xymfei,github

ov-seg

This is the official PyTorch implementation of the paper Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP.

panohead

PanoHead从单图生成 3D 纹理模型Code Repository for CVPR 2023 Paper "PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360 degree"

persam-personalized-segment-anything-

PerSAM（个性化细分任何内容）现已推出 @huggingface ！这种（超酷）方法允许 SAM 实现类似 Dreambooth 的个性化，能够仅基于单个（图像、蒙版）示例快速分割图像中的新事物

propainter

删除视频中物件[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting

remodiffuse

ReMoDiffuse: 可控的文本到动作，检索增强运动扩散模型Retrieval-Augmented Motion Diffusion Model

retrieval-based-voice-conversion-webui

变声器Voice data <= 10 mins can also be used to train a good VC model!

robustvideomatting

扣图视频中人物,背景变成绿幕Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

sadtalker

（CVPR 2023）SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.

sinmdm

Single Motion Diffusion Model

slahmr

SLAHMR跟踪视频中运动的人，可以估计视频中人物的全球轨迹和姿势

smpler-x

SMPLer-X可从视频中提取人体动作来制作虚拟角色动画

so-vits-svc

SoftVC VITS Singing Voice Conversion

stable-fast

快速稳定扩散，一个超轻量级的推理性能优化库An ultra lightweight inference performance optimization library for HuggingFace Diffusers on NVIDIA GPUs.

supervision

supervision跟踪识别视频中所有物体，v0.16.0实现了紧贴物件轮廓光环效果注释器来分割标识每个物件，roboflow/supervision: We write your reusable computer vision tools. 💜高级视频分析。跟踪器、区域、注释器等等We write your reusable computer vision tools. 💜

talkshow

TalkSHOW学习通过面部和手部动作，（ #CVPR2023 ）生成逼真、连贯和多样化的整体 3D 动作，即身体动作以及面部表情和手势贯和多样化的整体身体运动。This is the official repository for TalkSHOW: Generating Holistic 3D Human Motion from Speech [CVPR2023].

text2performer

Text2Performer. 文本提示生成高分辨率带清晰动作生动的人类视频Paper: Text2Performer: Text-Driven Human Video Generation

text2video

半个神器👉一键文本转视频的工具

tmr

文本到人体连续动作

track-anything

视频对象跟踪和分割工具,基于SAM。Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything and XMem.

triplanenet

TriPlaneNet：人物肖像生成人物肖像左右上下移动图,用3D GAN，以实现新颖的视图渲染用于 EG3D 反演的编码器，第二个版本已被 WACV 2024 接受，即将发布

v2vt

转录视频语音并翻译，语音克隆，口型同步，压制字幕，支持中英视频互相转换

video-retalking

VideoReTalking：让视频中的人物的嘴型与输入的声音同步[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

videocrafter

高质量的文本2视频和图像2视频制模型-A Toolkit for Text-to-Video Generation and Editing

vits-fast-fine-tuning

Colab快速得到語音合成模型。可克隆聲音，製作帶有訓練樣本說話特徵、語調的語音合成模型。只要錄幾句話，後續修改內容就不需要重錄。This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion

wechatmsg

提取微信聊天记录，将其导出成HTML、Word、CSV文档永久保存，对聊天记录进行分析生成年度聊天报告

xymfei Goto Github PK

xymfei's Projects

Recommend Projects

Recommend Topics

Recommend Org