zhangp365

zvec. A lightweight, lightning-fast, in-process vector database

texmath. A Haskell library for converting LaTeX math to MathML.

guanlan. 观澜（GuānLán）是一个基于 Karpathy LLM Wiki 模式的本地知识库项目：它让 LLM Agent 把原始资料增量“编译”为结构化、互相链接、可持续维护的 Markdown Wiki。

SCAIL. SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations (CVPR 2026 Findings)

Z-Image. Python

FlashVSR. [CVPR 2026] Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny conditional decoder.

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

Annual_meeting_lottery. 年会抽奖系统

mcp-run-python-code. Python interpreter, MCP server, no API key, free. Get results from running Python code. Python代码解释器MCP，功能包括：执行python代码，运行python库安装，运行python脚本。

SeedVR. Repo for SeedVR2 (ICLR2026) & SeedVR (CVPR2025 Highlight)

ComfyUI-SeedVR2_VideoUpscaler. Official SeedVR2 Video Upscaler for ComfyUI

AniCrafter. [ACM MM 2026] AniCrafter: Customizing Realistic Human-Centric Animation via Avatar-Background Conditioning in Video Diffusion Models

Paints-UNDO. Understand Human Behavior to Align True Needs

XVerse. [NeurIPS 2025] Official implementation of "XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation".

VRAG. Multimodal Retrieval-augmented Generation Framework Built by Tongyi Lab, Alibaba Group.

DreamO. [SIGGRAPH Asia 2025] DreamO: A Unified Framework for Image Customization

FramePack. Lets make video diffusion practical!

ComfyUI-easycontrol. Python

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

ComfyUI-UNO. Python

EasyControl. Implementation of "EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer"(ICCV2025)

ComfyUI-Gemini_Flash_2.0_Exp. A ComfyUI custom node that integrates Google's Gemini Flash 2.0 Experimental model, enabling multimodal analysis of text, images, video frames, and audio directly within ComfyUI workflows.

x-flux. Python

ComfyUI-Frame-Interpolation. A custom node set for Video Frame Interpolation in ComfyUI.

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

ComfyUI_PuLID_Flux_ll. Python

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

ComfyUI-XLA. ComfyUI for XLA devices for TPUs/GPUs

LLaVA-o1.

PhotoMaker. PhotoMaker [CVPR 2024]

Pyramid-Flow. [ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling

ComfyUI-PyramidFlowWrapper. Python

animatediff-controlnet. add a controlnet to animatediff to animate a given image

mochi. The best OSS video generation models, created by Genmo

flux. Official inference repo for FLUX.1 models

taming-transformers. Taming Transformers for High-Resolution Image Synthesis

ComfyUI_LayerStyle. A set of nodes for ComfyUI that can composite layer and mask to achieve Photoshop like functionality.

ComfyUI-Advanced-ControlNet. ControlNet scheduling and masking nodes with sliding context support

ComfyUI-Video-Matting. A minimalistic implementation of Robust Video Matting (RVM) and BRAIAI-RVMBG v1.4 in ComfyUI

ControlNetPlus. ControlNet++: All-in-one ControlNet for image generations and editing!

PuLID. [NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment

comfyui_controlnet_aux. ComfyUI's ControlNet Auxiliary Preprocessors

ComfyUI_IPAdapter_plus. Python

IC-Light. More relighting!

stable-fast. https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.

CharacterFaceSwap. Python

MedicalGPT. MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。

Real-ESRGAN. Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

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

ComfyUI-text-overlay. Overlay text on an image in ComfyUI with font/alignment/placement customization

ComfyUI_Custom_Nodes_AlekPet. Custom nodes that extend the capabilities of Comfyui

Fooocus. Focus on prompting and generating

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

AIGODLIKE-ComfyUI-Translation. A plugin for multilingual translation of ComfyUI，This plugin implements translation of resident menu bar/search bar/right-click context menu/node, etc

ComfyUI-VideoHelperSuite. Nodes related to video workflows

pycorrector. pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，Qwen2.5等模型应用在纠错场景，开箱即用。

chatglm.cpp. C++ implementation of ChatGLM-6B & ChatGLM2-6B

chatglm.cpp. C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)

stable-diffusion-webui-docker. Easy Docker setup for Stable Diffusion with user-friendly UI