We present FlashPortrait, an end-to-end video diffusion transformer capable of synthesizing ID-preserving, infinite-length videos while achieving up to 6$\times$ acceleration in inference speed.

A.I.G (AI-Infra-Guard) is a comprehensive, intelligent, and easy-to-use AI Red Teaming platform developed by Tencent Zhuque Lab.

Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets

Hunyuan 3D Part Segmentation and Generation Pipeline

We present StableAvatar, the first end-to-end video diffusion transformer, which synthesizes infinite-length high-quality audio-driven avatar videos without any post-processing, conditioned on a re…

Wan: Open and Advanced Large-Scale Video Generative Models

Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model

🚀 Truly open-source AI avatar(digital human) toolkit for offline video generation and digital human cloning.

Wan: Open and Advanced Large-Scale Video Generative Models

[CVPR2025] We present StableAnimator, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without any post-processing, conditioned on a reference ima…

Registration between a reconstructed point cloud and an estimated SMPL mesh.

High-resolution models for human tasks.

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Reverse engineered ChatGPT API

A multi-voice TTS system trained with an emphasis on quality

fAshIon Datasets

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

Making large AI models cheaper, faster and more accessible

The idea of this list is to collect shared data and algorithms around 3D Morphable Models. You are invited to contribute to this list by adding a pull request. The original list arised from the Dag…

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

A collection of design patterns/idioms in Python

ALL IN ONE Hacking Tool For Hackers

[CVPR 2020] GAN Compression: Efficient Architectures for Interactive Conditional GANs

This is a implementation of the 3D FLAME model in PyTorch

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Official code for the paper "InGAN: Capturing and Retargeting the DNA of a Natural Image"

This repository contains code corresponding to the paper "Tex2Shape: Detailed Full Human Body Geometry from a Single Image"

Python wrapper to Philipp Krähenbühl's dense (fully connected) CRFs with gaussian edge potentials.

Semantic Image Synthesis with SPADE

StyleGAN - Official TensorFlow Implementation