Mingliang Dai

VideoX-Fun. 📹 A more flexible framework that can generate videos at any resolution and creates videos from images.

sanyuan-skills. Expert code review skill: SOLID, security, performance, error handling, boundary conditions

vibe-vibe. AI for All: The First Systematic Vibe Coding Tutorial | From Zero to Full-Stack, Bring Your Ideas to Life | Live at: www.vibevibe.cn ；全民AI学习第一课，首个系统化 Vibe Coding 开源教程 | 零基础到全栈实战，让人人都能借助 AI 实现自己的想法与创意 | 在线地址：www.vibevibe.cn

sglang. SGLang is a high-performance serving framework for large language models and multimodal models.

Cobra. [SIGGRAPH 2025] Official code of the paper "Cobra: Efficient Line Art COlorization with BRoAder References". Cobra：利用更广泛参考图实现高效线稿上色

ComfyUI. The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

omini-kontext. An inference and training framework for multiple image input in Flux Kontext dev

sd-scripts. Python

FramePack. Lets make video diffusion practical!

musubi-tuner. Python

Muon. Muon is an optimizer for hidden layers in neural networks

zi2zi. Learning Chinese Character style with conditional GAN

gans-awesome-applications. Curated list of awesome GAN applications and demo

awesome-computer-vision. A curated list of awesome computer vision resources

Awesome-AI. A curated list of awesome things related to artificial intelligence tools

annotated_deep_learning_paper_implementations. 🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

ImageReward. [NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

llama.cpp. LLM inference in C/C++

flux. Official inference repo for FLUX.1 models

Paints-UNDO. Understand Human Behavior to Align True Needs

diff-pdf. A simple tool for visually comparing two PDF files

segmentation_models.pytorch. Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

colorizeDiffusion. Implementation of ColorizeDiffusion

reader. Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

Image-Super-Resolution-via-Iterative-Refinement. Unofficial implementation of Image Super-Resolution via Iterative Refinement by Pytorch

gpt_academic. 为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

AnyText. Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>

anime-segmentation. high-accuracy segmentation for anime character

IC-Light. More relighting!

ArtoPIH-Painterly-Image-Harmonization. [AAAI2024] Painterly Image Harmonization by Learning from Painterly Objects

ProPIH-Painterly-Image-Harmonization. [AAAI2024] Progressive Painterly Image Harmonization from Low-level Styles to High-level Styles

RETAB-Weak-Shot-Semantic-Segmentation. Official Implementation for Weak-shot Semantic Segmentation by Transferring Semantic Affinity and Boundary (BMVC 2022)

SSP-AI-Generated-Image-Detection. The code for "A Single Simple Patch is All You Need for AI-generated Image Detection"

Awesome-Image-Blending. A curated list of papers, code and resources pertaining to image blending.

PyTorch-GAN. PyTorch implementations of Generative Adversarial Networks.

pytorch-lightning-template. An easy/swift-to-adapt PyTorch-Lighting template. 套壳模板，简单易用，稍改原来Pytorch代码，即可适配Lightning。You can translate your previous Pytorch code much easier using this template, and keep your freedom to edit all the functions as well. Big-project-friendly as well. No need to rewrite your config in hydra.

AODA. Official implementation of "Adversarial Open Domain Adaptation for Sketch-to-Photo Synthesis"(WACV 2022/CVPRW 2021)

pytorch-lr-finder. A learning rate range test implementation in PyTorch

Neural-Network-Diffusion. We introduce a novel approach for parameter generation, named neural network parameter diffusion (p-diff), which employs a standard latent diffusion model to synthesize a new set of parameters

PseCo. (CVPR 2024) Point, Segment and Count: A Generalized Framework for Object Counting

cellpose. a generalist algorithm for cellular segmentation with human-in-the-loop capabilities

jonbarron.github.io. HTML

Pointnet_Pointnet2_pytorch. PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.

talk2arxiv. Talk to any ArXiv paper using ChatGPT

fduthesis. LaTeX thesis template for Fudan University

gpt-pilot. The first real AI developer

marker. Convert PDF to markdown + JSON quickly with high accuracy

bark. 🔊 Text-Prompted Generative Audio Model

make-real. Draw a ui and make it real

tldraw. Build infinite canvas apps in React with the tldraw SDK. World's best, top-most agent recommended #1 five star SDK.

projection-conditioned-point-cloud-diffusion. Official code for "Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction" (CVPR 2023)

academicpages.github.io. Github Pages template based upon HTML and Markdown for personal, portfolio-based websites.

NotionNext. Turn your Notion workspace into a fast, customizable website. Built with Next.js + Notion API, with multi-platform deployment and no self-hosted server required.

qwerty-learner. 为键盘工作者设计的单词记忆与英语肌肉记忆锻炼软件 / Words learning and English muscle memory training software designed for keyboard workers

Fooocus. Focus on prompting and generating

dcface. Python

zh-cn. 中文版学术主页

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

CV_interviews_Q-A. CV算法岗知识点及面试问答汇总，主要分为计算机视觉、机器学习、图像处理和 C++基础四大块，一起努力向offers发起冲击！

openpifpaf. Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.

ControlNet-v1-1-nightly. Nightly release of ControlNet 1.1

UniControl. Unified Controllable Visual Generation Model

Uni-ControlNet. [NeurIPS 2023] Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

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

sd-webui-controlnet. WebUI extension for ControlNet

chat-with-gpt. An open-source ChatGPT app with a voice

crowddiff. Python

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

ControlNet. Let us control diffusion models!

RectifiedFlow. Official Implementation of Rectified Flow (ICLR2023 Spotlight)

DREAM. This is the official code repository for the paper "Deep Rank-Consistent Pyramid Model for Better Crowd Counting".

ABM. Python

ProPos. Self-Supervised Learning for Deep Clustering (TPAMI 2022)

SegNeXt. Official Pytorch implementations for "SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation" (NeurIPS 2022)

LearningToCountAnything. This is the official implementation of: Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision Michael Hobley, Victor Prisacariu

LearningToCountEverything. Python

synsin. View synthesis for the public.

pytorch-nested-unet. PyTorch implementation of UNet++ (Nested U-Net).

DeepLearning-500-questions. 深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06

fucking-algorithm. Crack LeetCode, not only how, but also why.

tiler. 👷 Build images with images

Bayesian-Crowd-Counting. Official Implement of ICCV 2019 oral paper Bayesian Loss for Crowd Count Estimation with Point Supervision

Boosting-Crowd-Counting-via-Multifaceted-Attention. Official Implement of CVPR 2022 paper 'Boosting Crowd Counting via Multifaceted Attention'

awesome. 😎 Awesome lists about all kinds of interesting topics

fudan_sports_autoreserve. 复旦大学体育场馆自动预约 FDU Sports Auto Reserve

S-DCNet. Implementaion of S-DCNet (ICCV 2019)

PromptPapers. Must-read papers on prompt-based tuning for pre-trained language models.

byol-pytorch. Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch

deepmind-research. This repository contains implementations and illustrative code to accompany DeepMind publications

BooksKeeper. 对各类图书资源的收集。大量计算机、AI方面书籍。

awesome-AI-books. Some awesome AI related books and pdfs for learning and downloading, also apply some playground models for learning

PaintTransformer. Official PaddlePaddle implementation of Paint Transformer

Awesome-Crowd-Counting. Awesome Crowd Counting

nndl-practice. 邱锡鹏《神经网络与深度学习：案例与实践》PyTorch 实现

pytorch-zssr. PyTorch implementation of 1712.06087 "Zero-Shot" Super-Resolution using Deep Internal Learning

ZSSR. "Zero-Shot" Super-Resolution using Deep Internal Learning

Uformer. [CVPR 2022] Official implementation of the paper "Uformer: A General U-Shaped Transformer for Image Restoration".

TransGAN. [NeurIPS‘2021] "TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up", Yifan Jiang, Shiyu Chang, Zhangyang Wang

TTSR. [CVPR'20] TTSR: Learning Texture Transformer Network for Image Super-Resolution

DASR. [CVPR 2021] Unsupervised Degradation Representation Learning for Blind Super-Resolution

vit-pytorch. Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

XMU-Daily-Health-Report. Small script for automated health reporting

pytorch-cnn-visualizations. Pytorch implementation of convolutional neural network visualization techniques

Vine. Python

RDN. Torch code for our CVPR 2018 paper "Residual Dense Network for Image Super-Resolution" (Spotlight)

PISR. An official implementation of "Learning with Privileged Information for Efficient Image Super-Resolution" (ECCV2020) in PyTorch.

WeightNet. Python

attention-transfer. Improving Convolutional Networks via Attention Transfer (ICLR 2017)

PAN. (ECCV2020 Workshops) Efficient Image Super-Resolution Using Pixel Attention.

pytorch-OpCounter. Count the MACs / FLOPs of your PyTorch model.

Awesome-Super-Resolution. A curated list of awesome super-resolution resources.

tensorboardX. tensorboard for pytorch (and chainer, mxnet, numpy, ...)

EDSR-PyTorch. PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)

RCAN. PyTorch code for our ECCV 2018 paper "Image Super-Resolution Using Very Deep Residual Channel Attention Networks"

STR. Soft Threshold Weight Reparameterization for Learnable Sparsity

char-rnn.pytorch. PyTorch implementation of char-rnn (character-level language model)

google-research. Google Research

hyperledger. A collection of learning materials on Blockchain, Hyperledger, Ethereum, Solana, and IPFS.

go-ethereum. Go implementation of the Ethereum protocol

disksim-4-0-x64. C

dirichlet. Dirichlet MLE python library

FedMA. Code for Federated Learning with Matched Averaging, ICLR 2020.

dragon-book-exercise-answers. Compilers Principles, Techniques, & Tools (purple dragon book) second edition exercise answers. 编译原理（紫龙书）第2版习题答案。

bitcoin. Bitcoin Core integration/staging tree

2019nCoV_EID. R

FedProx. Federated Optimization in Heterogeneous Networks (MLSys '20)

webrtc. https://github.com/wangduanduan/wangduanduan.github.io/issues/241

privacy. Library for training machine learning models with privacy for training data

leaf. Leaf: A Benchmark for Federated Settings

private-ai. Repo for Udacity's Secure & Private AI course

medical-data.

machine-learning-diff-private-federated-learning. Simulate a federated setting and run differentially private federated learning.

High-quality-ellipse-detection. A high-quality ellipse detector based on arc-support line segments which can both accurately and efficiently detect ellipses in images.

EvaluatingDPML. This project's goal is to evaluate the privacy leakage of differentially private machine learning models.

shadowart_ai_experiment. HTML

four_flower. 使用tensorflow和cnn做的图像识别，对四种花进行了分类。

SNH. Java

pexpr. Evaluate results given by math expressions or export them as latex format