## Personal Projects
### Repo - [Anime Face Detector](https://huggingface.co/spaces/hysts/anime-face-detector) - https://github.com/hysts/anime-face-detector ### Having Fun with the TADNE (This Anime Does Not Exist) model - [TADNE](https://huggingface.co/spaces/hysts/TADNE) - https://thisanimedoesnotexist.ai/ - [TADNE Image Viewer](https://huggingface.co/spaces/hysts/TADNE-image-viewer) - [TADNE Image Selector](https://huggingface.co/spaces/hysts/TADNE-image-selector) - [TADNE Interpolation](https://huggingface.co/spaces/hysts/TADNE-interpolation) - [TADNE Image Search with DeepDanbooru](https://huggingface.co/spaces/hysts/TADNE-image-search-with-DeepDanbooru) ### StyleGAN3 Experiments - [StyleGAN3 Anime Face Generation (exp-001)](https://huggingface.co/spaces/hysts/stylegan3-anime-face-exp001) - [StyleGAN3 Anime Face Generation (exp-002)](https://huggingface.co/spaces/hysts/stylegan3-anime-face-exp002) - [StyleGAN3 Food101](https://huggingface.co/spaces/hysts/stylegan3-food101) ### Diffusers Experiments - [Anime Face Generation with Diffusers](https://huggingface.co/spaces/hysts/diffusers-anime-faces)
### Conference Papers - [CVPR 2022](https://huggingface.co/spaces/hysts/CVPR2022_papers) - https://cvpr2022.thecvf.com/ - https://openaccess.thecvf.com/CVPR2022 - https://github.com/amusi/CVPR2022-Papers-with-Code - [ICML 2022](https://huggingface.co/spaces/hysts/ICML2022_papers) - https://icml.cc/Conferences/2022/ - https://proceedings.mlr.press/v162/ - [NAACL 2022](https://huggingface.co/spaces/NAACL2022/papers) - https://2022.naacl.org/
### Object Detection - [MaskCut](https://huggingface.co/spaces/hysts/MaskCut) - https://github.com/facebookresearch/CutLER - [CutLER](https://huggingface.co/spaces/hysts/CutLER) - https://github.com/facebookresearch/CutLER - [mmdetection](https://huggingface.co/spaces/hysts/mmdetection) - https://github.com/open-mmlab/mmdetection - [CBNetV2](https://huggingface.co/spaces/Gradio-Blocks/CBNetV2) - https://github.com/VDIGPKU/CBNetV2 - http://arxiv.org/abs/2107.00420 ### Human Pose Estimation - [ViTPose](https://huggingface.co/spaces/Gradio-Blocks/ViTPose), [ViTPose (for video)](https://huggingface.co/spaces/hysts/ViTPose_video) - https://github.com/ViTAE-Transformer/ViTPose - https://arxiv.org/abs/2204.12484 ### Image Captioning - [BLIP-2](https://huggingface.co/spaces/hysts/BLIP2-with-transformers) - https://arxiv.org/abs/2301.12597 - https://github.com/salesforce/LAVIS/tree/main/projects/blip2 ### Image Restoration - [DDNM-HQ](https://huggingface.co/spaces/hysts/DDNM-HQ) - https://github.com/wyhuai/DDNM/ - https://arxiv.org/abs/2303.00354 - https://arxiv.org/abs/2212.00490
### GAN (General) - [StyleGAN-Human](https://huggingface.co/spaces/hysts/StyleGAN-Human), [StyleGAN-Human (interpolation)](https://huggingface.co/spaces/hysts/StyleGAN-Human-Interpolation), [StyleGAN-Human (Blocks ver.)](https://huggingface.co/spaces/Gradio-Blocks/StyleGAN-Human) - https://github.com/stylegan-human/StyleGAN-Human - [Self-Distilled StyleGAN](https://huggingface.co/spaces/hysts/Self-Distilled-StyleGAN) - https://github.com/self-distilled-stylegan/self-distilled-internet-photos - https://arxiv.org/abs/2202.12211 - [StyleGAN-XL](https://huggingface.co/spaces/hysts/StyleGAN-XL) - https://github.com/autonomousvision/stylegan_xl - https://arxiv.org/abs/2202.00273 - [StyleSwin](https://huggingface.co/spaces/hysts/StyleSwin) - https://github.com/microsoft/StyleSwin - https://arxiv.org/abs/2112.10762 - [Projected GAN](https://huggingface.co/spaces/hysts/projected_gan) - https://github.com/autonomousvision/projected_gan - https://arxiv.org/abs/2111.01007 - [StyleGAN3](https://huggingface.co/spaces/hysts/StyleGAN3) - https://github.com/NVlabs/stylegan3 - https://arxiv.org/abs/2106.12423 - [MobileStyleGAN](https://huggingface.co/spaces/hysts/MobileStyleGAN) - https://github.com/bes-dev/MobileStyleGAN.pytorch - https://arxiv.org/abs/2104.04767 - [StyleGAN2](https://huggingface.co/spaces/hysts/StyleGAN2) - https://github.com/NVlabs/stylegan3 - https://arxiv.org/abs/1912.04958 ### Editing, Controlling etc. - [Text2Human](https://huggingface.co/spaces/hysts/Text2Human) - https://github.com/yumingj/Text2Human - https://arxiv.org/abs/2205.15996 - [DualStyleGAN](https://huggingface.co/spaces/hysts/DualStyleGAN), [DualStyleGAN (Blocks ver.)](https://huggingface.co/spaces/Gradio-Blocks/DualStyleGAN) - https://github.com/williamyang1991/DualStyleGAN - https://arxiv.org/abs/2203.13248 - [HairCLIP](https://huggingface.co/spaces/Gradio-Blocks/HairCLIP) - https://github.com/wty-ustc/HairCLIP - https://arxiv.org/abs/2112.05142 - [GAN-Control](https://huggingface.co/spaces/hysts/gan-control) - https://github.com/amazon-research/gan-control - https://arxiv.org/abs/2101.02477 ### Text-to-Image Generation - [UniDiffuser](https://huggingface.co/spaces/thu-ml/unidiffuser) - https://arxiv.org/abs/2303.06555 - https://github.com/thu-ml/unidiffuser - [ControlNet](https://huggingface.co/spaces/hysts/ControlNet), [ControlNet-with-other-models](https://huggingface.co/spaces/hysts/ControlNet-with-other-models) - https://arxiv.org/abs/2302.05543 - https://github.com/lllyasviel/ControlNet - [Plug-and-Play diffusion features](https://huggingface.co/spaces/hysts/PnP-diffusion-features) - https://arxiv.org/abs/2211.12572 - https://github.com/MichalGeyer/plug-and-play - [TEXTure](https://huggingface.co/spaces/TEXTurePaper/TEXTure) - https://github.com/TEXTurePaper/TEXTurePaper - [Attend-and-Excite](https://huggingface.co/spaces/AttendAndExcite/Attend-and-Excite) - https://github.com/AttendAndExcite/Attend-and-Excite - https://arxiv.org/abs/2301.13826 - [LoRA DreamBooth Training UI](https://huggingface.co/spaces/lora-library/LoRA-DreamBooth-Training-UI) - https://github.com/huggingface/diffusers/tree/main/examples/dreambooth - [LoRA + SD training](https://huggingface.co/spaces/hysts/LoRA-SD-training) - https://github.com/cloneofsimo/lora - [Multiresolution Textual Inversion](https://huggingface.co/spaces/hysts/multiresolution-textual-inversion) - https://arxiv.org/abs/2211.17115 - https://github.com/giannisdaras/multires_textual_inversion - [CogView2](https://huggingface.co/spaces/THUDM/CogView2) - https://github.com/THUDM/CogView2 - https://arxiv.org/abs/2204.14217 ### Text-to-Video Generation - [Tune-A-Video Training UI](https://huggingface.co/spaces/Tune-A-Video-library/Tune-A-Video-Training-UI) - https://github.com/showlab/Tune-A-Video - https://arxiv.org/abs/2212.11565 - [CogVideo](https://huggingface.co/spaces/THUDM/CogVideo) - https://github.com/THUDM/CogVideo - https://arxiv.org/abs/2205.15868
### Face Detection/Alignment - [insightface SCRFD](https://huggingface.co/spaces/hysts/insightface-SCRFD) - https://github.com/deepinsight/insightface/tree/master/detection/scrfd - https://arxiv.org/abs/2105.04714 - [face-alignment](https://huggingface.co/spaces/hysts/1adrianb-face-alignment) - https://github.com/1adrianb/face-alignment - https://arxiv.org/abs/1703.07332 - [ibug-group/face_detection](https://huggingface.co/spaces/hysts/ibug-face_detection) - https://github.com/ibug-group/face_detection - [ibug-group/face_alignment](https://huggingface.co/spaces/hysts/ibug-face_alignment) - https://github.com/ibug-group/face_alignment - [atksh/onnx-facial-lmk-detector](https://huggingface.co/spaces/hysts/atksh-onnx-facial-lmk-detector) - https://github.com/atksh/onnx-facial-lmk-detector ### Face Detection/Alignment (Selfie) - [MediaPipe Face Mesh](https://huggingface.co/spaces/hysts/mediapipe-face-mesh) - https://github.com/google/mediapipe - https://arxiv.org/abs/1907.06724 - [MediaPipe Face Detection](https://huggingface.co/spaces/hysts/mediapipe-face-detection) - https://github.com/google/mediapipe - https://arxiv.org/abs/1907.05047 ### Face Parsing - [hhj1897/face_parsing](https://huggingface.co/spaces/hysts/ibug-face_parsing) - https://github.com/hhj1897/face_parsing - https://arxiv.org/abs/2102.02717 - [CelebAMask-HQ](https://huggingface.co/spaces/hysts/CelebAMask-HQ-Face-Parsing) - https://github.com/switchablenorms/CelebAMask-HQ - https://arxiv.org/abs/1907.11922 ### Head Pose Estimation - [Hopenet](https://huggingface.co/spaces/hysts/Hopenet) - https://github.com/natanielruiz/deep-head-pose - https://arxiv.org/abs/1710.00925 ### Age Estimation - [FP-Age](https://huggingface.co/spaces/hysts/ibug-fpage) - https://github.com/ibug-group/fpage - https://arxiv.org/abs/2106.11145 - [yu4u/age-estimation-pytorch](https://huggingface.co/spaces/hysts/age-estimation-APPA-REAL) - https://github.com/yu4u/age-estimation-pytorch ### Emotion Recognition - [ibug-group/emotion_recognition](https://huggingface.co/spaces/hysts/ibug-emotion_recognition) - https://github.com/ibug-group/emotion_recognition ### Person Detection - [Person Detection (insightface, SCRFD)](https://huggingface.co/spaces/hysts/insightface-person-detection) - https://github.com/deepinsight/insightface/tree/master/examples/person_detection - https://arxiv.org/abs/2105.04714 ### Human Pose Estimation - [MediaPipe Pose Estimation](https://huggingface.co/spaces/hysts/mediapipe-pose-estimation) - https://github.com/google/mediapipe - https://arxiv.org/abs/2006.10204
### Illustration Tagger - [RF5/danbooru-pretrained](https://huggingface.co/spaces/hysts/danbooru-pretrained) - https://github.com/RF5/danbooru-pretrained - [KichangKim/DeepDanbooru](https://huggingface.co/spaces/hysts/DeepDanbooru) - https://github.com/KichangKim/DeepDanbooru - [ShuhongChen/bizarre-pose-estimator (tagger)](https://huggingface.co/spaces/hysts/bizarre-pose-estimator-tagger) - https://github.com/ShuhongChen/bizarre-pose-estimator - https://arxiv.org/abs/2108.01819 ### Anime Face Detection - [nagadomi/lbpcascade_animeface](https://huggingface.co/spaces/hysts/lbpcascade_animeface) - https://github.com/nagadomi/lbpcascade_animeface - [zymk9/yolov5_anime](https://huggingface.co/spaces/hysts/yolov5_anime) - https://github.com/zymk9/yolov5_anime ### Anime Face Alignment - [kanosawa/anime_face_landmark_detection](https://huggingface.co/spaces/hysts/anime_face_landmark_detection) - https://github.com/kanosawa/anime_face_landmark_detection ### Anime Character Segmentation - [zymk9/Yet-Another-Anime-Segmenter](https://huggingface.co/spaces/hysts/Yet-Another-Anime-Segmenter) - https://github.com/zymk9/Yet-Another-Anime-Segmenter - [ShuhongChen/bizarre-pose-estimator (segmenter)](https://huggingface.co/spaces/hysts/bizarre-pose-estimator-segmenter) - https://github.com/ShuhongChen/bizarre-pose-estimator - https://arxiv.org/abs/2108.01819 ### Sketch - [AnimeGANv3 PortraitSketch](https://huggingface.co/spaces/hysts/AnimeGANv3_PortraitSketch) - https://github.com/TachibanaYoshino/AnimeGANv3 - https://colab.research.google.com/drive/1XYNWwM8Xq-U7KaTOqNap6A-Yq1f-V-FB?usp=sharing - [Mukosame/Anime2Sketch](https://huggingface.co/spaces/hysts/Anime2Sketch) - https://github.com/Mukosame/Anime2Sketch - https://arxiv.org/abs/2104.05703 - [MangaLineExtraction_PyTorch](https://huggingface.co/spaces/hysts/MangaLineExtraction_PyTorch) - https://github.com/ljsabc/MangaLineExtraction_PyTorch - https://www.cse.cuhk.edu.hk/~ttwong/papers/linelearn/linelearn.html ### OCR - [kha-white/manga-ocr](https://huggingface.co/spaces/hysts/Manga-OCR) - https://github.com/kha-white/manga-ocr