tao liu

UniRL. UniRL is a Framework for Unified Multimodal Model Reinforcement Learning

ideogram4. Ideogram 4: Open image model at the forefront of design

Qwen-Image-Bench. Python

xDiT. xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

FastGen. NVIDIA FastGen: Fast Generation from Diffusion Models

AnyFlow. Flow Map OPD for AnyStep Video Diffusion

Anchor-Forcing. [ECCV2026] Anchor Forcing is a cache-centric framework for interactive streaming video generation that preserves visual quality and coherent motion across prompt switches

LeapAlign_Code. [CVPR2026] LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories

SP-Ctrl. The official implementation of paper "Rethink Sparse Signals for Pose-guided Text-to-image Generation", accepted by ICCV 2025.

NiT. [NeurIPS 2025] Native-resolution diffusion Transformer

MoVieS. [CVPR 2026] Official implementation of "MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second".

kiuikit. A niche toolkit for computer vision and more.

brats-e1d3. E1D3 U-Net for Brain Tumor Segmentation

Cycle3D. [AAAI 2025🔥] Official implementation of Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle

spad. Code for SPAD : Spatially Aware Multiview Diffusers, CVPR 2024

semantic-progress-function. Official implementation of "Video Analysis and Generation via a Semantic Progress Function"

1Prompt1Story. 🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt

Flow-OPD. Official Repo of "Flow-OPD: On-Policy Distillation for Flow Matching Models"

PAE. Official Implementation of "What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion"

neo-unify. Toy-scale unified multimodal model experiments — encoder-free understanding & generation with Mixture-of-Transformers on MLX/Apple Silicon

HiDream-O1-Image. Python

rcm. rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale

HY-SOAR. HY-SOAR:Self-Correction for Optimal Alignment and Refinement in Diffusion Models

Adaptive-Video-Distillation. official code repository of 《Adaptive Video Distillation: Mitigating Oversaturation and Temporal Collapse in Few-Step Generation》

CDM. Continuous-Time Distribution Matching for Few-Step Diffusion Distillation👏

TwinFlow. [ICLR 2026] Taming large-scale few-step training with self-adversarial flows! 👏🏻

D-OPSD. Official Repo of "D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models"

DDT. [CVPR 2026] DDT: Decoupled Diffusion Transformer

SpatialEdit. [Official Repo] SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing

Web. 千古前端图文教程，超详细的前端入门到进阶知识库。从零开始学前端，做一名精致优雅的前端工程师。

Qwen. The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

threestudio. A unified framework for 3D content generation.

Reward-Forcing. [CVPR 2026 Highlight] Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation

MeanFlow. PyTorch implementation of MeanFlow & iMF (one-step generative modeling).

SiD. PyTorch code and model checkpoints for Score identity Distillation (SiD) and its adversarial version (SiDA)

DanceGRPO. An official implementation of DanceGRPO: Unleashing GRPO on Visual Generation

OneReward. Python

MixGRPO. [ECCV 2026] MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE

TempFlow-GRPO. [ICLR 26] TempFlow-GRPO (Temporal Flow GRPO), a principled GRPO framework that captures and exploits the temporal structure inherent in flow-based generation.

banana-slides. 一个基于nano banana pro🍌的原生AI PPT生成应用，迈向＂Vibe PPT＂; 支持上传任意模板图片，上传任意素材&智能解析，一句话/大纲/页面描述自动生成PPT，口头修改指定区域、一键导出可编辑ppt - An AI-native slides generator based on nano banana pro🍌

LongCat-Image. Python

UniWorld. UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

FlowEdit. Official implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models"

EditMGT. Official Repo for Paper <EditMGT Unleashing the Potential of Masked Generative Transformer in Image Editing>

Qwen-Image-Layered. Qwen-Image-Layered: Layered Decomposition for Inherent Editablity

DiffusionNFT. [ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

flow_grpo. [NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

Step1X-Edit. A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.

nk-diffusion. Jupyter Notebook

Z-Image. Python

REPA-E. [ICCV 2025] Official implementation of the paper: REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers

Cradle2Cane. (NeurIPS 2025) From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging

Cradle2Cane. （NeurIPS 2025) From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging

Lumina-DiMOO. Lumina-DiMOO - An Open-Sourced Multi-Modal Large Diffusion Language Model

AnthropomorphicIntelligence. Advancing AI by embracing human-likeness for better AI understanding, human–AI collaboration, and social simulation, bridging technology and genuine human experience.

Chain-of-Zoom. [NeurIPS'25 Spotlight] Official repository for "Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment"

Bagel. Open-source unified multimodal model

Loopfree. [CVPR2025] Official Implementations "One-Way Ticket : Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Models"

RPG-DiffusionMaster. [ICML 2024] Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs (RPG)

Awesome-Graphic-Design.

Awesome-Layout-Generation. Awesome Layout Generation

consistory. Python

MiVOLO. MiVOLO age & gender transformer neural network

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

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

arcface-pytorch. Python

CodeFormer. [NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

share. Python

Awesome-Image-Editing. A Survey of Image Editing

1Prompt1Story.github.io. Python

InterLCM. [ICLR2025] Official Implementations "InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration"

ToMe. [NeurIPS 2024] Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis

1Prompt1Story. (ICLR 2025 Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt

IC-Light. More relighting!

deepface. A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python

awesome-diffusion-categorized. collection of diffusion model papers categorized by their subareas

openvino_num. C++

CasPL. Python

mar. PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

Emu3. Next-Token Prediction is All You Need

stable-video-diffusion-colab. Jupyter Notebook

stable-video-diffusion-img2vid. Jupyter Notebook

ID-Preserving-Facial-Aging. Identity-Preserving Aging of Face Images via Latent Diffusion Models [IJCB 2023]

FADING. Python

v2ray-rules-dat. 🦄 🎃 👻 V2Ray 路由规则文件加强版，可代替 V2Ray 官方 geoip.dat 和 geosite.dat，适用于 V2Ray、Xray-core、mihomo(Clash-Meta)、hysteria、Trojan-Go 和 leaf。Enhanced edition of V2Ray rules dat files, applicable to V2Ray, Xray-core, mihomo(Clash-Meta), hysteria, Trojan-Go and leaf.

e4t-diffusion. Implementation of Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models

GrabCut. C++

VAR. [NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

InstantStyle. InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation 🔥

StoryGen. [CVPR 2024] Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models

adversarial-diffusion-distillation. My Implementation of Adversarial Diffusion Distillation https://arxiv.org/pdf/2311.17042.pdf

SuppressEOT. Official Implementations "Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models" (ICLR2024)

rcg. PyTorch implementation of RCG https://arxiv.org/abs/2312.03701

prompt-to-prompt. Jupyter Notebook

ImageWarping. C++

Faster-Diffusion. [NeurIPS 2024] Official implementation of "Faster Diffusion: Rethinking the Role of UNet Encoder in Diffusion Models"

CLIP. CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

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

StyleDiffusion. Official Implementations "StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing" (CVMJ2024)

CSLabInfo2023. 关于2023年CS保研实验室/导师招生广告的汇总。欢迎想要打广告的小伙伴积极PR，资瓷一下互联网精神吼不吼啊？

GrabCut. An implementation of http://dl.acm.org/citation.cfm?id=1015720

CSYuTuiMian2023. Python

CSSummerCamp2023. Python

zhao. 【编程随想】整理的《太子党关系网络》，专门揭露赵国的权贵

U2PL. [CVPR'22 & IJCV'24] Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels & Using Unreliable Pseudo-Labels for Label-Efficient Semantic Segmentation

iRingo. 解锁完整的 Apple功能和集成服务

machine-learning-roadmap. A roadmap connecting many of the most important concepts in machine learning, how to learn them and what tools to use to perform them.

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

gaohaoyang.github.io. blog & blog theme🤘

qiubaiying.github.io. BY Blog ->

yolov7_d2. 🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥

Handwritten-Digit-Recognition-using-Deep-Learning. Handwritten Digit Recognition using Machine Learning and Deep Learning

zju-icicles. 浙江大学课程攻略共享计划

Livox-SDK. Drivers for receiving LiDAR data and more, support Lidar Mid-40, Mid-70, Tele-15, Horizon, Avia.

ACSC. Automatic Calibration for Non-repetitive Scanning Solid-State LiDAR and Camera Systems

Camera-lidar-joint-calibration. A sample way to jointly calibrate camera and lidar

Practical-Ethical-Hacking-Resources. Compilation of Resources from TCM's Practical Ethical Hacking Udemy Course

livox_camera_lidar_calibration. Calibrate the extrinsic parameters between Livox LiDAR and camera

CheapSteam. Cheap Steam 为您提供 STEAM 与 BUFF 的饰品价格对比数据.

RM2021_simulation. RM2021 赛季 RMUC 模拟器开源资料

netflix-verify. 流媒体NetFlix解锁检测脚本 / A script used to determine whether your network can watch native Netflix movies or not

freeCodeCamp. freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.

Harry-hhj.github.io. A personal blog for sharing knowledges and experience.

yolor. implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)

yolov5. Ultralytics YOLOv5 in PyTorch > ONNX > CoreML > TFLite

rufus. The Reliable USB Formatting Utility

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/

linux-wifi-hotspot. Feature-rich wifi hotspot creator for Linux which provides both GUI and command-line interface. It is also able to create a hotspot using the same wifi card which is connected to an AP already ( Similar to Windows 10).

LCR_sjtu. 上海交通大学云汉交龙战队21赛季雷达站程序开源

Deep-Learning-21-Examples. 《21个项目玩转深度学习———基于TensorFlow的实践详解》配套代码

Hearthstone-Hearthbuddy. Hearthstone 炉石传说 Hearthbuddy 炉石兄弟

editor. The official Code in the Dark editor

DeepLearning. Python for《Deep Learning》，该书为《深度学习》(花书) 数学推导、原理剖析与源码级别代码实现

ailearning. AiLearning：数据分析+机器学习实战+线性代数+PyTorch+NLTK+TF2

referee_serial_port_protocol. 裁判系统串口协议文档以及示例程序

labelImg. LabelImg is now part of the Label Studio community. The popular image annotation tool created by Tzutalin is no longer actively being developed, but you can check out Label Studio, the open source data labeling tool for images, text, hypertext, audio, video and time-series data.

imgaug. Image augmentation for machine learning experiments.

Data-Structres. 浙江大学《数据结构》上课笔记 + 数据结构实现 + 课后题题解

CudaSift. A CUDA implementation of SIFT for NVidia GPUs (1.2 ms on a GTX 1060)

cmake-examples. Useful CMake Examples

binocular_stereo_vision. 存放之前使用c++编写的双目立体视觉三维重建的相关代码和文件

Binocular-vision-ranging. 通过双目视觉测距

SJTU-RM-CV-2019. 上海交通大学 RoboMaster 2019赛季 视觉代码

Shawn_pose_estimation_by_opencv. This is my initial experiments on pose estimation using opencv.More details:http://www.cnblogs.com/singlex/p/pose_estimation_0.html

leetcode-master. 《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀

PAT-Advanced-Level. Solutions to PAT💯