ComfyUI Custom Extensions
Browse 9,446 ComfyUI extensions and 73,215 custom nodes.
A wrapper of [a/CosyVoice2](https://github.com/FunAudioLLM/CosyVoice/)'s ComfyUI custom_nodes
ComfyUI custom nodes for Helios — a 14B real-time long video generation model achieving minute-scale, high-quality video synthesis. Supports Text-to-Video, Image-to-Video, and Video-to-Video generation.
Comfyui-SceneDetect is a ComfyUI custom node that uses PySceneDetect to locate scene boundaries in a video and emit one representative frame per scene as an `IMAGE` batch. It also returns per-scene metadata as JSON (`STRING`) and the total number of detected scenes (`INT`).
A ComfyUI node to download models(Checkpoints and LoRA) from external links and act as an output standalone node.
Layout editors and tools for MOSS-Image in ComfyUI
A ComfyUI node for selecting video resolutions with preset dimensions for video generation models like LTX, CogVideo, and Hunyuan. (Description by CC)
A feature that sends an email via Gmail once image generation is completed in Comfy-ui.
ComfyUI helpers nodes to work with automated high resolution generation workflows
Get the closest compatible flux resolution from a given resolution.
Local Ollama translation node for ComfyUI with English/Simplified Chinese prompt translation and privacy-first localhost defaults.
A ComfyUI node using Google Gemini for prompt refinement and high-fidelity multi-reference image generation.
Face/head replacement for ComfyUI via Google Nano Banana 2 (Gemini image editing). Five swap pathways (whole, crop, mask-inpaint, unbiased, painted-edit), mediapipe + YuNet + Gemini bbox detector cascade, LAB / grain / sharpness / Laplacian compositing, identity-ref obfuscation for celebrity-classifier evasion.
RGB to CMYK (save as tif)
Lightweight and fast, text to and from file tools for ComfyUI, has some JSON capabilities as well, great for storing, reading, organizing, batching text and batch text operations.
Home Buying Decision Factors | 买房决策因子
Real in-graph loops for ComfyUI, in the JkNodes category.
Schematic/technical annotation overlay generator — detection circles, tangent chains, crosshair frames, and pixelation zones over any image
A custom node for ComfyUI that integrates ElevenLabs' text-to-speech API, enabling high-quality voice synthesis within your ComfyUI workflows with voice tuning controls and speech-to-speech capabilities.
Some nodes for processing masks, currently including nodes that fill in the concave parts of existing masks with convex hulls.
Unified ComfyUI custom node for training-free diffusion acceleration, integrating multiple sampler-level and model-level acceleration methods into a single node. (Description by CC)
Dictionary-based prompt composition nodes and dictionary-building tools for ComfyUI.
Joy-LTX 2.5: JoyAI-Echo's performance on LTX-2.5. One-prompt takes with a VRAM-aware planner and multishot with seamless AV-extend joins (any length, one shot of VRAM).
A custom node for ComfyUI that leverages local Ollama vision models to generate detailed prompts or Danbooru-style tags from images.
A ComfyUI node suite for Vidu API, enabling Text-to-Video, Image-to-Video, and more
A set of tools for manipulating latent tensors in ComfyUI
Organize your ComfyUI workflows for production: a folder manager plus a project layer (exportable internal DB), bulk export and optional Git versioning, from a built-in panel.
ComfyUI custom node for removing brightness flicker and chunk boundary artifacts in AI-generated video sequences (WAN, VACE, FramePack, etc.).
Minimal and easy-to-use Google Translate text node for ComfyUI using the googletrans library with automatic language detection and full language support. (Description by CC)
This is a custom node for ComfyUI that analyzes audio files using Librosa, extracting tempo, beat times, energy levels, and timestamps. The analysis results can be displayed in a text box within ComfyUI.
Thumbnail-backed reusable prompt library node for ComfyUI
Spark-TTS controllable synthesis and voice cloning.
A ComfyUI node that detects the skin tone of a person in an image and matches it to the standard emoji skin tone palette.
Experimental Krea2 visual-token reference conditioning nodes for ComfyUI.
Nodes: Image(s) To Websocket (Base64), Load Image (Base64),Load Images (Base64)
A ComfyUI custom node for text generation using the Qwen3-4B language model, primarily for expanding image generation prompts with LLM support. (Description by CC)
Interactive video mask editor to fix mask flickering/missing frames from SAM/SAM3.1 before diffusion models or subject cropping.
The latent gets passed straight through unaltered, if it's empty (i.e from a 'Empty Latent Image' node) FLOAT outputs the first value, otherwise it outputs the second value
A powerful infinite canvas inpainting extension for ComfyUI inspired by InvokeAI Canvas and Painthua.com, enabling boundless painting and seamless iterative workflows.
Lightweight ComfyUI node for mosaic / pixelation restoration, based on lada.
An interactive, user-friendly cropping node that allows you to drag and resize the crop area directly in the ComfyUI interface.
Touch-first card-grid picker with preview thumbnails for the folder-backed model combos (LoRA, checkpoint, VAE, ControlNet, UNet, CLIP, upscale).
Rich metadata + fuzzy-search picker dialog for ComfyUI's sampler_name / sampler / scheduler combo widgets. Tooltip with year / family / ODE order / good-for, plus a centered modal that replaces the cryptic native dropdown.
Turn a track into a finished music video inside ComfyUI. Whisper large-v3 transcribes the lyrics with word-level timing, librosa (or a built-in numpy/scipy fallback) finds the BPM, the beat grid and the sections, and a local LM Studio model - or OpenRouter, OpenAI, Anthropic - writes the treatment, the art direction, a recurring-subject bible and every shot. Out come start-frame image prompts, MiniMax H3 image-to-video and reference-to-video prompts in their exact six-section format, negatives, per-shot timings and sample-accurate AUDIO slices for lipsync. It can render the frames and the clips through fal.ai or OpenRouter, then cut every clip to its shot on the beat with PyAV and mux the original music back in. A live gallery shows each frame and clip in the node as it lands, and a cost meter reports in USD what every model actually billed. The analysis is always local and free; nothing is rendered until you pick a provider.
将小说章节转换为影视分镜脚本的ComfyUI插件
ComfyUI for [a/CrossImageAttention](https://github.com/garibida/cross-image-attention)
The attention mask in the T5 part of flux and SD3 utilizes the text-side attention mask to make the model focus more on text embeddings during image generation, thereby enhancing semantic alignment with the text.
A ComfyUI custom node to generate 3D assets using [a/Stable3D](https://github.com/Stable-X/Stable3DGen)
Extend LoadImage node with subfolder support
Node:SendBase64ToRemote. To connect to another ComfyUI server.
Background removal based on BEN. NODES:LoadRembgByBenModel, RembgByBen, GetMaskByBen, RembgByBenAdvanced, BlurFusionForegroundEstimation.
Custom Node to detect face matching the input reference image.
ComfyUI-SpotEdit is a training-free, region-aware image editing framework based on diffusion Transformers with token pruning and KV cache injection. (Description by CC)
Nodes:SaveTifImage. ComfyUI custom node for purpose of saving image as uint16 tif file.
NODES: SDXLMixSampler, LatentByRatio
ComfyUI-FastVLM-7B Apple A custom node for Apple’s FastVLM-7B vision-language model. This node lets you pass an image + instruction and returns a generated text response.
This custom node for ComfyUI allows you to scrape and download images and videos from the Midjourney showcase pages. It uses undetected_chromedriver to bypass anti-scraping measures, but requires session cookies from a logged-in browser session to function correctly.
Native ComfyUI implementation of ByteDance SeedVR2 using ComfyUI's own model stack and core graph nodes.
A net tool node for comfyui, rewrite from [comfyui-tooling-nodes](https://github.com/Acly/comfyui-tooling-nodes) but support more big data sending.
a simple resize image node(s) in comfyui. This repository is not specific to the length and width values of an image, but focuses more on adjusting the total pixel count, side length specifications, and size ratios of the image.
A collection of custom ComfyUI nodes and utilities for generating AI image prompts representing the diverse attire, cultures, regions, and appearances of the world. This project is designed for easy extension to new countries, cultures, and body parts, using a modular JSON-based data structure and dynamic node generation.
Scene Viewer of SpatialGen
Draws live sampler previews on subgraph nodes in the classic canvas renderer, so you can watch a generation without entering the subgraph.
Utility nodes including ImageBlend, Math, Strings, Color tools, Wildcard Processor, Latent Noise Mask, and WAN Three Frame To Video for keyframe-based video generation
Bboxes (Bounding Boxes) handling and visualization
タグ選択、翻訳、編集、整理をまとめて扱うComfyUI向けプロンプト作業台 / A structured prompt workbench for ComfyUI with tag browsing, translation, editing, and organization.
This project makes local LLMs easy to use for prompt enhancement and image captioning –No API keys. No external tools. No headache.
Automatically detect and download missing LoRAs for ComfyUI workflows
Assorted custom nodes with a focus on simplicity and usability including watermark node and others focused on customizing my comfy experience.
This custom node allows you to overlay a watermark image onto an existing image within ComfyUI.
The ultimate tool for creating complex iterative workflows and frame-by-frame video processing in ComfyUI, designed to handle huge tasks without GPU crashes using intelligent sequential looping.
ComfyUI custom nodes for GPT-Image (gpt-image-2 and OpenAI-compatible image models). Text-to-image via /images/generations and image editing with up to 8 reference images via /images/edits. User-supplied base_url and api_key, no preset gateway.
Run ComfyUI workflows on RunPod Serverless
ComfyUI nodes enabling direct API key usage with custom proxy support for OpenAI, Claude, Gemini, and video/image generation services. (Description by CC)
ComfyUI's Smart Memory Management efficiently manages RAM, GPU memory, and garbage collection. This feature keeps frequently used models in memory to increase inference speed, and dynamically releases less important models when memory is low to optimize resources. However, not all ComfyUI custom node developers create nodes that are compatible with Smart memory management. This includes several impressive models. Mem-safe-wrapper is a custom node that wraps these model nodes to enable ComfyUI's Smart memory management capabilities.
Describe image or create caption files using Janus Pro Model
ComfyUI custom node Pushover Notification
Send generated image to PushOver API webhook with optional parameters such as prompt-id and metadata payload.
This is a tool that lets you digitally sign your images to prove you created them. Think of it like putting an invisible, tamper-proof seal on your artwork that says 'I made this.'
An OCR node for detect text in image and returns covering mask.
A ComfyUI custom node that emits a held, range-bound integer index with multiple advancement modes (loop, clamp, pingpong, random, shuffle) — useful as a Load Image batch index that advances every N runs.
Video with sound from MiniMax H3 and FastH3 on anex.sh, from inside ComfyUI: text to video, first and last frame, reference images and audio, video editing and 2K upscaling.
This node can easily switch between models and prompts by saving presets.
Simple ComfyUI Custom Node to enable saving checkpoints with V-Pred ZTSNR tensors and metadata.
Simple node to convert lora_stack output into string to generate a1111-style lora strength output text, like <lora:name:0.69>. Used to include your Lora names from Lora Stack in text input-output nodes and so on.
The FLUX model API from DashScope, developed by Black Forest Labs, offers superior image generation capabilities with optimized support for Chinese prompts, achieving a commendable tradeoff between performance and the quality of generated images compared to other open-source models.
These nodes allow you to use a distilled Qwen3-4B model as your text encoder in Stable Diffusion XL.
ComfyUI node that makes AI-generated images look like iPhone 15 Pro photos by emulating Apple's ISP color science pipeline, including tone mapping, Display P3 color, Smart HDR, and sensor effects. (Description by CC)
Help comfy deisgner develope custom nodes by foreground GUI without any coding knowledge, complementing the workflow what you design with LLM automatically
MultiDiffusion and SpotDiffusion tiled diffusion for ComfyUI, with Anima (COSMOS) 5D latent support.
An extension set of validation checks, automatic versioning numbering, automatic directory creation, and naming conventions are implemented to ensure that the file system is kept in sync with ShotGrid.
XY plots for any ComfyUI workflow: vary any widget on any node from a grid editor and render a labelled grid in one queue.
Swap the speaking voice in a mixed audio clip (dialogue + ambient sound) while keeping the background intact — Demucs separation, Whisper transcription, local-Gemma emotion tagging, ECAPA-TDNN speaker auto-assignment, Fish Audio S2 cloning, with a Muse-Director-style timeline editor for reviewing/correcting segments.
Deterministic Prompt Enhancement via Procedural Augmentation for ComfyUI
markdown file selector for credentials and system prompts on demand
Drift Johnson's XTTS nodes
AI dance choreography from music. Generate full-body dance motion (BVH/FBX/JSON) from any audio track using MVNT's diffusion model trained with 100+ professional choreographers. Create rigged 3D characters from images, preview motion as stick-figure animations, and export photorealistic AI music videos — all inside ComfyUI. Nodes: MVNT Generate Dance, MVNT Generate Character, MVNT Export Video, MVNT Preview BVH, MVNT List Styles, MVNT Estimate Cost, MVNT Load Motion.
Based off of: [a/Birch-san/diffusers-play/approx_vae](https://github.com/Birch-san/diffusers-play/tree/main/approx_vae). This ComfyUI node allows you to quickly preview SDXL 1.0 latents.
Advanced custom samplers and schedulers for ComfyUI, ported from the Stable Diffusion WebUI reForge extension.
A custom node set for ComfyUI that provides nodes for encoding and decoding images using Tiny AutoEncoders for Stable Diffusion (TAESD) models.
Calibrated sampler for Krea 2 Turbo: schedules measured on your checkpoint, two-phase prompts, composition previews, a prompt enhancer that uses Krea 2's own text encoder, NAG (negative prompt at cfg 1) and PAG/SEG. Idea: AlchemicaMente · code: Claude (Anthropic).