ComfyUI Custom Extensions
Browse 8,543 ComfyUI extensions and 65,510 custom nodes.
A very useful automatic cropping tool! It can realize cropping, expansion and rotation functions in the form of a slider.
TEX (Tensor Expression Language). Per-pixel DSL for ComfyUI
Professional video save node for ComfyUI - ProRes ladder, All-Intra H.264/H.265, FFV1 lossless. Honest 10-bit pipeline that preserves diffusion float precision.
A professional collection of ComfyUI Sora video generation nodes
ComfyUI nodes for Janus
A set of custom nodes modified to achieve things I felt were missing.
The fastest Qwen3-TTS for ComfyUI — the only node pack running CUDA graph capture, for 5-8x faster generation with no quality loss. Voice cloning, voice design, custom speakers, reusable clone prompts and batch generation.
Nodes: Prompt Agent, Prompt Agent (String). This script provides a prompt agent node for the Comfy UI stable diffusion client.
ComfyUI nodes for LLaMA-Mesh model.
ComfyUI 插件合集：模型匹配、工作流辅助和自定义节点。
Precision dimension control nodes for aspect ratio adjustments and resizing workflows
Simple, fast canvas-based mask editor for ComfyUI: dirty-rect rendering, preview-resolution painting with full-res export, tile-based undo/redo.
ComfyUI simple Image To Prompt node.
Nodes:Q-Align Scoring. Implementation of [a/Q-Align](https://arxiv.org/abs/2312.17090) for ComfyUI
The patch file needs to be used with ComfyUI-ZML-Image.中文用户不要下载这个,这是英文补丁.
ComfyUI nodes including LLM Text Generation for any LLM server (multiple image/video/audio input, preset management, hide API-key, clean VRAM, auto-unload), Merge LoRA Stacks, Image Pixel Comparison, and other nodes for quality-of-life improvements.
ComfyUI Node - Hugging Face repositories GTP2 Prompt
ComfyUI custom nodes for mosaic detection and creation.
This custom node allow upscaling an image by a factor using a model.
Generate high-quality SVG graphics from text descriptions and images using OmniSVG in ComfyUI.
Improved DanTagGen implementation that posesses all functionality of the A1111 webui extension.
Nodes:MeshHamer Hand Refiner. See also: [a/HaMeR: Hand Mesh Recovery](https://github.com/geopavlakos/hamer/tree/main)
Adds simple One-Time Password (OTP) authentication using Google Authenticator to protect publicly accessible ComfyUI instances.
G-Prompts — capture the text prompt that produced a result, review your library, and feed prompts back into workflows.
Folder-based batch queue helpers for ComfyUI
Save images with visible watermarks (logo/text), invisible watermarks (LSB steganography), and metadata embedding. Supports PNG/JPEG/WebP with browser download.
a custom node for [a/StyleShot](https://github.com/open-mmlab/StyleShot.git)
A lightweight custom node for **ComfyUI** that connects to a local **llama.cpp OpenAI-compatible server** with support for chat, vision, streaming, JSON mode, and clean answer/thinking separation.
NODES: Google Veo2 Video Generation
Per-region prompt and LoRA control for SD1.5, SDXL, Z-Image, and Qwen — compatible with multiple model architectures.
This custom node includes the following functions: Chat_GPT, image_moderation, media_loader, merge_strings, sequential_image_loader.
This is a ComfyUI custom nodes pack that makes working with ZIP files super convenient: upload ZIP directly, load/unpack images, masks, prompts, videos, and audio for batch workflows.
Colored (frequency-shaped) noise diffusion sampling for ComfyUI: parametric + faithful gamma-matrix modes.
Nodes for XY-style testing of parameters such as seed, steps, cfg, denoise, prompts, and LoRAs. Does not require a custom KSampler and works with any KSampler, including the default ComfyUI one.
A custom node suite to augment the capabilities of AP Workflows for ComfyUI
A custom node suite to augment the capabilities of the [a/AP Workflows for ComfyUI](https://perilli.com/ai/comfyui/).
A custom node suite to augment the capabilities of the [a/Open Creative Studio for ComfyUI](https://oc.studio/).
A ComfyUI custom node for loading images sequentially from a directory. Loops back to the first image when reaching the end
A lightweight suite of ComfyUI custom nodes for AI prompt management and history tracking.
A CLIP text encoder with 18 cinematic camera movement presets (dolly, pan, tilt, zoom, orbit and more). Subject-aware and free-camera modes, blend slider to mix your prompt with camera movements, and a live text output to preview the final prompt.
Saya Comfy Couple+ is a modified Comfy Couple node for ComfyUI made for cleaner solo, duo, and dual-character workflows with better control over prompts, masks, and IPAdapter routing.
Save and restore ComfyUI workflows from JPEG images via EXIF UserComment metadata.
Presets for ComfyUI Nodes with user persistance
A ComfyUI custom node set for integrating [a/Ovis2](https://huggingface.co/AIDC-AI/Ovis2-34B), a powerful multimodal large language model designed to analyze images and videos.
Frontend-only workflow productivity extension providing Alt-right-click smart linking, selection-wide smart connection, input swapping, reroute insertion, data-flow arrangement, and bypass controls.
A template-based prompt library and weighted prompt editor for ComfyUI
ComyUI wrapper for RaymondLZhou/deepDeband image and video debanding
Training-free TRELLIS.2 image-to-3D acceleration: forecast the flow-matching velocity on skipped DiT steps (HiCache Hermite / HiCache++ DMD, via hicache-pp) across the sparse-structure and shape-SLaT stages (texture optional). ~2x faster, near-lossless. Pairs with visualbruno/ComfyUI-Trellis2.
A custom node for ComfyUI that automatically saves your prompts, generated images, and workflow metadata into a browsable history, accessible directly from the node.
Dark minimal theme for ComfyUI inspired by Linear, Vercel, and Raycast. Pure black aesthetic, zinc scale, dot grid background, and ghost/outline buttons.
Entry point for HommageTools node collection for ComfyUI. Handles node registration, imports, and logging configuration.
A collection of powerful custom nodes for ComfyUI that connect your local workflows to closed-source AI models via their APIs, supporting Google Gemini, Imagen, Veo, OpenAI's GPT-Image-1, and FLUX models.
ComfyUI Node for loading multiple Lora's [a/HunyuanVideo](https://github.com/Tencent/HunyuanVideo)
Extra-stealth metadata removal node for ComfyUI
Colorist film tools for ComfyUI: 35mm-faithful film grain (per-channel, band-pass, midtone-weighted, added not overlaid, fresh or coherent) plus a companion warm-highlight halation node.
Custom nodes for ComfyUI enabling seamless loading and saving of media files (images, videos, audio, text) directly from/to AWS S3 or S3-compatible storage services.
Simple node for advanced wildcard text processing. Supports variables, conditionals, tag aggregation, weighted selection, and deep nesting. Lightweight, fast, zero external dependencies.
LatentSync 1.5 wrapper for ComfyUI
Switch sampler nodes for ComfyUI
Nodes:ImageScore, Loader, Image Processor, Real Image Processor, Fake Image Processor, Text Processor. ComfyUI Nodes for ClipScore
A Simple Python RSS Feed Reader to create Prompts in Comfy UI
ComfyUI custom node: Audio → Spectrogram image
Intended to be used with SwarmUI-rtx-upscale; provides RTX support with simplified enum handling.
Provides recommended resolution presets specifically. Select a preset from the dropdown to easily output the corresponding width and height values for use with nodes like Empty Latent Image.
Custom node that displays the intermediate images generated at each denoising step during sampling. (Description by CC)
Some additional audio utilites for use on top of Sample Diffusion ComfyUI Extension
parakeet-tdt-0.6b-v2: Automatic speech recognition (ASR) model designed for high-quality English transcription, featuring support for punctuation, capitalization, and accurate timestamp prediction.
AMD Unified Memory TeaCache for LTX2 (LTXAV). Lean single-file caching for 48-layer dual-stream transformer. Caches both video and audio residuals. No CPU offload - designed for AMD APUs with unified memory. ~35% speedup on cached denoising steps.
This model was fine-tuned on Flux.1-Dev to with reflection tuning to serve as a corrector for self-refinement framework introduced in From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning.
ComfyUI nodes for processing SVG and generating G-code using vpype
Another comfy implementation for the short video generation project hpcaitech/Open-Sora, supporting latest V2 and V3 models as well as image to video functions, etc.
ComfyUI custom node for BriaAI Fibo Edit image model.
Fixed version of the original [a/MagicQuill](https://github.com/magic-quill/ComfyUI_MagicQuill) node. Required nodes: ComfyUI-Brushnet and ComfyUI Controlnet AUX
Official BudgetPixel nodes for ComfyUI — generate images, video, music and sound effects with 60+ hosted models (FLUX, Seedream, Kling, Seedance, Wan, and more) using your BudgetPixel API key.
Generate random prompts easily for FMJ.
A custom node implementation for ComfyUI that integrates with Together.ai's FLUX image generation models. This project is inspired by and adapted from [a/ComfyUI-FLUX-BFL-API](https://github.com/gelasdev/ComfyUI-FLUX-BFL-API) to work with the Together.ai API.
Signal Processing Nodes For ComfyUI
ComfyUI nodes for loading images and drawing polygon masks interactively on them with a polygon lasso style tool
Fork of [a/sd_webui_stealth_pnginfo](https://github.com/ashen-sensored/sd_webui_stealth_pnginfo) with ComfyUI support.
Nodes:Simple Google Translator, Simple Resolution Solver. This is a small set of simple nodes that help your workflow on ComfyUI.
FlashAttention-2 Triton kernel for AMD RDNA3 (gfx1100 / Radeon RX 7900 XT/XTX/GRE)
🚀 Picks a random IMAGE file from a directory and provides you with the IMAGE and its filepath as a STRING! This awesome tool brings a touch of randomness to your files and images, making your file management tasks a breeze.
Used for batch extraction of prompt words.
Premium Quad-Modal suite (Image, Video, Text, Audio) for Pollinations.ai. Includes native Settings menu integration, BYOP support, and an automated real-time model list updater.
ComfyUI nodes for PromptWrapper, Mainly for prompt word translation, Chinese translation into English or English translation into Chinese.
🧩 Aspect Ratio Image Size Calculator, 🖼️ Aspect Ratio Resizer, and 📄 Markdown Link Generator for ComfyUI.
This custom node facilitates direct interaction with the Google Gemini API for advanced image editing tasks within ComfyUI with parallel request handling.
Example of using ComfyUI Toolbar to Toggle ComfyUI links on/off
A random prompt node
ComfyUI nodes for loading, merging, and saving Krea 2 PEFT/Diffusers and Kohya LoRAs.
Save image node with dynamic paths and an 'Open Folder' button.
This is a custom node that allows you to easily call up and set image size presets. Settings can be made by editing the included config.yaml. It is almost identical to Comfyroll Studio's CR AspectRatio. I created it because I wanted to easily edit the presets.
Creates images using the NanoBanana API. To use it, you must enter your issued API key.
NODES:Mesh To Voxel, Voxel Block Saver, Voxel Viewer, Voxel Block Loader, Voxel Video Viewer, Voxel Blocks Into Voxel Video, Voxel Video Preview, Voxelize Mesh, ...
Custom ComfyUI node integrating Google's Gemini 3 Pro model for native image generation and processing, featuring multi-API key load balancing and auto-retry mechanisms. (Description by CC)
This custom node allows you to load data from one or more CSV files, then feed that data into subsequent nodes in a ComfyUI workflow.
A comprehensive image gallery extension for ComfyUI that provides advanced image management, metadata editing, NSFW content filtering, real-time file monitoring, and a full-featured file explorer.
A very simple Discord webhook integration node for ComfyUI that lets you post images and text.
GGUF-only build of Qwen3.5-Uncensored for ComfyUI. Uses llama-cpp-python instead of transformers — no transformers dependency, compatible with older ComfyUI nodes.