Justin John

so-vits-svc-4.0-v2. SoftVC VITS Singing Voice Conversion

so-vits-svc-4.0. SoftVC VITS Singing Voice Conversion

VQGAN-CLIP. VQGAN+CLIP Colab Notebook with user-friendly interface.

FakeYou-Tacotron2-Notebook. Tacotron2 Training Notebook for FakeYou.com

Wav2Lip. This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020.

MaskGCT-Windows. MaskGCT-Windows For Windows Users

StyleFlow-Windows-10. StyleFlow: Attribute-conditioned Exploration of StyleGAN-generated Images using Conditional Continuous Normalizing Flows

Audio-Splitter. Audio Splitter provides a user-friendly solution for splitting audio files based on silence detection.

StyleGAN3-CLIP-ColabNB. Google Colab notebook for NVIDIA's StyleGAN3 and OpenAI's CLIP for a text-based guided image generation.

TalkNET-colab. NVIDIA's TalkNET - Train and Synthesize on colab

EverybodyDanceNow-Colab. Motion Retargeting Video Subjects, Modified Colab Version by Justin John

TTS-TT2. Tacotron 2 - PyTorch implementation with faster-than-realtime inference

SpeedScribe. High-performance ASR tool using Faster Whisper, supporting custom models, multi-language transcription, and real-time processing feedback.

video-retalking. [SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

local-llasa-tts-windows. Examples of using the llasa-tts models locally

PF-AFN-Windows. Windows implementation by Justin John for "Parser-Free Virtual Try-on via Distilling Appearance Flows", CVPR 2021.

ditto-talkinghead-windows. Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis

LatentSync-windows. Taming Stable Diffusion for Lip Sync!

efficient-vits-finetuning. Finetuning VITS Efficiently

tacotron2. Tacotron 2 - PyTorch implementation with faster-than-realtime inference

csm-windows. A Conversational Speech Generation Model

Mangio-RVC-Fork-Simple-CLI. Python

GPT-SoVITS-No-WebUI. No WebUI google colab implementation of GPT-SoVITS

StyleGANEX. StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Faces

3d-photo-inpainting-Windows. [CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting

e4s-windows. (CVPR 2023) E4S: Fine-grained Face Swapping via Regional GAN Inversion

OpenMMD. OpenMMD is an OpenPose-based application that can convert real-person videos to the motion files (.vmd) which directly implement the 3D model (e.g. Miku, Anmicius) animated movies.

so-vits-svc. 基于vits与softvc的歌声音色转换模型

ARPAtaco2. Tacotron 2 - PyTorch implementation with faster-than-realtime inference and CMU Pronouncing Dictionary support

Wav2Lip-Colab. A slightly modified version of Wav2Lip for newbies

PCAVS-Colab. Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation (CVPR 2021)

EverybodyDanceNow-Windows10. EverybodyDanceNow implementation for Windows 10

GPT-SoVITS-v1-No-WebUI-Colab. No WebUI google colab implementation of GPT-SoVITS

talknet-hifi-gan. HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

AMLD2020-Dirty-GANcing. AMLD 2020

Mano2Smpl-X. We provide a way to fuse MANO parameters into SMPLX.

instant-ngp-Windows. Instant neural graphics primitives: lightning fast NeRF and more

wav2lip-onnx-HQ. Full version of wav2lip-onnx including face alignment and face enhancement and more...

Mocapy. Markerless motion capture: video/webcam -> VRM avatar bones -> BVH