Starred repositories
82
stars
written in Python
Clear filter
Robust Speech Recognition via Large-Scale Weak Supervision
💻 A fully functional local AWS cloud stack. Develop and test your cloud & Serverless apps offline
Clone a voice in 5 seconds to generate arbitrary speech in real-time
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Instant voice cloning by MIT and MyShell. Audio foundation model.
Industry leading face manipulation platform
A Deep Learning based project for colorizing and restoring old images (and video!)
Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team, Alibaba Cloud.
HunyuanVideo: A Systematic Framework For Large Video Generation Model
PyTorch package for the discrete VAE used for DALL·E.
High-Resolution 3D Human Digitization from A Single Image.
Stable Diffusion built-in to Blender
A Blender script to procedurally generate 3D spaceships
ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution. The training codes are in BasicSR.
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
A command line toolkit to generate maps, point clouds, 3D models and DEMs from drone, balloon or kite images. 📷
Efficient 3D human pose estimation in video using 2D keypoint trajectories
An extensive node suite that enables ComfyUI to process 3D inputs (Mesh & UV Texture, etc) using cutting edge algorithms (3DGS, NeRF, etc.)
The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.
A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.
From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
DECA: Detailed Expression Capture and Animation (SIGGRAPH 2021)
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019)
[ICLR 2025] From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"
Expressive Body Capture: 3D Hands, Face, and Body from a Single Image
Specifications and tools for 360º video and spatial audio.