legendrain Goto Github PK

betterdflextractor

A better face extractor for DeepFaceLab, using 3DDFA_V2.

chatglm-llama-chinese-insturct

探索中文instruct数据在ChatGLM, LLaMA上的微调表现

coze-discord

Using two Discord robot proxies for Coze service, free access to the API features of the GPT-4 advanced model.使用两个Discord机器人代理Coze服务，免费使用GPT-4高级模型的API功能

daclip-uir

PyTorch code for "Controlling Vision-Language Models for Universal Image Restoration", ICLR 2024.

deepfacelive-virtualcam

A simple script to create a virtual camera and route deepfakelive's output stream to it using Python and OpenCV

deepfacelive_unrealengine_showcase

dfrf

[ECCV2022] The implementation for "Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesis".

diffusionmat

digitalavatarrealtime

推理服务和推理视频流服务

dinet

提交的新代码

dinet_optimized

An optimized pipeline for DINet reducing inference latency for up to 60% 🚀. Kudos for the authors of the original repo for this amazing work.

dinet_optimized2

A

er-nerf

[ICCV'23] Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis

ffhq-uv

The official repository of our CVPR2023 paper "FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstruction".

galtransl

支持GPT3.5/4/Newbing等大语言模型的Galgame自动化翻译解决方案

gptwntranslator

A web novel translator using OpenAI's GPT AI models

hairstep

Repository for "HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling". [CVPR2023 Highlight]

hdtr-net

A Real-Time High-Definition Teeth Restoration Network for ArbitraryTalking Face Generation Methods

hyperlips

Pytorch official implementation for our paper "HyperLips: Hyper Control Lips with High Resolution Decoder for Talking Face Generation".

iastreameur

AIStreameur : Faite streamer vos personne préféré !

latentavatar

A PyTorch implementation of "LatentAvatar: Learning Latent Expression Code for Expressive Neural Head Avatar"

mandelbulber2

Official repository for Mandelbulber v2

rad-nerf

Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition

sg

spiga

SPIGA: Shape Preserving Facial Landmarks with Graph Attention Networks.

wav2lip_288x288_test