Expressive Anechoic Recordings of Speech (EARS)

Bring portraits to life!

Simple library to speed up or slow down speech

MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting

Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

FaceChain is a deep-learning toolchain for generating your Digital-Twin.

Mamba SSM architecture

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

[TPAMI2023] RestoreFormer++

[CVPR 2022] RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairs

Zero-Shot Speech Editing and Text-to-Speech in the Wild

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

Official Jax Implementation of MaskGIT

Real time transcription with OpenAI Whisper.

A python library for real-time audio time-scale modification procedures

Real-time Audio time-scale and pitch modification in Python

An open-source Python library for audio time-scale modification.

Multilingual and Controllable Text-to-Speech Toolkit of the Speech and Language Technologies Group at the University of Stuttgart.

Inpaint anything using Segment Anything and inpainting models.

Official JAX implementation of MAGVIT: Masked Generative Video Transformer

[CVPR 2024] MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

AI powered speech denoising and enhancement

Official implementation of "Separate Anything You Describe"

Outfit Anyone: Ultra-high quality virtual try-on for Any Clothing and Any Person

Real-time face swap for PC streaming or video calls