Chengxi Guo

the-art-of-debugging. The Art of Debugging Open Book

dailypaper-skills. 用Agent skills打造我的论文流水线

ungguf. GGUF -> Safetensor converter

ASI-Evolve. Python

frequencylaw. Official repository for textual frequency law

smolvlm-realtime-webcam. Real-time webcam demo with SmolVLM and llama.cpp server

lobehub. 🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

LangBot. Production-grade platform for building agentic IM bots - 生产级多平台智能机器人开发平台/ Agent、知识库编排、插件系统 / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信, 企微智能机器人, 公众号) / 飞书 / 钉钉 / QQ / Matrix e.g. Integrated with ChatGPT(GPT), DeepSeek, Dify, n8n, Langflow, Coze, Claude, Gemini, GLM, Ollama, SiliconFlow, Moonshot, openclaw / hermes agent, deerflow

agent-lightning. The absolute trainer to light up AI agents.

lerobot. 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

SSDD. Official implementation for SSDD Single-Step Diffusion Decoder for Efficient Image Tokenization.

so-novel. 小说下载｜网文下载 | 网络小说

xiaohongshu-mcp. MCP for xiaohongshu.com

UNO. [ICCV 2025] 🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning

diffusion-4k. [CVPR 2025] Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models

FlexControl.

UniVRM. UniVRM is a gltf-based VRM format implementation for Unity. English is here https://vrm.dev/en/ . 日本語 はこちら https://vrm.dev/

Wan2.1. Wan: Open and Advanced Large-Scale Video Generative Models

ThinkPO. Python

DeepEP. DeepEP: an efficient expert-parallel communication library

yolov12. [NeurIPS 2025] YOLOv12: Attention-Centric Real-Time Object Detectors

Awesome-LLM-Judges. ⚖️ Awesome LLM Judges ⚖️

MetaGPT. 🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

JudgeBench. Python

dify. Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

lm-evaluation-harness. A framework for few-shot evaluation of language models.

opik. Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

danbooru-tag-tree. A tag tree for getting a group of tags or checking what group a tag in

diffusion-pipe. A pipeline parallel training script for diffusion models.

StableAnimator. [CVPR2025] We present StableAnimator, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without any post-processing, conditioned on a reference image and a sequence of poses.

ComfyUI-RMBG. A ComfyUI custom node designed for advanced image background removal and object, face, clothes, and fashion segmentation, utilizing multiple models including RMBG-2.0, INSPYRENET, BEN, BEN2, BiRefNet, SDMatte, SAM, SAM2, SAM3 and GroundingDINO.

SystemAnimatorOnline. XR Animator, AI-based Full Body Motion Capture and Extended Reality (XR) solution, powered by System Animator Online

RF-Inversion. Rectified Flow Inversion (RF-Inversion) - ICLR 2025

Weylus. Use your tablet as graphic tablet/touch screen on your computer.

Graphite. Community-built comprehensive 2D content creation appplication for graphic design, digital art, and interactive real-time motion graphics powered by a node-based procedural graphics engine

ctrlora. [ICLR 2025] Codebase for "CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation"

krita-ai-diffusion. Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required.

Animate-X. [ICLR 2025] Animate-X - PyTorch Implementation

ComfyUI-PyramidFlowWrapper. Python

comfyui-flux-accelerator. Accelerates Flux.1 image generation, just by using this node.

models. All my self trained & released AI upscaling models. After gathering and applying over 600 different upscaling models, I learned how to train my own models, and these are the results.

pose-depot. A collection of ControlNet poses

lora-scripts. SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.

Neural_Gaffer. [NeurIPS 2024] Official code for "Neural Gaffer: Relighting Any Object via Diffusion"

PhotoPoster. To support and further the research in the field of portrait animation , we are excited to launch PhotoPoster, an open project for pose-driven image generation.

speech-to-speech. Build local voice agents with open-source models

ControlNeXt. Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA

argilla. Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets

style-transfer-comfyui-workflow. A style transfer testing workflow for ComfyUI. Made with 💚 by the CozyMantis squad.

StabilityMatrix. Multi-Platform Package Manager for Stable Diffusion

PhotoMaker. PhotoMaker [CVPR 2024]

public-apis. A collective list of free APIs

Kolors. Kolors Team

pyramidinfer. Python

PowerInfer. High-speed Large Language Model Serving for Local Deployment

AsyncDiff. [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising

ComfyUI_densediffusion. DenseDiffusion custom node for ComfyUI

InstanceDiffusion. [CVPR 2024] Code release for "InstanceDiffusion: Instance-level Control for Image Generation"

redka. Redis re-implemented with SQL

seed-tts-eval. Python

ComfyUI_omost. ComfyUI implementation of Omost

Omost. Your image is almost there!

ComfyUI-3D-Pack. An extensive node suite that enables ComfyUI to process 3D inputs (Mesh & UV Texture, etc) using cutting edge algorithms (3DGS, NeRF, etc.)

Phased-Consistency-Model. [NeurIPS 2024] Boosting the performance of consistency models with PCM!

ComfyUI-Easy-Use. In order to make it easier to use the ComfyUI, I have made some optimizations and integrations to some commonly used nodes.

MetaCLIP. NeurIPS 2025 Spotlight; ICLR2024 Spotlight; CVPR 2024; EMNLP 2024

ICLR24. Official code for ICLR 2024 paper, "A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation"

FT-CLIP. CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet

IC-Light. More relighting!

ChatTTS. A generative speech model for daily dialogue.

comfyui-inpaint-nodes. Nodes for better inpainting with ComfyUI: Fooocus inpaint model for SDXL, LaMa, MAT, and various other tools for pre-filling inpaint & outpaint areas.

streaming. A Data Streaming Library for Efficient Neural Network Training

open-tts-tracker.

ComfyUI-PuLID-ZHO. Unofficial implementation of PuLID（diffusers） for ComfyUI

Awesome-Chinese-LLM. 整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

ComfyUI_InstantID. Python

Comfyui-Yolov8. Python

APISR. APISR: Anime Production Inspired Real-World Anime Super-Resolution (CVPR 2024)

Face-Upscalers-ONNX. ONNX-Powered Inference for State-of-the-Art Face Upscalers

ComfyUI-AnimateAnyone-Evolved. Improved AnimateAnyone implementation that allows you to use the opse image sequence and reference image to generate stylized video

AnimateLCM. [SIGGRAPH ASIA 2024 TCS] AnimateLCM: Computation-Efficient Personalized Style Video Generation without Personalized Video Data

fastdup. fastdup is a powerful, free tool designed to rapidly generate valuable insights from image and video datasets. It helps enhance the quality of both images and labels, while significantly reducing data operation costs, all with unmatched scalability.

OpenMoE. A family of open-sourced Mixture-of-Experts (MoE) Large Language Models

VIRL. (ECCV 2024) Code for V-IRL: Grounding Virtual Intelligence in Real Life

CapHuman. [CVPR2024] CapHuman: Capture Your Moments in Parallel Universes

LLM-Uncertainty-Bench. Benchmarking LLMs via Uncertainty Quantification

X-Pose. [ECCV 2024] Official implementation of the paper "X-Pose: Detecting Any Keypoints"

HierSpeechpp. The official implementation of HierSpeech++

axolotl. Go ahead and axolotl questions

Moore-AnimateAnyone. Character Animation (AnimateAnyone, Face Reenactment)

Focus-on-Your-Instruction. [CVPR 2024] Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention Modulation

TinyLlama. The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

VCoder. [CVPR 2024] VCoder: Versatile Vision Encoders for Multimodal Large Language Models

CartoonSegmentation. Instance segmentation for cartoon/anime characters and some visual techniques building around it.

TheChosenOne. Unofficial implementation of the paper "The Chosen One: Consistent Characters in Text-to-Image Diffusion Models"

Awesome-Video-Datasets. Video datasets

litgpt. 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Open-AnimateAnyone. Unofficial Implementation of Animate Anyone

CritiqueLLM. Python

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

RobustVideoMatting. Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

OpenVoice. Instant voice cloning by MIT and MyShell. Audio foundation model.

efficientspeech. PyTorch code implementation of EfficientSpeech - to be presented at ICASSP2023.

Matcha-TTS. [ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching

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

distilabel. Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

swift-chat. Mac app to demonstrate swift-transformers

llm-viz. 3D Visualization of an GPT-style LLM

FIREBALL. Home of FIREBALL: A Dataset of Dungeons and Dragons Actual-Play with Structured Game State Information (ACL 2023)

LLM-Agent-Paper-List. The paper list of the 86-page SCIS cover paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

PixivUtil2. Download images from Pixiv and more!

GenAI_LLM_timeline. ChatGPT, GenerativeAI and LLMs Timeline

VALL-E-X. An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/

VITS-fast-fine-tuning. This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion

PokemonRedExperiments. Playing Pokemon Red with Reinforcement Learning

LanguageAgentTreeSearch. [ICML 2024] Official repository for "Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models"

sd-webui-EasyPhoto. 📷 EasyPhoto | Your Smart AI Photo Generator.

agents. An Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents

exllamav2. A fast inference library for running LLMs locally on modern consumer-class GPUs

LLaSM. 第一个支持中英文双语语音-文本多模态对话的开源可商用对话模型。便捷的语音输入将大幅改善以文本为输入的大模型的使用体验，同时避免了基于 ASR 解决方案的繁琐流程以及可能引入的错误。

SoTaNa. Jupyter Notebook

MultiCapCLIP. (ACL'2023) MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning

MockingBird. 🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time

audiocraft_plus. Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

Platypus. Code for fine-tuning Platypus fam LLMs using LoRA

AgentBench. A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

generative_agents. Generative Agents: Interactive Simulacra of Human Behavior

gpt-researcher. An autonomous agent that conducts deep research on any data using any LLM providers

awesome-talking-head-generation.

LMOps. General technology for enabling AI capabilities w/ LLMs and MLLMs

SadTalker. [CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

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

RecurrentGPT. Official Code for Paper: RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text

gchar. Crawler and cleaner of data for novelai embedding's training

llama.onnx. LLaMa/RWKV onnx models, quantization and testcase

MOSS. An open-source tool-augmented conversational language model from Fudan University

FlagInstruct.

textgen. Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.

Inpaint-Anything. Inpaint anything using Segment Anything and inpainting models.

RRHF. [NIPS2023] RRHF & Wombat

JARVIS. JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

musiclm-pytorch. Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch

ChatGLM-Tuning. 基于ChatGLM-6B + LoRA的Fintune方案

visual-openllm. something like visual-chatgpt, 文心一言的开源版

ChatPaper. Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复

ChatGLM-6B. ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

minimal-llama. Python

llama_infer. Inference script for Meta's LLaMA models using Hugging Face wrapper

pix2pix. Image-to-image translation with conditional adversarial nets

stable-diffusion-webui. Stable Diffusion web UI

ControlNet. Let us control diffusion models!

attrs. Python Classes Without Boilerplate

cattrs. Composable custom class converters for attrs, dataclasses and friends.

Robyn. Robyn is a Super Fast Async Python Web Framework with a Rust runtime.

PPHC. 📙《高并发的哲学原理》开源图书（CC BY-NC-ND）https://pphc.lvwenhan.com

trlx. A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

bitsandbytes. Accessible large language models via k-bit quantization for PyTorch.

PaLM-rlhf-pytorch. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

transformers_tasks. ⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.

safetensors. Simple, safe way to store and distribute tensors

rust-bert. Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)

promptsource. Toolkit for creating, sharing and using natural language prompts.

flash-linux0.11-talk. 你管这破玩意叫操作系统源码 — 像小说一样品读 Linux 0.11 核心代码

pinyin-ime. Pinyin IME with rust - 拼音输入法rust版

rime-ice. Rime 配置：雾凇拼音 | 长期维护的简体词库

prompt-to-prompt. Jupyter Notebook

stable-diffusion-streamlit. Quantized stable-diffusion cutting down memory 75%, testing in streamlit, deploying in container

sentence-transformers-tf. sentence-transformers with tensorflow

awesome-sanic. A curated list of awesome Sanic resources and extensions

citybound. A work-in-progress, open-source, multi-player city simulation game.

wezterm. A GPU-accelerated cross-platform terminal emulator and multiplexer written by @wez and implemented in Rust

fastgpt. ⚡ boost inference speed of GPT models in transformers by onnxruntime

evaluate. 🤗 Evaluate: A library for easily evaluating machine learning models and datasets.

motan-go. The golang implementation of Motan

Fengshenbang-LM. Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

ChineseSTS. 中文文本语义相似度（Chinese Semantic Text Similarity）语料库建设

sanic. Accelerate your web app development | Build fast. Run fast.

rustpad. Efficient and minimal collaborative code editor, self-hosted, no database required

ColossalAI. Making large AI models cheaper, faster and more accessible

lightseq. LightSeq: A High Performance Library for Sequence Processing and Generation

avvvatars. Beautifully crafted unique avatar placeholder for your next react project

ElectronBot. C

poetry. Python packaging and dependency management made easy

gotop. A terminal based graphical activity monitor inspired by gtop and vtop

magic. CSS3 Animations with special effects

awesome-robotics. A list of awesome Robotics resources

wukong-robot. 🤖 wukong-robot 是一个简单、灵活、优雅的中文语音对话机器人/智能音箱项目，支持ChatGPT多轮对话能力，还可能是首个支持脑机交互的开源智能音箱项目。

openrave. Open Robotics Automation Virtual Environment: An environment for testing, developing, and deploying robotics motion planning algorithms.

Auto-CLUD. 一键运行 中文语言理解测评基准 CLUE 任务

CoSENT. 比Sentence-BERT更有效的句向量方案

best_AI_papers_2021. A curated list of the latest breakthroughs in AI (in 2021) by release date with a clear video explanation, link to a more in-depth article, and code.

spark-sklearn. (Deprecated) Scikit-learn integration package for Apache Spark

mujoco. Multi-Joint dynamics with Contact. A general purpose physics simulator.

ml-agents. The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.

minerl. MineRL Competition for Sample Efficient Reinforcement Learning - Python Package

rocket-recycling. Rocket-recycling with Reinforcement Learning

automa. A browser extension for automating your browser by connecting blocks

extendedsamplecharacter-dontstarvetogether. A template character mod for Don't Starve Together

SinglepassTextCluster. SinglepassTextCluster, an TextCluster tools based on Singlepass cluster algorithm that use tfidf vector and doc2vec，which can be used for individual real-time corpus cluster task。基于single-pass算法思想的自动文本聚类小组件，内置tfidf和doc2vec两种文本向量方法，可自动输出聚类数目、类簇文档集合和簇类大小，用于自有实时数据的聚类任务。

secguide. 面向开发人员梳理的代码安全指南