taichuai

taichuai's Stars

• hacksider/Deep-Live-Cam

  real time face swap and one-click video deepfake with only a single image

  Language:Python41.9k2475806.1k

• 1adrianb/face-alignment

  :fire: 2D and 3D Face alignment library build using pytorch

  Language:Python7.2k1743161.4k

• google-deepmind/alphafold3

  AlphaFold 3 inference pipeline.

  Language:Python5.7k49201671

• mseitzer/pytorch-fid

  Compute FID scores with PyTorch.

  Language:Python3.5k1386516

• Tencent/Hunyuan3D-1

  Tencent Hunyuan3D-1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation

  Language:Python2.5k187

• genmoai/models

  The best OSS video generation models

  Language:Python2.1k3467209

• deepseek-ai/Janus

  Janus-Series: Unified Multimodal Understanding and Generation Models

  Language:Python1.3k232260

• wenqsun/DimensionX

  DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion

  Language:Python1.1k413266

• NVIDIA/Cosmos-Tokenizer

  A suite of image and video neural tokenizers

  Language:Python1k17026

• edwko/OuteTTS

  Interface for OuteTTS models.

  Language:Python786204162

• mqz111a/virtual_human_stream

  The "virtual_human_stream" project is a real-time digital human system supporting audio-video dialogue. It integrates models like ernerf, musetalk, and wav2lip for voice cloning, video stitching, and streaming via RTMP/WebRTC. It’s optimized for high performance and easy customization, with support for ChatGPT dialogue integration.

  Language:Python61342091

• Henry-23/VideoChat

  实时语音交互数字人，支持端到端语音方案（GLM-4-Voice - THG）和级联方案（ASR-LLM-TTS-THG）。可自定义形象与音色，无须训练，支持音色克隆，首包延迟低至3s。Real-time voice interactive digital human, supporting end-to-end voice solutions (GLM-4-Voice - THG) and cascaded solutions (ASR-LLM-TTS-THG). Customizable appearance and voice, supporting voice cloning, with initial package delay as low as 3s.

  Language:Python56493573

• EnVision-Research/Lotus

  Official Implementation of LOTUS: Diffusion-based Visual Foundation Model for High-quality Dense Prediction

  Language:Python532162429

• adobe-research/MakeItTalk

  Language:Jupyter Notebook5002523308

• OleehyO/TexTeller

  TexTeller can convert image to latex formulas (image2latex, latex OCR) with higher accuracy and exhibits superior generalization ability, enabling it to cover most usage scenarios.

  Language:Python40161746

• xg-chu/GAGAvatar

  [NeurIPS 2024] Generalizable and Animatable Gaussian Head Avatar

  Language:Python381162436

• wdndev/tiny-llm-zh

  从零实现一个小参数量中文大语言模型。

  Language:Python37361741

• dongzhuoyao/awesome-flow-matching

  A summary of related works about flow matching, stochastic interpolants

  35914213

• Femoon/tts-azure-web

  TTS Azure Web 是一个 Azure 文本转语音（TTS）网页应用，可以在本地或者云端使用你的 Azure Key 一键部署。TTS Azure Web is an Azure Text-to-Speech (TTS) web application. It allows you to run it locally or deploy it with a single click using your Azure Key.

  Language:TypeScript3552742

• VideoVerses/VideoTuna

  Let's finetune video generation models!

  Language:Python33771111

• VITA-MLLM/Freeze-Omni

  ✨✨Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM

  Language:Python22815

• ddlBoJack/Awesome-Speech-Language-Model

  Paper, Code and Resources for Speech Language Model and End2End Speech Dialogue System.

  14312

• shaopengw/Awesome-Music-Generation

  Awesome music generation model——MG²

  Language:Python1219711

• cantabile-kwok/vec2wav2.0

  Code for vec2wav 2.0, a speech token vocoder for VC. Paper: https://arxiv.org/abs/2409.01995

  Language:Python581055

• LeCAR-Lab/wococo

  Language:Python56004

• XingliangJin/MCM-LDM

  [CVPR 2024] Arbitrary Motion Style Transfer with Multi-condition Motion Latent Diffusion Model

  Language:Python474129

• GhostCai/PortraitRelighting

  Official PyTorch implementation of the CVPR 2024 Highlight Paper "Real-time 3D-aware Portrait Video Relighting"

  Language:Python36565

• audeering/w2v2-age-gender-how-to

  How to use our public wav2vec2 age and gender model

  Language:Jupyter Notebook30352

• liuhuang31/Megatts2_HierSpeechpp

  Megatts2 use HierSpeechpp's vocoder

  Language:Python171

• PeizhiYan/mediapipe-blendshapes-to-flame

  Mapping Mediapipe's 52 blendshapes to FLAME's expression coefficients and poses.

  Language:Jupyter Notebook6210