LoRA Loader for Nunchaku Qwen Image on ComfyUI

MSST-GUI is a Qt5-based inference GUI, designed to provide a convenient and intuitive way to inference (mainly for my own use)

Object-oriented handling of audio data, with GPU-powered augmentations, and more.

All the tools you need to save images with their generation metadata on ComfyUI. Compatible with Civitai & Prompthero geninfo auto-detection. Works with png, jpeg and webp.

使用IndexTTS模型在ComfyUI中实现高质量文本到语音转换的自定义节点。支持中文和英文文本，可以基于参考音频复刻声音特征。

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

Simple GUI for training LoRA on Wan 2.1 models using musubi-tuner.

哔哩下载姬downYuanh，哔哩哔哩网站视频下载工具，支持批量下载，支持8K、HDR、杜比视界，提供工具箱（音视频提取、去水印等）。

[Preprint 2025] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

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, BiRefN…

Run Segformer at lightning speed for image or video segmentation / 以极快的速度运行 Segformer 模型进行图像或视频内容分割

Real-Time Diffusion-Based Streaming Video Super-Resolution / 基于Diffusion架构的实时视频流超分模型

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation.

A powerful OCR node for ComfyUI that integrates the DeepSeek-OCR model from Hugging Face.

Contexts Optical Compression

MoCha: End-to-End Video Character Replacement without Structural Guidance

DFloat11: Lossless LLM Compression for Efficient GPU Inference

Fork of the official DF11 ComfyUI custom node that aims to support other model architectures (currently only Flux-Schnell and Chroma), and support loading existing DF11 models that were originally …

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 de…

Comfyui implementation of OpenIXCLab Sec-4B

ComfyUI-QwenVL custom node integrates the Qwen-VL series, including the latest Qwen3-VL models, including Qwen2.5-VL and the latest Qwen3-VL, to enable advanced multimodal AI for text generation, i…

The successful integration of Qwen3-VL-Instruct series into the ComfyUI platform has enabled a smooth operation, supporting (but not limited to) text-based queries, video queries, single-image quer…

A simple node that can dynamically adjust the reserved memory of a workflow in real-time, used to avoid the utilization of shared memory.

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

Custom nodes that bring Character.AI's Ovi video+audio generator to ComfyUI with streamlined setup, selectable precision, attention-backend control, and per-node device targeting for multi-GPU rigs.

New Front-end of ComfyUI-Easy-Use

Kolors Team

GGUF Quantization support for native ComfyUI models