水镜扒奇's starred repositories
GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
insightface
State-of-the-art 2D and 3D Face Analysis Project
first-order-model
This repository contains the source code for the paper First Order Motion Model for Image Animation
video-subtitle-extractor
视频硬字幕提取,生成srt文件。无需申请第三方API,本地实现文本识别。基于深度学习的视频字幕提取框架,包含字幕区域检测、字幕内容提取。A GUI tool for extracting hard-coded subtitle (hardsub) from videos and generating srt files.
Baichuan-7B
A large-scale 7B pretraining language model developed by BaiChuan-Inc.
Background-Matting
Background Matting: The World is Your Green Screen
ECCV2022-RIFE
ECCV2022 - Real-Time Intermediate Flow Estimation for Video Frame Interpolation
video-subtitle-remover
基于AI的图片/视频硬字幕去除、文本水印去除,无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API,本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.
FaceDetection-DSFD
腾讯优图高精度双分支人脸检测器
SadTalker-Video-Lip-Sync
本项目基于SadTalkers实现视频唇形合成的Wav2lip。通过以视频文件方式进行语音驱动生成唇形,设置面部区域可配置的增强方式进行合成唇形(人脸)区域画面增强,提高生成唇形的清晰度。使用DAIN 插帧的DL算法对生成视频进行补帧,补充帧间合成唇形的动作过渡,使合成的唇形更为流畅、真实以及自然。
face2face-demo
pix2pix demo that learns from facial landmarks and translates this into a face
FaceRecognition-tensorflow
基于TensorFlow训练的人脸识别神经网络
LiveSpeechPortraits
Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation (SIGGRAPH Asia 2021)
best-chinese-prompt
AI中文提示词秘籍ChatGPT中文提示词秘籍(Prompt圣经)K-Render整理
Realistic-Neural-Talking-Head-Models
My implementation of Few-Shot Adversarial Learning of Realistic Neural Talking Head Models (Egor Zakharov et al.).
face_segmentation
Deep face segmentation in extremely hard conditions
Video-Auto-Wipe
Erase specific content from the video that you don't wanna see