Official code for DiFaReli

Official Implementation for "HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach"

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

[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

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

Implementation of Natural Speech 2, Zero-shot Speech and Singing Synthesizer, in Pytorch

🔊 Text-Prompted Generative Audio Model

Real-time face swap for PC streaming or video calls

Instant neural graphics primitives: lightning fast NeRF and more

[CVPR 2022] Thin-Plate Spline Motion Model for Image Animation.

Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and Lighting From Images".

[CVPR'23, Highlight] ECON: Explicit Clothed humans Optimized via Normal integration

[CVPR'22] ICON: Implicit Clothed humans Obtained from Normals

🔥🔥NSFW implement in pytorch（色情图&性感图识别，本程序经过了线上大数据集测试，性能优异效果良好）🔥🔥

AudioLDM: Generate speech, sound effects, music and beyond, with text.

PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.

This repository contains the source code for the paper First Order Motion Model for Image Animation

Supplementary materials for paper MegaPortraits [ACMM22]

Apply diffusion models using the new Hugging Face diffusers package to synthesize music instead of images.

A simple notebook demonstrating prompt-based music generation via Mubert API

Muzic: Music Understanding and Generation with Artificial Intelligence

Versatile Diffusion: Text, Images and Variations All in One Diffusion Model, arXiv 2022 / ICCV 2023

Official implementation of VQ-Diffusion

Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

More practical frame interpolation approach.

Jupyter Notebooks to help you get hands-on with Pinecone vector databases

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

Function to frontalize non-frontal 2D facial landmarks generated from the DLIB library