list.yaml

facebook/seamless_m4t:
  created: "2023-08-21T11:19:39.000Z"
  github:
    - https://github.com/facebookresearch/seamless_communication
  tags:
    - audio
    - speech-to-speech translation
    - speech-to-text translation
    - text-to-speech translation
    - text-to-text translation
    - Automatic Speech Recognition
hysts/daily-papers:
  created: "2023-08-17T03:23:33.000Z"
  tags:
    - list of papers
hysts/SD-XL:
  arxiv:
    - https://arxiv.org/abs/2307.01952
  created: "2023-07-27T05:10:31.000Z"
  github:
    - https://github.com/stability-ai/generative-models
  tags:
    - diffusion model
    - text to image
huggingface-projects/llama-2-7b-chat:
  arxiv:
    - https://arxiv.org/abs/2307.09288
  created: "2023-07-19T03:33:27.000Z"
  github:
    - https://github.com/facebookresearch/llama
  tags:
    - chatbot
    - LLM
    - Llama 2
hysts/Kandinsky-2-1:
  created: "2023-07-14T12:34:56.000Z"
  tags:
    - diffusion model
    - text to image
hysts/Kandinsky-2-2:
  created: "2023-07-14T09:48:26.000Z"
  tags:
    - diffusion model
    - text to image
hysts/zeroscope-v2:
  created: "2023-06-27T02:57:53.000Z"
  tags:
    - diffusion model
    - text to video
ICML2023/ICML2023_papers:
  created: "2023-06-15T17:16:16.000Z"
  tags:
    - list of papers
hysts/Shap-E:
  arxiv:
    - https://arxiv.org/abs/2305.02463
  created: "2023-05-05T07:40:18.000Z"
  github:
    - https://github.com/openai/shap-e
  tags:
    - diffusion model
    - text to 3D
    - image to 3D
hysts/ControlNet-v1-1:
  arxiv:
    - https://arxiv.org/abs/2302.05543
  created: "2023-04-15T01:26:54.000Z"
  github:
    - https://github.com/lllyasviel/ControlNet
    - https://github.com/lllyasviel/ControlNet-v1-1-nightly
  tags:
    - diffusion model
    - text2image
    - image2image
DeepFloyd/IF:
  created: "2023-03-30T01:36:56.000Z"
  github:
    - https://github.com/deep-floyd/IF
  tags:
    - diffusion model
    - text2image
damo-vilab/modelscope-text-to-video-synthesis:
  arxiv:
    - https://arxiv.org/abs/2303.08320
  created: "2023-03-19T04:30:43.000Z"
  github:
    - https://github.com/modelscope/modelscope
  tags:
    - diffusion model
    - text2video
thu-ml/unidiffuser:
  arxiv:
    - https://arxiv.org/abs/2303.06555
  created: "2023-03-14T05:06:57.000Z"
  github:
    - https://github.com/thu-ml/unidiffuser
  tags:
    - diffusion model
    - text2image
    - image2image
    - image captioning
ELITE-library/ELITE:
  arxiv:
    - https://arxiv.org/abs/2302.13848
  created: "2023-03-09T03:28:49.000Z"
  github:
    - https://github.com/csyxwei/ELITE
  tags:
    - diffusion model
    - text2image
hysts/cv_diffusion_text-to-image-synthesis_tiny:
  created: "2023-03-08T05:44:53.000Z"
  tags:
    - diffusion model
    - text2image
hysts/DDNM-HQ:
  arxiv:
    - https://arxiv.org/abs/2303.00354
    - https://arxiv.org/abs/2212.00490
  created: "2023-03-02T03:35:13.000Z"
  github:
    - https://github.com/wyhuai/DDNM/tree/main/hq_demo
  tags:
    - diffusion model
    - super resolution
hysts/ControlNet-with-Anything-v4:
  arxiv:
    - https://arxiv.org/abs/2302.05543
  created: "2023-02-16T05:05:27.000Z"
  github:
    - https://github.com/lllyasviel/ControlNet
  tags:
    - diffusion model
    - text2image
    - image2image
hysts/ControlNet:
  arxiv:
    - https://arxiv.org/abs/2302.05543
  created: "2023-02-14T01:03:00.000Z"
  github:
    - https://github.com/lllyasviel/ControlNet
  tags:
    - diffusion model
    - text2image
    - image2image
hysts/PnP-diffusion-features:
  arxiv:
    - https://arxiv.org/abs/2211.12572
  created: "2023-02-13T06:20:32.000Z"
  github:
    - https://github.com/MichalGeyer/plug-and-play
  tags:
    - diffusion model
    - image2image
hysts/BLIP2-with-transformers:
  arxiv:
    - https://arxiv.org/abs/2301.12597
  created: "2023-02-10T09:45:07.000Z"
  github:
    - https://github.com/salesforce/LAVIS/tree/main/projects/blip2
  tags:
    - image captioning
    - VQA
Tune-A-Video-library/Tune-A-Video-inference:
  arxiv:
    - https://arxiv.org/abs/2212.11565
  created: "2023-02-09T02:39:44.000Z"
  github:
    - https://github.com/showlab/Tune-A-Video
  tags:
    - diffusion model
    - text2video
    - video2video
TEXTurePaper/TEXTure:
  arxiv:
    - https://arxiv.org/abs/2302.01721
  created: "2023-02-06T09:16:46.000Z"
  github:
    - https://github.com/TEXTurePaper/TEXTurePaper
  tags:
    - diffusion model
    - text-guided
    - texture
    - 3D
AttendAndExcite/Attend-and-Excite:
  arxiv:
    - https://arxiv.org/abs/2301.13826
  created: "2023-02-01T06:18:56.000Z"
  github:
    - https://github.com/AttendAndExcite/Attend-and-Excite
  tags:
    - diffusion model
    - text2image
Tune-A-Video-library/Tune-A-Video-Training-UI:
  arxiv:
    - https://arxiv.org/abs/2212.11565
  created: "2023-01-30T08:10:09.000Z"
  github:
    - https://github.com/showlab/Tune-A-Video
  tags:
    - diffusion model
    - text2video
    - video2video
facebook/CutLER:
  arxiv:
    - https://arxiv.org/abs/2301.11320
  created: "2023-01-28T11:11:22.000Z"
  github:
    - https://github.com/facebookresearch/CutLER
  tags:
    - object detection
    - segmentation
    - unsupervised
facebook/MaskCut:
  arxiv:
    - https://arxiv.org/abs/2301.11320
  created: "2023-01-28T04:37:53.000Z"
  github:
    - https://github.com/facebookresearch/CutLER
  tags:
    - object detection
    - segmentation
    - unsupervised
lora-library/LoRA-DreamBooth-Training-UI:
  created: "2023-01-20T05:11:08.000Z"
  github:
    - https://github.com/huggingface/diffusers/tree/main/examples/dreambooth
  tags:
    - LoRA
    - DreamBooth
    - diffusion model
    - text2image
hysts/LoRA-SD-training:
  created: "2022-12-11T07:01:37.000Z"
  github:
    - https://github.com/cloneofsimo/lora
  tags:
    - LoRA
    - DreamBooth
    - diffusion model
    - text2image
hysts/multiresolution-textual-inversion:
  arxiv:
    - https://arxiv.org/abs/2211.17115
  created: "2022-12-03T09:13:05.000Z"
  github:
    - https://github.com/giannisdaras/multires_textual_inversion
  tags:
    - diffusion model
    - text2image
hysts/diffusers-anime-faces:
  created: "2022-08-12T10:03:37.000Z"
  tags:
    - diffusion model
    - anime
    - illustration
    - personal project
THUDM/CogVideo:
  arxiv:
    - https://arxiv.org/abs/2205.15868
  created: "2022-07-18T09:06:22.000Z"
  github:
    - https://github.com/THUDM/CogVideo
  tags:
    - text2video
hysts/AnimeGANv3_PortraitSketch:
  created: "2022-07-13T17:51:20.000Z"
  github:
    - https://github.com/TachibanaYoshino/AnimeGANv3
  tags:
    - sketch
hysts/ICML2022_papers:
  created: "2022-07-13T11:47:41.000Z"
  tags:
    - list of papers
hysts/CVPR2022_papers:
  created: "2022-07-11T12:16:32.000Z"
  tags:
    - list of papers
NAACL2022/papers:
  created: "2022-07-10T21:40:05.000Z"
  tags:
    - list of papers
THUDM/CogView2:
  arxiv:
    - https://arxiv.org/abs/2204.14217
  created: "2022-06-20T16:06:52.000Z"
  github:
    - https://github.com/THUDM/CogView2
  tags:
    - text2image
hysts/MangaLineExtraction_PyTorch:
  created: "2022-06-10T23:12:02.000Z"
  github:
    - https://github.com/ljsabc/MangaLineExtraction_PyTorch
  tags:
    - anime
    - illustration
    - sketch
hysts/ViTPose_video:
  arxiv:
    - https://arxiv.org/abs/2204.12484
  created: "2022-06-08T10:38:50.000Z"
  github:
    - https://github.com/ViTAE-Transformer/ViTPose
  tags:
    - human pose estimation
hysts/Text2Human:
  arxiv:
    - https://arxiv.org/abs/2205.15996
  created: "2022-06-04T08:12:18.000Z"
  github:
    - https://github.com/yumingj/Text2Human
  tags:
    - text2image
Gradio-Blocks/ViTPose:
  arxiv:
    - https://arxiv.org/abs/2204.12484
  created: "2022-05-29T06:25:28.000Z"
  github:
    - https://github.com/ViTAE-Transformer/ViTPose
  tags:
    - human pose estimation
Gradio-Blocks/CBNetV2:
  arxiv:
    - http://arxiv.org/abs/2107.00420
  created: "2022-05-29T03:51:21.000Z"
  github:
    - https://github.com/VDIGPKU/CBNetV2
  tags:
    - image classification
hysts/mmdetection:
  created: "2022-05-29T02:11:52.000Z"
  github:
    - https://github.com/open-mmlab/mmdetection
  tags:
    - object detection
    - instance segmentation
    - panoptic segmentation
    - segmentation
Gradio-Blocks/HairCLIP:
  arxiv:
    - https://arxiv.org/abs/2112.05142
  created: "2022-05-26T21:38:44.000Z"
  github:
    - https://github.com/wty-ustc/HairCLIP
  tags:
    - GAN
    - image editing
    - face
Gradio-Blocks/DualStyleGAN:
  arxiv:
    - https://arxiv.org/abs/2203.13248
  created: "2022-05-20T22:17:37.000Z"
  github:
    - https://github.com/williamyang1991/DualStyleGAN
  tags:
    - GAN
    - image editing
    - face
Gradio-Blocks/StyleGAN-Human:
  arxiv:
    - https://arxiv.org/abs/2204.11823
  created: "2022-05-20T13:19:56.000Z"
  github:
    - https://github.com/stylegan-human/StyleGAN-Human
  tags:
    - GAN
hysts/StyleGAN-Human-Interpolation:
  arxiv:
    - https://arxiv.org/abs/2204.11823
  created: "2022-04-22T09:48:26.000Z"
  github:
    - https://github.com/stylegan-human/StyleGAN-Human
  tags:
    - GAN
hysts/StyleGAN-Human:
  arxiv:
    - https://arxiv.org/abs/2204.11823
  created: "2022-04-22T08:28:33.000Z"
  github:
    - https://github.com/stylegan-human/StyleGAN-Human
  tags:
    - GAN
hysts/gan-control:
  arxiv:
    - https://arxiv.org/abs/2101.02477
  created: "2022-04-18T18:53:22.000Z"
  github:
    - https://github.com/amazon-research/gan-control
  tags:
    - GAN
hysts/Manga-OCR:
  created: "2022-04-18T17:27:04.000Z"
  github:
    - https://github.com/kha-white/manga-ocr
  tags:
    - anime
    - illustration
    - OCR
hysts/atksh-onnx-facial-lmk-detector:
  created: "2022-04-18T15:59:06.000Z"
  github:
    - https://github.com/atksh/onnx-facial-lmk-detector
  tags:
    - face
    - face detection
    - face landmark detection
hysts/Hopenet:
  arxiv:
    - https://arxiv.org/abs/1710.00925
  created: "2022-04-15T20:03:00.000Z"
  github:
    - https://github.com/natanielruiz/deep-head-pose
  tags:
    - face
    - head pose estimation
hysts/mediapipe-pose-estimation:
  arxiv:
    - https://arxiv.org/abs/2006.10204
  created: "2022-04-15T19:57:59.000Z"
  github:
    - https://github.com/google/mediapipe
  tags:
    - mediapipe
    - human pose estimation
hysts/mediapipe-face-detection:
  arxiv:
    - https://arxiv.org/abs/1907.05047
  created: "2022-04-15T19:56:19.000Z"
  github:
    - https://github.com/google/mediapipe
  tags:
    - mediapipe
    - face
    - face detection
hysts/mediapipe-face-mesh:
  arxiv:
    - https://arxiv.org/abs/1907.06724
  created: "2022-04-15T19:53:57.000Z"
  github:
    - https://github.com/google/mediapipe
  tags:
    - mediapipe
    - face
    - face landmark detection
hysts/Anime2Sketch:
  arxiv:
    - https://arxiv.org/abs/2104.05703
  created: "2022-04-15T16:10:50.000Z"
  github:
    - https://github.com/Mukosame/Anime2Sketch
  tags:
    - anime
    - illustration
    - sketch
hysts/TADNE-image-search-with-DeepDanbooru:
  created: "2022-04-14T22:00:57.000Z"
  tags:
    - anime
    - illustration
    - TADNE
hysts/TADNE-image-selector:
  created: "2022-04-14T18:09:44.000Z"
  tags:
    - anime
    - illustration
    - TADNE
hysts/TADNE-image-viewer:
  created: "2022-04-14T15:06:35.000Z"
  tags:
    - anime
    - illustration
    - TADNE
hysts/TADNE-interpolation:
  created: "2022-04-10T12:05:21.000Z"
  tags:
    - anime
    - illustration
    - TADNE
hysts/TADNE:
  created: "2022-04-10T04:54:39.000Z"
  tags:
    - anime
    - illustration
    - TADNE
hysts/ibug-emotion_recognition:
  created: "2022-04-09T17:20:11.000Z"
  github:
    - https://github.com/ibug-group/emotion_recognition
  tags:
    - face
    - emotion recognition
hysts/ibug-face_alignment:
  created: "2022-04-09T17:18:40.000Z"
  github:
    - https://github.com/ibug-group/face_alignment
  tags:
    - face
    - face landmark detection
hysts/ibug-fpage:
  arxiv:
    - https://arxiv.org/abs/2106.11145
  created: "2022-04-09T16:04:16.000Z"
  github:
    - https://github.com/ibug-group/fpage
  tags:
    - face
    - age estimation
hysts/ibug-face_parsing:
  arxiv:
    - https://arxiv.org/abs/2102.02717
  created: "2022-04-09T13:09:31.000Z"
  github:
    - https://github.com/hhj1897/face_parsing
  tags:
    - face
    - face parsing
    - segmentation
hysts/ibug-face_detection:
  created: "2022-04-09T12:26:23.000Z"
  github:
    - https://github.com/ibug-group/face_detection
  tags:
    - face
    - face detection
hysts/insightface-SCRFD:
  arxiv:
    - https://arxiv.org/abs/2105.04714
  created: "2022-04-06T12:07:02.000Z"
  github:
    - https://github.com/deepinsight/insightface/tree/master/detection/scrfd
  tags:
    - face
    - face detection
hysts/insightface-person-detection:
  arxiv:
    - https://arxiv.org/abs/2105.04714
  created: "2022-04-06T08:39:44.000Z"
  github:
    - https://github.com/deepinsight/insightface/tree/master/examples/person_detection
  tags:
    - person detection
hysts/CelebAMask-HQ-Face-Parsing:
  arxiv:
    - https://arxiv.org/abs/1907.11922
  created: "2022-04-06T02:56:32.000Z"
  github:
    - https://github.com/switchablenorms/CelebAMask-HQ
  tags:
    - face
    - face parsing
    - segmentation
hysts/MobileStyleGAN:
  arxiv:
    - https://arxiv.org/abs/2104.04767
  created: "2022-04-05T09:23:01.000Z"
  github:
    - https://github.com/bes-dev/MobileStyleGAN.pytorch
  tags:
    - GAN
hysts/Self-Distilled-StyleGAN:
  arxiv:
    - https://arxiv.org/abs/2202.12211
  created: "2022-04-05T02:40:27.000Z"
  github:
    - https://github.com/self-distilled-stylegan/self-distilled-internet-photos
  tags:
    - GAN
hysts/StyleGAN2:
  arxiv:
    - https://arxiv.org/abs/1912.04958
  created: "2022-04-03T19:53:52.000Z"
  github:
    - https://github.com/NVlabs/stylegan3
  tags:
    - GAN
hysts/projected_gan:
  arxiv:
    - https://arxiv.org/abs/2111.01007
  created: "2022-04-03T17:28:35.000Z"
  github:
    - https://github.com/autonomousvision/projected_gan
  tags:
    - GAN
hysts/StyleGAN3:
  arxiv:
    - https://arxiv.org/abs/2106.12423
  created: "2022-04-03T15:56:35.000Z"
  github:
    - https://github.com/NVlabs/stylegan3
  tags:
    - GAN
hysts/StyleGAN-XL:
  arxiv:
    - https://arxiv.org/abs/2202.00273
  created: "2022-03-31T19:20:05.000Z"
  github:
    - https://github.com/autonomousvision/stylegan_xl
  tags:
    - GAN
hysts/1adrianb-face-alignment:
  arxiv:
    - https://arxiv.org/abs/1703.07332
  created: "2022-03-28T11:33:31.000Z"
  github:
    - https://github.com/1adrianb/face-alignment
  tags:
    - face
    - face detection
    - face landmark detection
hysts/DualStyleGAN:
  arxiv:
    - https://arxiv.org/abs/2203.13248
  created: "2022-03-23T20:42:59.000Z"
  github:
    - https://github.com/williamyang1991/DualStyleGAN
  tags:
    - GAN
hysts/StyleSwin:
  arxiv:
    - https://arxiv.org/abs/2112.10762
  created: "2022-03-15T14:27:48.000Z"
  github:
    - https://github.com/microsoft/StyleSwin
  tags:
    - GAN
hysts/age-estimation-APPA-REAL:
  created: "2022-02-28T00:45:11.000Z"
  github:
    - https://github.com/yu4u/age-estimation-pytorch
  tags:
    - face
    - age estimation
hysts/anime_face_landmark_detection:
  created: "2022-01-24T09:09:55.000Z"
  github:
    - https://github.com/kanosawa/anime_face_landmark_detection
  tags:
    - anime
    - illustration
    - anime face landmark detection
hysts/lbpcascade_animeface:
  created: "2022-01-24T08:24:09.000Z"
  github:
    - https://github.com/nagadomi/lbpcascade_animeface
  tags:
    - anime
    - illustration
    - anime face detection
hysts/yolov5_anime:
  created: "2022-01-24T05:55:41.000Z"
  github:
    - https://github.com/zymk9/yolov5_anime
  tags:
    - anime
    - illustration
    - anime face detection
hysts/bizarre-pose-estimator-segmenter:
  arxiv:
    - https://arxiv.org/abs/2108.01819
  created: "2022-01-24T03:14:52.000Z"
  github:
    - https://github.com/ShuhongChen/bizarre-pose-estimator
  tags:
    - anime
    - illustration
    - anime character segmentation
hysts/Yet-Another-Anime-Segmenter:
  created: "2022-01-24T00:01:55.000Z"
  github:
    - https://github.com/zymk9/Yet-Another-Anime-Segmenter
  tags:
    - anime
    - illustration
    - anime character segmentation
hysts/bizarre-pose-estimator-tagger:
  arxiv:
    - https://arxiv.org/abs/2108.01819
  created: "2022-01-23T13:26:52.000Z"
  github:
    - https://github.com/ShuhongChen/bizarre-pose-estimator
  tags:
    - anime
    - illustration
    - anime label prediction
hysts/DeepDanbooru:
  created: "2022-01-23T12:04:20.000Z"
  github:
    - https://github.com/KichangKim/DeepDanbooru
  tags:
    - anime
    - illustration
    - anime label prediction
    - Danbooru
hysts/danbooru-pretrained:
  created: "2022-01-23T10:46:30.000Z"
  github:
    - https://github.com/RF5/danbooru-pretrained
  tags:
    - anime
    - illustration
    - anime label prediction
    - Danbooru
hysts/stylegan3-anime-face-exp002:
  created: "2021-12-02T19:33:20.000Z"
  tags:
    - GAN
    - personal project
hysts/stylegan3-food101:
  created: "2021-11-22T04:05:46.000Z"
  tags:
    - GAN
    - personal project
hysts/stylegan3-anime-face-exp001:
  created: "2021-11-22T02:10:56.000Z"
  tags:
    - GAN
    - personal project
hysts/anime-face-detector:
  created: "2021-11-15T02:15:45.000Z"
  github:
    - https://github.com/hysts/anime-face-detector
  tags:
    - anime
    - illustration
    - anime face detection
    - anime face landmark detection
    - personal project