XiuSdk's repositories
AniPortrait
AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation
BFRffusion
Official codes of Towards Real-World Blind Face Restoration with Generative Diffusion Prior
CelebV-Text
(CVPR 2023) CelebV-Text: A Large-Scale Facial Text-Video Dataset
champ
Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance
DeepFaceLive
Real-time face swap for PC streaming or video calls
FreeU
FreeU: Free Lunch in Diffusion U-Net
keras-core
A multi-backend implementation of the Keras API, with support for TensorFlow, JAX, and PyTorch.
LayerDiffusion
Transparent Image Layer Diffusion using Latent Transparency
llama2.c
Inference Llama 2 in one file of pure C
mergekit
Tools for merging pretrained large language models.
minSDTF
Stable Diffusion V1.5 Inference With PyTorch Weights And More Features Like Stable Diffusion Web UI In TensorFlow
ml-facelit
Official repository of FaceLit: Neural 3D Relightable Faces (CVPR 2023)
Next3D
[CVPR 2023 Highlight] Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars
PromptGenTF
A Simple and Efficient PromptGen Inference Implementation In TensorFlow 2
Real-ESRGAN
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
roop
one-click deepfake (face swap)
SEO
A Simple and Efficient Optimizer for Deep Learning
SkinDeep
Get Deinked!!
so-vits-svc
SoftVC VITS Singing Voice Conversion
soundstorm-pytorch
Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch
stable-diffusion
A latent text-to-image diffusion model
T2I-Adapter
T2I-Adapter
taesd-tf
Tiny AutoEncoder for Stable Diffusion in TensorFlow / Keras
text-generation-webui
A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, Pythia, OPT, and GALACTICA.
wav2lip-hq
Extension of Wav2Lip repository for processing high-quality videos.
yolov8-face
yolov8 face detection with landmark
yolov8-face-landmarks-opencv-dnn
使用OpenCV部署yolov8检测人脸和关键点，包含C++和Python两个版本的程序，只依赖opencv库就可以运行，彻底摆脱对任何深度学习框架的依赖。