Starred repositories
ShadowFormer (AAAI2023), Pytorch implementation
A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Era of Deep Learning (Awesome & Benchmark)
[TAI 2025] Official implementation of TAI-accepted paper: ShadowMaskFormer: Mask Augmented Patch Embedding for Shadow Removal
Implementation of Analyzing and Improving the Image Quality of StyleGAN (StyleGAN 2) in PyTorch
[ACM MM 2021 Oral] Unsupervised Portrait Shadow Removal via Generative Priors
ComfyUI的模型下载节点，支持civitai和huggingface下的模型下载。
Free and Open Source Machine Translation API. Self-hosted, offline capable and easy to setup.
[AAAI 2025, Oral] DepthFM: Fast Monocular Depth Estimation with Flow Matching
[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
OpenMMLab's next-generation platform for general 3D object detection.
From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
DreamO native implementation for ComfyUI
DreamO: A Unified Framework for Image Customization
rnnoise noise suppression library as a WASM module
Javascript audio library for the modern web.
HunyuanVideo: A Systematic Framework For Large Video Generation Model
Production First and Production Ready End-to-End Speech Recognition Toolkit
优化wav2lip的执行步骤，将头脸分离、嘴型替换、回补背景三个步骤分离，添加gfpgan强化面部功能，实现提前解帧，流式循环处理，对接obs
Python bindings for the Chromium Embedded Framework (CEF)
simple and efficient python implemention of a series of adaptive filters. including time domain adaptive filters(lms、nlms、rls、ap、kalman)、nonlinear adaptive filters(volterra filter、functional link a…