#
hwscut
Follow
Starred repositories
An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.
EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation
Fine-tune BERT models to classify Arabic text by different dialects.
Unified-Modal Speech-Text Pre-Training for Spoken Language Processing
An Open-Sourced LLM-empowered Foundation TTS System
Real-time face swap for PC streaming or video calls
Repository for training models for music source separation.
Offical implement of Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for talking head Video Generation
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation
This repository gives the official implementation of Realistic and Efficient Face Swapping: A Unified Approach with Diffusion Models (WACV 2025)
Multilingual Voice Understanding Model
[ACM TOG, 2024] Identity-Preserving Face Swapping via Dual Surrogate Generative Models
[ICCV 2023] BlendFace: Re-designing Identity Encoders for Face-Swapping https://arxiv.org/abs/2307.10854
A Survey on Deepfake Generation and Detection
Official Implementation of 'ReliableSwap: Boosting General Face Swapping Via Reliable Supervision'
A new one shot face swap approach for image and video domains
a node for comfyui for restore/edit/enchance faces utilizing face recognition
[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation
Official PyTorch implementation of Revisiting Image Pyramid Structure for High Resolution Salient Object Detection (ACCV 2022)
TTS models for Arabic (Tacotron2, FastPitch)
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Official inference repo for FLUX.1 models
Open-Sora: Democratizing Efficient Video Production for All
[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment