Pinned Repositories
Anime2Sketch
A sketch extractor for anime/illustration.
animegan2-pytorch
PyTorch implementation of AnimeGANv2
CLIP
Contrastive Language-Image Pretraining
FaceMesh
Cross-platform, customizable ML solutions for live and streaming media.
gradio
Create UIs for prototyping your machine learning model in 3 minutes
JoJoGAN
Official PyTorch repo for JoJoGAN: One Shot Face Stylization
lambda-diffusers
PaddleHub
Awesome pre-trained models toolkit based on PaddlePaddle.(300+ models including Image, Text, Audio and Video with Easy Inference & Serving deployment)
PaintTransformer
PyTorch implementation of paper: Paint Transformer: Feed Forward Neural Painting with Stroke Prediction, ICCV 2021.
VQGAN-CLIP
AK391's Repositories
AK391/JoJoGAN
Official PyTorch repo for JoJoGAN: One Shot Face Stylization
AK391/animegan2-pytorch
PyTorch implementation of AnimeGANv2
AK391/PAMA
AK391/ArcaneGAN
ArcaneGAN
AK391/autocrop
:relieved: Automatically detects and crops faces from batches of pictures.
AK391/openpose
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
AK391/realworld-stylegan2-encoder
Various applications based on Stylegan2 Style mixing that can be inference on cpu.
AK391/steerable-nafx
Steerable discovery of neural audio effects
AK391/bizarre-pose-estimator
AK391/BlendGAN
Official PyTorch implementation of "BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation" (NeurIPS 2021)
AK391/BLIP
PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
AK391/ConvNeXt
Code release for ConvNeXt model
AK391/Detic
Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".
AK391/GPEN
AK391/kapao
KAPAO is an efficient multi-person human pose estimation model that detects keypoints and poses as objects and fuses the detections to predict human poses.
AK391/kogpt
KakaoBrain KoGPT (Korean Generative Pre-trained Transformer)
AK391/lang-seg
Language-Driven Semantic Segmentation
AK391/mae
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
AK391/midi-ddsp
Synthesis of MIDI with DDSP (https://midi-ddsp.github.io/)
AK391/mt3
MT3: Multi-Task Multitrack Music Transcription
AK391/omnivore
Omnivore: A Single Model for Many Visual Modalities
AK391/omnizart
Omniscient Mozart, being able to transcribe everything in the music, including vocal, drum, chord, beat, instruments, and more.
AK391/PaddleGAN
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, wav2lip, picture repair, image editing, photo2cartoon, image style transfer, and so on.
AK391/PaddleSpeech
A Speech Toolkit based on PaddlePaddle.
AK391/pyxelate
Python class that generates pixel art from images
AK391/stylegan2-ada-pytorch
StyleGAN2-ADA - Official PyTorch implementation
AK391/SWAG
Official repository for "Revisiting Weakly Supervised Pre-Training of Visual Perception Models".
AK391/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
AK391/UniFormer
[ICLR2022] official implementation of UniFormer
AK391/yolov3
YOLOv3 in PyTorch > ONNX > CoreML > TFLite