ComfyUI Custom Extensions
Browse 9,446 ComfyUI extensions and 73,215 custom nodes.
Professional astrology engine for ComfyUI with natal chart, transit, synastry calculation and zodiac wheel visualization nodes. (Description by CC)
Custom node for ComfyUI that integrates Puter.js AI image generation directly into workflows with text-to-image and image-to-image support.
A toon composition tool for ComfyUI. (Description by CC)
ComfyUI node for downloading videos and audio using yt-dlp with automatic quality selection and cookie support. (Description by CC)
WebUI-style prompt editor for ComfyUI: Danbooru/e621 tag search, colored tag groups, draggable chips and presets. Edit only - never writes into nodes.
Node similar to the original videocombine with additional features: control sound volume, video timeline, and save current frame to image.
Formats datetime values in ComfyUI workflows. (Description by CC)
A custom node for ComfyUI that randomly selects a checkpoint from a configurable list of models with weighted selection, per-model CFG ranges, and enable/disable toggles.
Nodes:Masks to Colored Masks, Color Picker
Nodes:ColorListMaskToImage, FlattenAndCombineMaskImages
ComfyUI nodes for local Whisper and Gemini/OpenRouter audio transcription for voice cloning labels.
Custom nodes for saving images/videos without metadata and GPU-accelerated frame rate processing (25fps→16fps). Includes 5 nodes: Save Image/Video (No Metadata), Frame Rate Resampler (CPU/GPU). Supports CUDA acceleration and multiple nterpolation methods. Requires ffmpeg.
Custom nodes for ComfyUI to convert between equirectangular (360°) images and a strip of 6 cube faces (90° FOV each).
Do you want to easily swap width and heigth? Than this is for you. From portrait to Landscape. Is you images model trained on 1MP pictures, then you can easily scale those down. For best pictures width and heigth should be a factor of 32, say no more...
Preserve Civitai LoRA hashes and generation settings in locally generated ComfyUI image metadata.
NODES: AutoCrop, ColorQuantizer, ExtractBlack, ExtractBlackAdvanced, RasterToUniformSVG, ... (10 total)
A custom node to add metadata to images, videos and audios, to be conform to the new article 50 of EU AI Act law.
Adds hotkeys (F8 / Ctrl+K) and a toolbar button to cycle node link styles (Spline / Linear / Straight).
Runs a ComfyUI-Lora-Manager recipe in a WAN 2.2 workflow: prompt, settings and its LoRAs split between the high-noise and low-noise experts.
Simpler ComfyUI nodes for controlling RunningHub workflows locally.
Standalone export of custom nodes for FLUX and SD3 RALU sampling experiments with model-family adapters. (Description by CC)
save your image with customized naming rule
Nodes for JSON Key/Value (KV) storage with on-the-fly UI preview, dynamic drop-downs, random selection, and inline edit mode.
Official Minds integration for ComfyUI: compare image and video creative preferences with selected AI-powered Audiences in one node. Connect images, videos with audio, hosted media or text concepts. Review the draft, see rankings and findings in the embedded Minds widget, then send selected original media downstream with audio preserved. Use it for ads, thumbnails, packaging and creative revisions. Requires a Minds account, ready Audiences and a server-side API key. Compare 2–20 alternatives. Results estimate synthetic preferences, not clicks or sales. Scroll inside results with the wheel or trackpad. Guide: https://getminds.ai/guide/integration-comfyui Workflow: https://raw.githubusercontent.com/minds-ai-co/ComfyUI-Minds/main/docs/images/workflow.png Results: https://raw.githubusercontent.com/minds-ai-co/ComfyUI-Minds/main/docs/images/response.png
Hair Edge Color Overlay node for ComfyUI that applies a soft airbrush-style color overlay to hair areas near the face. (Description by CC)
Webtoon-style pink airbrush overlay on skin areas. Simulates overlay-layer pink airbrush post-processing.
Blender (WebAssembly) inside a ComfyUI node: block out scenes, stage actors and cameras, and render structure-control video or images. Photo and video input routes download their models in-node after a licence confirmation.
More test nodes for ComfyUI_Mira extension. (Description by CC)
ComfyUI nodes for script-aware Kling prompt planning with GPT-5.4
Publish meshes and 3D files from ComfyUI to Miris, and stream them
ComfyUI V3 custom nodes to generate random integer and float values.
Mithril-Nodes is a collection of custom nodes for ComfyUI that enhance workflow modularity, data routing, and configuration management. These nodes help you build more dynamic, organized, and reusable pipelines for generative AI workflows.
Apply additional sampling to specific area
It has the ability to concatenate text.
This node can easily switch between models and prompts by saving presets.
This is the node that performs the magnification calculation.
some tools.
Node: Color Enhance, Color Blend. This is the same algorithm GIMP/GEGL uses for color enhancement. The gist of this implementation is that it converts the color space to CIELCh(ab) and normalizes the chroma (or [colorfulness](https://en.wikipedia.org/wiki/Colorfulness)] component. Original source can be found in the link below.
This extension fixes URL encoding issues when ComfyUI is accessed through reverse proxies like 'jupyter-server-proxy'.
Modellix media generation custom nodes for ComfyUI
Run hosted image, video, audio and 3D models from ComfyUI with a ModelRunner API key. One typed node per model. (No GPU Required)
A ComfyUI custom node for high-quality text translation using Tencent's HY-MT1.5-1.8B-FP8 model.
Upload image from comfyui to WordPress add your site setting in file wordpress_config.json
A custom node for filtering, adding, removing, and processing WD14/Danbooru tags based on saved profiles.
Personal helper nodes
A node that fetches URLs from a newline separated list and returns the websites' content as a single concatenated string.
Exact cross-resolution MiniMax H3 audio-latent transplantation for ComfyUI
Illustration-friendly NSFW + gore gate combining SmilingWolf WD tagger v3, CompVis CLIP safety checker, and OwenElliott image-safety-classifier-s NSFL signal with boolean OR. Drop-in compatible with the existing CLIP-based safety-checker node (matches the (IMAGE, nsfw) output signature).
This custom node for ComfyUI provides a set of input elements to create forms or interact with your workflows.
A demonstration custom node that showcases how to integrate Vue as a frontend framework within ComfyUI, complete with PrimeVue components and vue-i18n support.
Every group of the workflow as a switch, in one draggable panel with user-defined categories.
Text utilities and NTD11 video mosaic nodes. Includes weighted random prompts, text concatenation, a video file picker, folder batch processing, and audio preservation. Video detection requires an NVIDIA CUDA GPU.
Defocus Blur Detection Custom Node for ComfyUI wrapping D-DFFNet model detecting out-of-focus areas.
ComfyUI custom node for DMENet-style single-image defocus-map estimation.
A minimal ComfyUI custom node for PBaSR x4 image upscaling inference.
Lock Mode feature for ComfyUI. Make simple no-code UI easily.
This node allows you to use Google's Gemini Nano Banana 2 (Imagen 3 / 3.1 Flash) models for image generation directly within ComfyUI using an API Key.
Automation nodes for ComfyUI: RM Styles (load prompts from JSON with random/increment modes), Power LoRA Loader (advanced LoRA loading with random weights), image fallback, mask gate, latent operations, and video combine nodes.
Preset management & switching tool with visual gallery. Save/switch style and LoRA configs. 预设管理与切换工具,带可视化画廊,支持中英文。
This extension provides styler nodes for SDXL. NOTE: Due to the dynamic nature of node name definitions, ComfyUI-Manager cannot recognize the node list from this extension. The Missing nodes and Badge features are not available for this extension.
ComfyUI custom nodes for HeartMuLa music generation
This is a custom node for ComfyUI that can detect circular patterns in an image and generate a standardized circular output.
ComfyUI nodes for image generation via Poe API
Load the Comfyui nodes variables from a file. (Description by CC)
Save ComfyUI node variables to files with optional metadata attachment to image outputs.
Advanced Prompt Engineering nodes powered by Llama 3.
Generate multiple images from prompt list with upscaling, LUT, and real-time preview
A lightweight scratchpad for safely organizing prompts in ComfyUI with comment removal, preset management, and CodeMirror-based editing interface. (Description by CC)
Run text encoders and VAEs on another ComfyUI instance to save VRAM, and use them like the normal loaders.
Create stunning parallax animations! Transform your ComfyUI generations into immersive 3D animations with realistic depth-based motion. Powered by advanced depth estimation, no external depth maps needed. Perfect for creating eye-catching content that leaps off the screen with realistic depth!
Universal live hardware and generation monitoring bar for ComfyUI.
ComfyS3 helpful util nodes for dynamic workflows
Batched, memory-bounded replacement for KJNodes' ColorMatchV2 — processes long video sequences a few frames at a time instead of holding the whole batch (and color_matcher's internal float64 copies of it) in RAM at once. Same color_matcher library and methods under the hood, drop-in compatible with ColorMatchV2's method/strength/multithread behavior.
A frontend stopwatch for the whole ComfyUI workflow that also tracks average GPU temperature, GPU utilization, VRAM, and system RAM while it runs. Starts counting on Run, shows total time plus the averages collected along the way on finish. Doesn't need to be wired to anything.
A collection of batch-processing utility nodes for ComfyUI. These nodes read structured JSON data files and output parameters one entry at a time, driven by a seed value — making them ideal for automated batch illustration and generation workflows.
ComfyUI custom node that creates optimized image collages from batches of 2-6 images
LASED (Learning Ant Swarm Edge Detection) nodes: a colour-region-aware, learnable edge/contour extractor with a sticky-latch masking mode. Swarm Edge, Multi-Seed, Food Map, Overlay, Animate and Point Picker nodes.
A custom node for ComfyUI that saves images as 16-bit TIFF files with optional Adobe RGB (1998) color space conversion and embedded ICC profiles.
save images to SCP upload, direct to webserver
A ComfyUI custom node pack that provides text-free, deterministic CLIP conditioning for Stable Diffusion image generation using integer seeds instead of text prompts.
zerobytes procedural EDIT system for instruction based image generation with custom word pools
A ComfyUI custom node that draws a status bar over the top of each image in an input batch.
Analog knobs, switches and faders for your ComfyUI workflows, alongside pixel art cleanup, CRT/VHS and film looks, model merging and LoRA tools. The pack also covers the everyday bits: browsing folders, saving images, reading metadata and captioning batches.
Qwen25-VL is a plugin for ComfyU
Pass string and images between multiple ComfyUI via socket. Easy and intuitive nodes for remote connection.
Custom node to generate a image using NanoGPT API
ComfyUI nodes for scanning image folders, browsing prompt metadata, and building reusable prompts.
Save images as PNG/JPEG/TIFF/PSD with DPI metadata and filename tokens (%model%, %seed%)
Native ComfyUI video nodes for Venice.ai Wan 3.0
Wavelet-based frequency-aware noise coloring for ComfyUI samplers; adapts noise injection across frequency bands during generation to improve image detail and quality. (Description by CC)
Nanaix image generation and editing nodes for ComfyUI
A collection of logic and utility nodes for ComfyUI to enhance workflow capabilities.
Custom node set for ComfyUI to assist in constructing prompts for Anima text-to-image generation with structured assembly, Danbooru tag validation, and tag normalization. (Description by CC)
Local-only output nodes that derive a stable run key, save image hashes, and write a receipt beside ComfyUI images. Repeated identical outputs are reported without overwriting the completed receipt.
PuLID for ComfyUI with Chroma support with changed class names to avoid conflicts
A custom node for ComfyUI that adds text overlay to images, with options for text and background color, opacity, and vertical positioning.
ComfyUI custom nodes for T5Gemma-TTS, a multilingual text-to-speech model with voice cloning and duration control, based on the T5Gemma encoder-decoder LLM architecture.
neggles custom comfy nodes.