#
Starred repositories
287
stars
written in Python
Clear filter
Unlimited-length talking video generation that supports image-to-video and video-to-video generation
A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)
Unofficial Implementation of Animate Anyone
PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
neuralnetworksanddeeplearning.com integrated scripts for Python 3.5.2 and Theano with CUDA support
Keras Attention Layer (Luong and Bahdanau scores).
MuseV: Infinite-length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising
CTPN + DenseNet + CTC based end-to-end Chinese OCR implemented using tensorflow and keras
GGUF Quantization support for native ComfyUI models
"Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)
🚀 一键部署（含离线整合包）！基于 ChatTTS ，支持流式输出、音色抽卡、长音频生成和分角色朗读。简单易用，无需复杂安装。
Based on Talking-head-anime 3, works like Vtube Studio.
Using modified BiSeNet for face parsing in PyTorch
Automatically remove the mosaics in images and videos, or add mosaics to them.
High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance
DECA: Detailed Expression Capture and Animation (SIGGRAPH 2021)
xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
V-Express aims to generate a talking head video under the control of a reference image, an audio, and a sequence of V-Kps images.
A very simple BiLSTM-CRF model for Chinese Named Entity Recognition 中文命名实体识别 (TensorFlow)
DeepMind's Tacotron-2 Tensorflow implementation
A set of tools for extracting tables from PDF files helping to do data mining on (OCR-processed) scanned documents.
Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span)
Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.