e3b0dbdaa3c1ef646731/simple_cb.py)\n- [White-box-Cartoonization](https://github.com/SystemErrorWang/White-box-Cartoonization)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fttop32%2Farcaneanimegan","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fttop32%2Farcaneanimegan","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fttop32%2Farcaneanimegan/lists"}