ComfyUI Custom Extensions
Browse 8,543 ComfyUI extensions and 65,510 custom nodes.
A simplified node that provides access to Ollama. It allows you to send prompts, system prompts, and images to your Ollama instance and receive text-based responses.
A simple node to load image from local path or http url.
ComfyUI supports over [a/Boese0601/MagicDance](https://github.com/Boese0601/MagicDance).
TeaCache optimization nodes for ComfyUI's NewBie implementation, featuring patched loader and coefficient calculator for faster inference with configurable quality. (Description by CC)
NODES:Save Image and ntfy
Nodes: CLIPTextEncodeSDXL-Multi-IO, CLIPTextEncodeSDXL-Pipe, Empty Latent Image from Aspect-Ratio, Random Find and Replace.
Live preview nodes for MiniMax H3 — hear the shot's stereo audio while it denoises, which ComfyUI's own preview discards.
This node customizes the ComfyUI frontend by relocating the action bar into the top bar and hiding selected UI elements to reduce visual clutter.
Resolution picker and latent generator for ComfyUI. Select presets like HD, FullHD, 2K, 4K, 8K with aspect ratios (1:1, 9:16, 4:5, 21:9 etc.) via dropdowns. Automatically snaps width/height to latent-safe multiples of 64. Ideal for EmptyLatentImage, AnimateDiff, ControlNet, video formats, and KSampler workflows. Outputs clean INT values or ready-to-use LATENT tensor.
Assorted Nodes by BuffMcBigHuge
Prompt generator from CSV files with randomization and external text input.
Custom nodes for enhancing and manipulating prompts in ComfyUI. Includes nodes for random color palette generation following different color theory methodologies, prompt text replacement and randomization, list sampling, loading files into strings, and season/weather/time-of-day generation.
Control lighting in AI-generated images through color gradients and shapes.
A smart custom node for ComfyUI that automatically detects the aspect ratio of an input image and matches it to the closest ratio from a user-defined list.
TinySanaPreview is a custom ComfyUI node that implements real-time previews during generation for Sana diffusion models.
A custom node pack for ComfyUI that provides an intuitive prompt drafting, saving, loading and management system with wildcard support.
A ComfyUI companion pack for ComfyUI-PromptDrafter that adds scene-based batch generation — set up combinations of presets across multiple PromptDrafter nodes and render all of them in a single workflow run.
multiline text node that strips c-style comments (i.e.'//' and '/* ... */') before passing output string downstream
360° panoramic depth estimation with multi-plane synchronization for ComfyUI, featuring equirectangular-cubemap transformations, cross-face consistency, and boundary blending for seamless depth maps.
Advanced equirectangular (360°) image processing nodes for ComfyUI, enabling precise rotation, horizon adjustment, and specialized cropping operations for panoramic images.
ComfyUI custom nodes for integrating with the Upsampler API to enhance and upscale images using AI.
Nodes: that we currently provide the package only for x86-64 linux, such as Ubuntu or Debian, and Python 3.8, 3.9, and 3.10.
This custom node allows you to generate logo images using Google Fonts.
🤖 CCTech generic Flux-family reference-conditioning tools for ComfyUI — multi-reference latent chaining, per-reference K/V weighting, color/identity anchoring, and text/reference balance. Works on Flux.1, Flux.1 Kontext, and Flux.2 Klein checkpoints.
Make every ComfyUI image Civitai-ready. CiviScribe saves PNG, JPEG, and WebP with your prompts, generation settings, model, LoRAs, hashes, and only the resources actually used. PNG files can also carry a reloadable workflow, so your uploads keep their creation details without manual metadata work.
This repository contains a custom node for ComfyUI that pads an image to be square, filling the new pixels black.
Krea2-UniDepth native functional depth and image-reference conditioning.
Splits audio into frame-synced chunks for video generation workflows with support for overlapping segments for seamless transitions.
Utility nodes for trimming and processing LTX2 AV audio latents in ComfyUI sliding window generation workflows.
Utilize the power of an LLM into ComfyUI to transform your text-to-image and text-to-video ideas into highly detailed prompts for generation while giving you full control.
URN Queue Media Viewer is a standalone ComfyUI queue visualisation and queue-management extension designed to make queued jobs easier to manage.
Arcade Games
ComfyUI custom nodes for OpenMOSS MOSS-TTS v1.5 — three variants: Local-Transformer (Qwen3-4B backbone, 48 kHz stereo), Delay (8B, 24 kHz) and VoiceGenerator (1.7B, 24 kHz, voice design). Reference-free TTS, zero-shot voice cloning, continuation, duration control, 31 languages.
Advanced RoPE modifications for Chroma/FLUX models including DyPE, YaRN, and other RoPE extension methods.
A ComfyUI custom node pack for image captioning and text generation with ToriiGate-0.5, a fine-tuned Qwen3.5-4B model.
A ComfyUI Custom Node that enables arrow key canvas navigation with a pan speed setting.
A ComfyUI node that improves inpainting results by extending mask boundaries with geometric patterns, helping create smoother transitions and better context for AI-driven image completion.
Generate LTX-Video 2.3 optimized prompts using a local Ollama LLM. Drop-in replacement with 100% local processing, no cloud API keys needed.
This allows for mathematical operations on input images and precise manipulation of channels through NumPy formulas, making it suitable for ComfyUI users with programming experience.
ComfyUI custom node for downloading models from CivitAI, HuggingFace, and custom URLs
Create a fully autonomous Telegram bot inside a single ComfyUI workflow. Simply copy your bot_token, hit run and that's it! The pack features a unified user message receiver (uses Long Polling) and a rich collection of media senders. The nodes are designed for continuous operation of the workflow under the Run (Instant) queueing mode.
Custom node that previews generated images on the node and pauses workflow until user confirmation.
A visual pill-based prompt composer node for ComfyUI. Features 4 prompt panels (Quality, Main, Aesthetic, Negative), tag browser, drag-to-reorder pills, weight control, presets, Lucky prompt generator, manual override mode, and wildcard (.yaml) file loader.
A ComfyUI custom node package for Wan 2.2 Image-to-Video generation workflows.
Example of a Combo widget changing Node appearance
Post images and video to Discord. Nodes to facilitate communication using REST.
Analyze ComfyUI image, audio, and video lists with Ollama, llama.cpp GGUF, or native generative CLIP backends
Analyze ComfyUI image, audio, and video lists with Ollama, llama.cpp GGUF, or native generative CLIP backends
This is a set of custom nodes for ComfyUI that provide anime-style image segmentation using efficient pre-trained models.
Saves images directly to OneDrive using Microsoft's free API service.
A custom node for ComfyUI designed to automatically clean and format natural language captions (generated by VLMs like Florence-2, CogVLM, or JoyTag) for LoRA training datasets.
Krea-2-Turbo text-to-image on Apple MLX (Apple Silicon), with stackable LoRAs. Runs the MLX pipeline in-process and returns ComfyUI IMAGE tensors.
Multi-view mesh refiner node for ComfyUI-Trellis2 with spatial blending across front/back/left/right views.
Custom ComfyUI node for background removal in images. Built with ONNX models and Pillow (PIL).
Load Qwen-VL and Qwen3-VL models locally and apply PEFT LoRA adapters for enhanced image captioning. Supports 4-bit and 8-bit quantization (BitsAndBytes), FP8 pre-quantized models, Flash Attention 2, SageAttention, and torch.compile. Includes a LoRA strength slider and configurable captioning prompts.
This custom node allows you to convert trajectories from JSON files directly into WanMove TRACKS.
A ComfyUI node that converts images to pixel art using the neural network from the SIGGRAPH Asia paper Make Your Own Sprites.
Quality of life ComfyUI nodes: dynamic string formatting with Python f-strings or Jinja2 templates, seed-controlled random input selection, and workflow circuit-breaker for conditional queue interruption.
Custom nodes for managing [a/Ollama](https://ollama.com/) models in ComfyUI workflows. Load and unload models on-demand to optimize memory usage in constrained environments.
Pin widget controls from any node to a persistent sidebar panel
ComfyUI node that lets you set the aspect ratio with the prompt. Converts megapixels + aspect ratio into width/height, with prompt-based ratio detection and randomization.
Nodes:SmartMask, ResizeCropFit, Percent Padding, SoftErosion, StringScheduleHelper, DStack, DavchaConditioningConcat, DavchaModelMergeSimple, DavchaCLIPMergeSimple, DavchaModelMergeSD1, DavchaModelMergeSDXL, ConditioningCompress... Some personal QoL and experimental nodes
vLLM nodes for comfyui using llama-cpp-python
Custom node for ComfyUI integrating audio-separator library that separates audio stems (vocals vs instrumental), removes noise, and fixes audio artifacts using GPU acceleration. (Description by CC)
Essential custom nodes for ComfyUI workflows
Cactus Needle 2 in ComfyUI: a 45M-parameter CPU model that turns text into typed graph parameters, plus nodes that read a ComfyUI workflow back out of a PNG.
A custom ComfyUI node for generating consistent character images using Ideogram API v3's character reference feature. Part of the Desert Pixel (DP) node collection.
A dynamic theme-based prompt generator for ComfyUI that creates versatile, random prompts optimized for face swap workflows.
A custom ComfyUI node that splits sampling steps between a main sampler and a refiner sampler, with independent denoise control for each phase, with upscalers now
Custom Node for ComfyUI that allows you set a weighted curve to your ControlNet giving you more control over the weight of the model over the course of generation.
Public-alpha ComfyUI node for Wan I2V/V2V cascade continuation. R178 adds the Tail 5 Continuation Gate: pause at cascade boundaries, inspect the source plus five tail-frame candidates, choose the best continuation frame, resume the same run, save one stitched video, and write a detailed report. Defaults stay conservative with Observe Only math, Report Only prompt analysis, no prompt text injection, and experimental research modes kept out of the public default path.
This is a node to convert workflows to cyuai api available nodes.
A lean ComfyUI node pack wrapping trellis-mac — the Apple Silicon port of Microsoft's TRELLIS.2 image-to-3D model for MPS-based 3D generation.
ComfyUI custom node package for bridging NAIA 2.0 prompts into ComfyUI workflows via its Remote Web API.
A set of custom nodes enabling Text-to-Video support for FramePack-F1
Validated MiniMax H3 long-sequence Sol-Attn patch for AMD ROCm with conservative accepted-block routing.
Professional audio processing nodes for ComfyUI
Fast parallel PNG image-sequence saver for ComfyUI. Multithreaded 8/16-bit PNG encoding with first-frame-only metadata — a big speedup over Save Image (Advanced) for video/frame dumps.
Easy functional programming and flow control within ComfyUI
A collection of custom nodes for ComfyUI
ComfyUI custom nodes to covert string/image/file to md5 hash
Automatic mask refinement and histogram-based multi-threshold nodes for ComfyUI by easygoing0114
ComfyUI-Cleaner 文件目录清理插件，主要应用linux服务自动清理生产物文件
ComfyUI custom nodes for OpenMOSS MOSS-TTS v1.5 — both the 1.7B Local-Transformer (48 kHz) and the 8B full model (24 kHz). Reference-free TTS, zero-shot voice cloning, audio continuation, hard duration control, 31 languages, stereo output.
Modified version of ComfyUI-LLM-text-processor with 10 image inputs and renamed node.
Aggressive RAM and VRAM cleanup nodes for ComfyUI on Windows. Clears model caches, CLIP, checkpoints, VAE, and forces Windows to release physical RAM.
Compact MiniMax H3 and Music 3 directors with OpenRouter, Ollama, API and local LLM providers.
Lots of randomizers, a simple oobabooga adapter with json options to pass, and other useful nodes.
Composable ComfyUI V3 nodes for YuE2 music generation
ComfyUI custom node for image privacy protection using RGB channel independent differential bit-shifting encryption. (Description by CC)
Control different parts of your image with separate prompts using visual box drawing.
RIFE video frame interpolation node for ComfyUI using real-time intermediate flow estimation to generate smooth intermediate frames between video frames with automatic model download and multiple precision support.
ComfyUI custom nodes for Immich integration — upload, metadata, album management
Text-to-image prompt enhancer node for ComfyUI using an OpenAI-compatible endpoint
Semantic image, video, and document search for ComfyUI using Qwen3-VL multimodal embeddings
A clean, lightweight ComfyUI plugin to transmit data wirelessly between nodes using a global key-value store.
In-graph ComfyUI nodes + MCP bridge for external coding agents (Claude Code / Codex)
ComfyUI nodes for dynamic JSON loading and string/path utility operations
Custom nodes for sharp frame selection and analysis. (Description by CC)
Automatically snapshots workflow state with a sidebar to browse and restore previous versions.