ComfyUI Custom Extensions
Browse 9,446 ComfyUI extensions and 73,215 custom nodes.
ComfyUI custom nodes and startup patches for GPU-resident model loading and sticky VRAM residency
Spectrum-style hidden-state forecasting patcher for native ComfyUI Qwen Image-family models.
FLUX.2 high-resolution drift correction and ComfyUI node pack
NODES: Get Prompt_Id, Success Callback get comfyui task id and Callback for successful image generation, in conjunction with the back-end
Save and switch whole-workflow states: node bypass/mode AND widget parameter values, in one click.
Universal Load/Save nodes for conditioning and latent data with enhanced compatibility across different sessions and applications.
Preserve image quality with flux-kontext-diff-merge. This ComfyUI node merges only changed areas from AI edits, ensuring clarity and detail.
A lot of custom nodes for ComfyUI are really just bindings to HuggingFace Diffusers and/or Transformers, but overly constrained to use them in very particular ways.
Fast and regularized Flow Matching and Diffusion samplers (Flow-WLS Savitzky-Golay multistep, CAB-2..6, and high-order DPM++ solvers) achieving stable few-step generation in 10 steps with zero artifacts.
Utility, text, logic, and image helper nodes for ComfyUI with updated IO typing and safer script evaluation.
把 MiniMax H3 Extender 的 Motion Context 续接能力与 SelfLift 双分辨率采样合成一个 ComfyUI 节点:低分辨率 Euler 前缀 → 干净端点预测 → 伪影感知一致性提升 → 高分辨率 Euler 后缀,段间完整保留 Motion Context 的时间连续性。以只读方式桥接两个姊妹包,不修改、不内置、不随包分发它们。附带中文界面、草稿/逐段成片实时预览、可选语义桥、外接 SIGMAS、二采专用模型、条件卡提示词只读/编辑、逐段输入集合节点,以及参考图打包与成片导出配套节点。
The SwD Preset Selector is a custom node for ComfyUI that provides a simple way to select predefined SwD configurations.
Custom nodes that preview image with a magnifier.
工作流模型管理 - 扫描工作流中引用的模型,自动从 HuggingFace、CivitAI 等来源解析并下载缺失模型,支持目录自动识别、来源校验与断点续传。
MiniMax H3 reference media and rich prompt transport nodes for ComfyUI.
3D camera controller for ComfyUI bringing cinematic camera language to AI image generation. Features 3D orbit control, preset angles, intelligent prompt generation, and multi-angle workflow support. (Description by CC)
ComfyUI custom node - compare N images / multi-frame batches with slider & grid modes, bake per-port labels, export a composite grid image.
ComfyUI-YogurtNodes is a collection of custom nodes for ComfyUI, providing a series of practical image processing and workflow enhancement functionalities.
A ComfyUI plugin supporting Google Gemini 3 Pro model for image generation and text analysis with customizable aspect ratio and image quality. (Description by CC)
Add Switch on nodes, Make nodes amount small! It helps conveniently to use less nodes for doing the same things.
Make Muyan-TTS avialbe in ComfyUI.
ComfyUI audio-reactive animation node combining RyanOnTheInside's reactive features with Fillip's path animation for creating audio-driven visual animations. (Description by CC)
Qwen3 api node
An advanced ComfyUI image loader with managed libraries, bounded recursive folder browsing, image editing, and mask output
ComfyUI custom nodes for MorphGS: video-to-4D character motion transfer (rig conversion, DINOv2/SV4D preprocessing, gsplat-based training, animated .glb/.fbx export). Installs like any other node: pip requirements plus prebuilt pytorch3d/gsplat CUDA wheels matched to your torch build by install.py -- no compiler, no CUDA toolkit, torch untouched. Needs Blender 4.2+ on PATH; SV4D/SP4D checkpoint goes in models/diffusion_models.
Provide concise instructions for AI coding agents to implement a ComfyUI plugin that reproduces the behavior of the three-step novel reference pipeline in this repository as ComfyUI nodes
豆包 Seedance 2.0 视频生成节点(走 DMXAPI):文生视频 / 首帧生视频 / 首尾帧生视频 / 视频编辑·延长·多模态参考生视频 / 任务获取。Doubao Seedance 2.0 video nodes via DMXAPI.
Custom node for ComfyUI. It can read metadata from the image filepath, and filepath can be provided as a connected input, which allows it to batch read image metadata in a loop.
A comprehensive ComfyUI extension for creating, previewing, and analyzing DCI (DSG Combined Icons) format files. This extension fully implements the DCI specification, supporting multi-state icons, multiple color tones, scaling factors, and advanced metadata analysis.
ComfyUI node for writing and reading QR codes.
A streamlined latent size node for ComfyUI with resolution presets, scale control, and batch output.
A ComfyUI custom node that converts RGBA-style assets into fully solid RGB textures by bleeding edge colors outward from the alpha mask, designed for foliage, grass, decals, and cutout assets.
TRELLIS.2 image-to-3D generation for ComfyUI, running natively on Apple Silicon (MPS/Metal).
Displays GPU VRAM usage and system RAM usage as bar widgets in a ComfyUI node.
Stash nodes for ComfyUI: Load content from Stash for use in Comfy workflows.
Batch-tag a folder of anime images with AnimeTimm and save matching UTF-8 caption files.
Specialized ComfyUI node designed to automate the creation of high-precision captioning datasets using multimodal LLMs. (Description by CC)
Tools about metadata.
Load INT8 ConvRot (.comfy_quant) quantized ControlNet and model-patch files in stock ComfyUI loaders. No new nodes; patches ControlNetLoader, DiffControlNetLoader and ModelPatchLoader.
ComfyUI node for postfx library - Theme-based image post-processing & film-emulation pipeline — pure Python, CPU, no GPU.
Predict how Instagram, TikTok and X will treat your content before you post it. Local Qwen-VL observation + deterministic rules engine. No API keys, runs fully offline.
A ComfyUI output node that takes a full-quality master image (any resolution, any aspect ratio) and emits platform-ready derivatives with the minimum possible cropping and a controlled, high-fidelity encode.
Custom nodes for Qwen-Image-Edit with multi-image support, more flexibility around the vision transformer (qwen2.5-vl), custom system prompts, and some other experimental things to come.
Rembg Background Removal Node for ComfyUI
Pair prompts with their LoRAs on the canvas, then manage the rest from one panel — LoRAs, checkpoints, workflows and wildcards, with Civitai and Hugging Face search, server-side downloads, update checks, and a three-way merge that upgrades a workflow without losing your edits.
Character reference gallery and recipe node for ComfyUI
Lightweight ComfyUI translation node for Tencent Hy-MT2 models powered by GGUF (llama.cpp). Fast, memory-efficient, and cleanly managed.
A ComfyUI custom node for integrating LLM API calls into workflows
The core Create Bounding Boxes box editor made usable in the classic UI (Nodes 1.0), on top of the original node; the original core files are not modified. Not standalone: connect its bboxes output to the bboxes input of the core Create Bounding Boxes node and keep using that node's preview, bboxes and elements outputs.
Neo Image Chooser — a node for selecting images with a pleasant UI that allows pausing workflows for frame selection or image save confirmation. (Description by CC)
Random anime/game character picker with franchise pool management for ComfyUI.
A ComfyUI custom node for saving images in date directories like SD-Web-UI does.
Structured prompt-library and LoRA workflow nodes for ComfyUI that keep reusable prompt material outside workflow graphs.
Starlight 2.6 video enhancement nodes for ComfyUI and RunningHub
A collection of utility nodes for ComfyUI to streamline workflows, including prompt editing, translation, model preset management, image preprocessing, and metadata editing.
Nodes for ComfyUI, mostly for llm calling and automatizing pulid multiface.
ComfyUI node for tag-based prompt editing with support for individual tag editing, weight adjustment, reordering, deletion, and Japanese translation. (Description by CC)
Multi-segment minimaxH3DYTsc 6.0 — official MiniMaxH3ImageToVideo / ReferenceToVideo pipeline.
Draw a mask at any point in a ComfyUI workflow (after resize / rotate / crop), keep every mask as a numbered file, and shape the mask edge.
ComfyUI custom nodes for Nucleus-Image 17B MoE diffusion model with FP8 and bf16 precision support, dynamic block swap, CFG rescaling, and model shift parameters. (Description by CC)
Shamelessly copied the code to auto color correct the image like in gimp from this answer: [a/https://stackoverflow.com/a/56365560/4561887](https://stackoverflow.com/a/56365560/4561887)
Prompt enhancers for LM Studio and compatible CLIP text-generation models, a text box with reusable snippets, prompt and note databases, a multi-image loader, image scaling and padding, and latent presets.
A lightweight node to compress and preview images using the temp directory, displaying file sizes on the node UI.
A ComfyUI custom node for inpainting workflows with integrated Photopea editing and adjustable region selection. Features: adjustable reference region, integrated Photopea image editing, professional mask editing with feathering control, auto mask detection, multi-language support.
ComfyUI custom node for browsing Civitai image prompts directly inside a node.
A suite of ComfyUI nodes for generating parameter sweep video matrices with labeled grids. Create comprehensive visual comparisons of how different parameter combinations affect your video generation results.
Lightweight ComfyUI node for text-prompted segmentation masks ◧ using CLIPSeg and mask auto-aligned trim. numpy 2.x safe, TensorFlow-free, auto model caching.
ComfyUI custom node pack with tagger functionality combining WD14, Camie, and PixAI models. (Description by CC)
A ComfyUI custom node using YOLO to detect and crop objects in images or video frames with temporal smoothing, masking, and preview output. (Description by CC)
Companion extension node for comfyui-adaptiveprompts that adds advanced, experimental, or specific workflow-related features.
Generates audio from music prompt using MusicGen
Converts image description to music prompt
comfyui-zeug (German for 'gear' or 'stuff') is a collection of custom nodes for ComfyUI, designed to enhance functionality and provide additional features.
ComfyUI-RefCap: Reference capture for MiniMax H3. One file per character, object or place that replays H3's reference conditioning exactly.
A ComfyUI node to manipulate 3D objects.
Custom nodes for the Foundation-1 audio model in ComfyUI, providing BPM-aware generation and streamlined audio workflows.
Native dependency-free Qwen3-ASR speech-to-text for ComfyUI.
Native dependency-free RVC voice conversion for ComfyUI.
A collection of utility nodes for ComfyUI to improve workflow efficiency.
Voice effects and voice changer for ComfyUI: clean up recordings, transform voices (monster, robot, gender, age…) with presets, live preview
ComfyUI节点 - 将多张图像拼接成网格图。支持动态输入(1-32张图像)、多种分辨率预设、行列设置,自动为每个网格添加顺序编号。
When your workflow starts acting weird and you need to know what's actually happening to your data - not just guess from looking at the output.
Experimental MiniMax H3 frame-rate adjustment with temporal-coordinate retiming and pre-sampling AV duration alignment for ComfyUI.
A ComfyUI custom node that refines and quantizes messy AI-generated pixel art into clean, perfect, and grid-aligned pixels.
ComfyUI custom node for offline Chinese speech-to-text using FunASR with VAD and punctuation support.
Extract keyframes from video
Extended HTTP request nodes for ComfyUI — supports image, audio, video binary data, form-data upload, and raw binary I/O. Fork of felixszeto/ComfyUI-RequestNodes.
A ComfyUI plugin for uploading generated images and videos to Alibaba Cloud OSS (Object Storage Service).
Fail-safe Google Translate prompt node for ComfyUI (retry + caching).
Node for compositing multiple images with interactive preview and layer management
This repository contains custom nodes for Stability AI API which supports SD3.0 and 3.5.
ComfyUI ChatGPT Helper ComfyUI ChatGPT Helper is a custom node extension for ComfyUI that integrates OpenAI's ChatGPT capabilities directly into your ComfyUI workflows. This tool allows for dynamic prompt generation, automated text manipulation, and enhanced interactivity within your AI image generation processes.
Query any OpenAI-compatible chat endpoint from ComfyUI, with model auto-discovery and a variable number of text inputs.
Nodes: LiamLoadImage. This node provides the capability to load images from a URL.
Comprehensive QwenVL integration for ComfyUI with HuggingFace and GGUF model support
A lightweight ComfyUI custom node for LoRA weight optimization using CMA-ES and Tournament GA algorithms.
A ComfyUI custom node pack for calling LLM providers.
This is an audio processing script that applies soft limiting, optional loudness normalization, and optional slicing for transcription. It can also produce stereo-mixed outputs with optional audio appended to the end. The script organizes processed files into structured folders with sanitized filenames and retains original timestamps for continuity.
Convert a structured scene description into an optimised SDXL prompt via LLM