1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Instant voice cloning by MIT and MyShell. Audio foundation model.

Stable Diffusion built-in to Blender

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

The official PyTorch implementation of the paper "Human Motion Diffusion Model"

GeneFace++: Generalized and Stable Real-Time 3D Talking Face Generation; Official Code

Real-time and accurate open-vocabulary end-to-end object detection

HPy: a better API for Python

[CVPR2024] DisCo: Referring Human Dance Generation in Real World

STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution

Code of [CVPR 2024] "Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling"

MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model

High-accuracy NLP parser with models for 11 languages.

g2p: English Grapheme To Phoneme Conversion

[CVPR 2024] Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models, a no lighting baked texture generative model

[ECCV 2024] Single Image to 3D Textured Mesh in 10 seconds with Convolutional Reconstruction Model.

[ICCV 2023] Text2Tex: Text-driven Texture Synthesis via Diffusion Models

Investigating CoT Reasoning in Autoregressive Image Generation

[CVPR2024] Official implementation of SplattingAvatar.

Create 3d rooms in blender from floorplans.

Single Motion Diffusion Model

[ ECCV 2024 ] MotionLCM: This repo is the official implementation of "MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model"

This is the official repository for OTAvatar: One-shot Talking Face Avatar with Controllable Tri-plane Rendering [CVPR2023].

[ICLR 2024] Generalizable and Precise Head Avatar from Image(s)

DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models

Large Motion Model for Unified Multi-Modal Motion Generation

[CVPR'23] Learning Neural Parametric Head Models

The official code of our ICCV2023 work: Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation