tadax

ai-topics. HTML

pico-banana-400k. Python

ComfyUI_FlashVSR. FlashVSR：Towards Real-Time Diffusion-Based Streaming Video Super-Resolution，you can use it in comfyUI

nanochat. The best ChatGPT that $100 can buy.

dots.ocr. Multilingual Document Layout Parsing in a Single Vision-Language Model

SuperClaude_Framework. A configuration framework that enhances Claude Code with specialized commands, cognitive personas, and development methodologies.

plamo-translate-cli. Python

torchtitan. A PyTorch native platform for training generative AI models

LanPaint. High quality training free inpaint for every stable diffusion model. Supports ComfyUI

build-your-own-x. Master programming by recreating your favorite technologies from scratch.

deer-flow. An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

jax-ddim. Jax/Flax implementation of Denoising Diffusion Implicit Models

OpenVision. OpenVision (ICCV 2025), OpenVision 2 (CVPR 2026), and OpenVision 3

ty. An extremely fast Python type checker and language server, written in Rust.

system_prompts_leaks. Extracted system prompts from Anthropic - Claude Fable 5, Opus 4.8, Claude Code, Claude Design. OpenAI - ChatGPT GPT-5.6, Codex GPT-5.6, GPT-5.5. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Cursor, Copilot, VS Code, Perplexity, and more. Updated regularly.

mimic. Mimic is a eBPF virtual machine and emulator which runs in userspace

octox. Unix-like OS in Rust inspired by xv6-riscv

CogView4. CogView4, CogView3-Plus and CogView3(ECCV 2024)

diffusers-torchao. End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).

atuin. ✨ Making your shell magical

sapiens. High-resolution models for human tasks.

BiRefNet. [CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation

ai-toolkit. The ultimate training toolkit for finetuning diffusion models

SimpleTuner. A general fine-tuning kit geared toward image/video/audio diffusion models.

whisper-medusa. Whisper with Medusa heads

EasyAnimate. 📺 An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion

starline. Strict coloring machine for line drawings.

asdbctl. Small command line utility to get/set the brightness of Apple Studio Displays from Linux

aesthetic-predictor-v2-5. SigLIP-based Aesthetic Score Predictor

Rope. GUI-focused roop

torchtune. PyTorch native post-training library

cleanlab. Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

EdgeSAM. Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"

fastsdcpu. Fast stable diffusion on CPU and AI PC

data-engineer-handbook. This is a repo with links to everything you'd ever want to learn about data engineering

ML-from-scratch-seminar. This repository is part of a "Machine Learning from Scratch" seminar at Harvard Medical School.

consistencydecoder. Consistency Distilled Diff VAE

caption-upsampling. This repository implements the idea of "caption upsampling" from DALL-E 3 with Zephyr-7B and gathers results with SDXL.

cf-clearance. Purpose To make a cloudflare v2 challenge pass successfully, Can be use cf_clearance bypassed by cloudflare, However, with the cf_clearance, make sure you use the same IP and UA as when you got it.

lama. 🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

ml-stable-diffusion. Stable Diffusion with Core ML on Apple Silicon

FFTformer. [CVPR 2023] Efficient Frequency Domain-based Transformer for High-Quality Image Deblurring

Rerender_A_Video. [SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation

CelebBasis. Official Implementation of 'Inserting Anybody in Diffusion Models via Celeb Basis'

roop. roop extension for StableDiffusion web-ui

InstaFlow. :zap: InstaFlow! One-Step Stable Diffusion with Rectified Flow (ICLR 2024)

cog-sdxl. Stable Diffusion XL training and inference as a cog model

ML-For-Beginners. 12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all

CoreML-Models. Converted CoreML Model Zoo.

folly. An open-source C++ library developed and used at Facebook.

Alamofire. Elegant HTTP Networking in Swift

project-layout. Standard Go Project Layout

dl. Command-line file downloader tool

invisible-watermark. python library for invisible image watermark (blind image watermark)

dotfiles.fish. my dotfiles

tips-for-studying-and-working-abroad-ja. Tips for studying and working abroad for Japanese students

softargmax. A differentiable argmax function for PyTorch

yt-dlc. media downloader and library for various sites.

RePaint. Official PyTorch Code and Models of "RePaint: Inpainting using Denoising Diffusion Probabilistic Models", CVPR 2022

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

digital_video_introduction. A hands-on introduction to video technology: image, video, codec (av1, vp9, h265) and more (ffmpeg encoding). Translations: 🇺🇸 🇨🇳 🇯🇵 🇮🇹 🇰🇷 🇷🇺 🇧🇷 🇪🇸

IF. Python

segment-geospatial. A Python package for segmenting geospatial data with the Segment Anything Model (SAM)

shap-e. Generate 3D objects conditioned on text or images

humanrf. Official code for "HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion"

consistency_models. A mini-library for training consistency models.

bark-with-voice-clone. 🔊 Text-prompted Generative Audio Model - With the ability to clone voices

StableLM. StableLM: Stability AI Language Models

PIDM. Person Image Synthesis via Denoising Diffusion Model (CVPR 2023)

segment-anything. 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.

face-parsing.PyTorch. Using modified BiSeNet for face parsing in PyTorch

tomesd. Speed up Stable Diffusion with this one simple trick!

EDICT. Jupyter Notebook

alpaca-lora. Instruct-tune LLaMA on consumer hardware

AlpacaChat. A Swift library that runs Alpaca-LoRA prediction locally to implement ChatGPT like app on Apple platform devices.

semantic-segmentation-editor. Web labeling tool for bitmap images and point clouds

faster-whisper. Faster Whisper transcription with CTranslate2

GLIGEN. Open-Set Grounded Text-to-Image Generation

ControlNet-for-Diffusers. Transfer the ControlNet with any basemodel in diffusers🔥

lora. Using Low-rank adaptation to quickly fine-tune diffusion models.

LAVIS. LAVIS - A One-stop Library for Language-Vision Intelligence

minDiffusion. Self-contained, minimalistic implementation of diffusion models with Pytorch.

guided-diffusion. Python

Paint-by-Example. Paint by Example: Exemplar-based Image Editing with Diffusion Models

pix2pix-zero. Zero-shot Image-to-Image Translation [SIGGRAPH 2023]

chibicc. A small C compiler

ControlNet. Let us control diffusion models!

nanoGPT. The simplest, fastest repository for training/finetuning medium-sized GPTs.

whisper.cpp. Port of OpenAI's Whisper model in C/C++

vall-e. PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

metaseq. Repo for external large-scale work

tweepy-authlib. 【メンテナンス終了】Twitter Web App (Web 版公式クライアント) の内部 API を使い、Tweepy でスクリーンネームとパスワードで認証するためのライブラリ

fluxsort. A fast branchless stable quicksort / mergesort hybrid that is highly adaptive.

carbonyl. Chromium running inside your terminal

nlpaug. Data augmentation for NLP

tuning_playbook. A playbook for systematically maximizing the performance of deep learning models.

scenic. Scenic: A Jax Library for Computer Vision Research and Beyond

xformers. Hackable and optimized Transformers building blocks, supporting a composable construction.

fairscale. PyTorch extensions for high performance and large scale training.

silicon. Create beautiful image of your source code.

puppy-browser. An example implementation of a tiny Web browser for educational purposes.

lightning-hydra-template. PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡

YOLOX. YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

SimSwap. An arbitrary face-swapping framework on images and videos with one single trained model!

pytorch-ddpm. Unofficial PyTorch implementation of Denoising Diffusion Probabilistic Models

diffusion. Denoising Diffusion Probabilistic Models

torchtyping. Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.

pysen. Python linting made easy. Also a casual yet honorific way to address individuals who have entered an organization prior to you.

awesome-offline-rl. An index of algorithms for offline reinforcement learning (offline-rl)

review_object_detection_metrics. Object Detection Metrics. 14 object detection metrics: mean Average Precision (mAP), Average Recall (AR), Spatio-Temporal Tube Average Precision (STT-AP). This project supports different bounding box formats as in COCO, PASCAL, Imagenet, etc.

DALL-E. PyTorch package for the discrete VAE used for DALL·E.

stylegan2-ada-pytorch. StyleGAN2-ADA - Official PyTorch implementation

PyramidFill. Python

stylegan2-pytorch. Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement

sam. Python

perceptual-quality. Perceptual quality metrics for TensorFlow

DALLE-pytorch. Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

Deep3DFaceReconstruction. Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019)

Deep3DFaceReconstruction-pytorch. Pytorch version of Deep3DFaceReconstruction

WM3DR. Python

mmtracking. OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

autoalbument. AutoML for image augmentation. AutoAlbument uses the Faster AutoAugment algorithm to find optimal augmentation policies. Documentation - https://albumentations.ai/docs/autoalbument/

HyperRIM. Python

Object-Detection-Metrics. Most popular metrics used to evaluate object detection algorithms.

ScaledYOLOv4. Scaled-YOLOv4: Scaling Cross Stage Partial Network

DG-Net. :couple: Joint Discriminative and Generative Learning for Person Re-identification. CVPR'19 (Oral) :couple:

U-2-Net. The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."

CelebAMask-HQ. A large-scale face dataset for face parsing, recognition, generation and editing.

mediapipe. Cross-platform, customizable ML solutions for live and streaming media.

ML-From-Scratch. Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.

yacs. YACS -- Yet Another Configuration System

faceshifter. Unofficial PyTorch Implementation for FaceShifter (https://arxiv.org/abs/1912.13457)

stylegan2-ada. StyleGAN2 with adaptive discriminator augmentation (ADA) - Official TensorFlow implementation

FGVC. [ECCV 2020] Flow-edge Guided Video Completion

Kindai-OCR. OCR system for recognizing modern Japanese magazines

setup.py. 📦 A Human's Ultimate Guide to setup.py.

dx. DX Analytics | Financial and Derivatives Analytics with Python

safaribooks. Download and generate EPUB of your favorite books from O'Reilly Learning (aka Safari Books Online) library.

ncnn. ncnn is a high-performance neural network inference framework optimized for the mobile platform

lag. Python

Js2Py. JavaScript to Python Translator & JavaScript interpreter written in 100% pure Python🚀 Try it online:

jispy. A JavaScript interpreter in Python, built for embedding JavaScript.

ResNeSt. ResNeSt: Split-Attention Networks

audio. Data manipulation and transformation for audio signal processing, powered by PyTorch

rvemu-for-book. Reference implementation for the book "Writing a RISC-V Emulator in Rust".

PRML. PRML algorithms implemented in Python

fastbook. The fastai book, published as Jupyter Notebooks

landmark-detection. Four landmark detection algorithms, implemented in PyTorch.

first-order-model. This repository contains the source code for the paper First Order Motion Model for Image Animation

generative_inpainting. DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral

kaolin. A PyTorch Library for Accelerating 3D Deep Learning Research

flownet2-pytorch. Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Deep-Flow-Guided-Video-Inpainting. pytorch implementation for "Deep Flow-Guided Video Inpainting"(CVPR'19)

facenet-pytorch. Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models

PySceneDetect. :movie_camera: Python and OpenCV-based scene cut/transition detection program & library.

fromthetransistor. From the Transistor to the Web Browser, a rough outline for a 12 week course

termshark. A terminal UI for tshark, inspired by Wireshark

Ultra-Light-Fast-Generic-Face-Detector-1MB. 💎1MB lightweight face detection model (1MB轻量级人脸检测模型)

Chainer-DeepFill. Python

3DDFA. The PyTorch improved version of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.

face-alignment. :fire: 2D and 3D Face alignment library build using pytorch

fewshot-face-translation-GAN. Generative adversarial networks integrating modules from FUNIT and SPADE for face-swapping.

react-nodegui. Build performant, native and cross-platform desktop applications with native React + powerful CSS like styling.🚀

GSCNN. Gated-Shape CNN for Semantic Segmentation (ICCV 2019)

mmagic. OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.

Chainer_Realtime_Multi-Person_Pose_Estimation. Chainer version of Realtime Multi-Person Pose Estiamtion

One_Shot_Face_Reenactment. Official test script for 2019 BMVC paper 'One-shot Face Reenactment' in PyTorch.

PyTorch-GAN. PyTorch implementations of Generative Adversarial Networks.

MUNIT. Multimodal Unsupervised Image-to-Image Translation

mobilenets-tpu. MobileNetV3 tf.keras implementation with pre-trained weights using the TPU Estimator API

face_swap. End-to-end, automatic face swapping pipeline

FUNIT. Translate images to unseen domains in the test time with few example images.

cvat. Computer Vision Annotation Tool (CVAT) is a leading platform for building high-quality visual datasets for vision AI. It offers open-source, cloud, and enterprise products, as well as labeling services, for image, video, and 3D annotation with AI-assisted labeling, quality assurance, team collaboration, analytics, and developer APIs.

imat_comp. iMaterialist (Fashion) Competition 2019

robustness. Corruption and Perturbation Robustness (ICLR 2019)

Total-Text-Dataset. Total Text Dataset. It consists of 1555 images with more than 3 different text orientations: Horizontal, Multi-Oriented, and Curved, one of a kind.

Lychee. A great looking and easy-to-use photo-management-system you can run on your server, to manage and share photos.

SCUT-FBP5500-Database-Release. A diverse benchmark database for multi-paradigm facial beauty prediction

modanet. ModaNet: A large-scale street fashion dataset with polygon annotations

EconML. ALICE (Automated Learning and Intelligence for Causation and Economics) is a Microsoft Research project aimed at applying Artificial Intelligence concepts to economic decision making. One of its goals is to build a toolkit that combines state-of-the-art machine learning techniques with econometrics in order to bring automation to complex causal inference problems. To date, the ALICE Python SDK (econml) implements orthogonal machine learning algorithms such as the double machine learning work of Chernozhukov et al. This toolkit is designed to measure the causal effect of some treatment variable(s) t on an outcome variable y, controlling for a set of features x.

mmdetection. OpenMMLab Detection Toolbox and Benchmark

stylegan-encoder. StyleGAN Encoder - converts real images to latent space

coursera-dl. Script for downloading Coursera.org videos and naming them.

tencent-ml-images. Largest multi-label image database; ResNet-101 model; 80.73% top-1 acc on ImageNet

nlp-tutorial. Natural Language Processing Tutorial for Deep Learning Researchers

face.evoLVe. 🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

PytorchSSD. pytorch version of SSD and it's enhanced methods such as RFBSSD,FSSD and RefineDet

FaceBoxes.PyTorch. A PyTorch Implementation of FaceBoxes

nsfw_data_source_urls. Collection of NSFW images URLs for the purposes of training an NSFW Image Classifier

nsfw_data_scraper. Collection of scripts to aggregate image data for the purposes of training an NSFW Image Classifier

tensorflow-yolov3. 🔥 TensorFlow Code for technical report: "YOLOv3: An Incremental Improvement"

ffhq-dataset. Flickr-Faces-HQ Dataset (FFHQ)

stylegan. StyleGAN - Official TensorFlow Implementation

CornerNet. tensorflow

ESRGAN. ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution. The training codes are in BasicSR.

PyTorch_YOLOv3. Implementation of YOLOv3 in PyTorch

ssd_keras. Port of Single Shot MultiBox Detector to Keras

nineserver. HTTP server to develop a web app in C++ easily

Inception-v4. Inception-v4, Inception - Resnet-v1 and v2 Architectures in Keras

annoy. Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk