ComfyUI Custom Extensions
Browse 9,420 ComfyUI extensions and 73,215 custom nodes.
Nodes:Word Cloud, Load Text File
Maintained by Eden.art, this is a growing suite of custom nodes for building advanced pipelines.
Latent upscaler supporting arbitrary scales between 1.0-2.0x for various models/VAEs.
Real-time Gallery for ComfyUI with image metadata inspection. Support for images and video.
Nuke-style OpenColorIO color nodes for ComfyUI. Read a still/sequence/video, grade in ACES, decode a generative model's latent without the 0..1 clamp, write EXR/TIFF/PNG/JPEG or ProRes/DNxHR/h264/hevc - fully color-managed, on ComfyUI's native VIDEO wire, and encode ACEScct for LTX-2.5's native HDR path. Thirteen nodes: Read, Write, Player, ColorSpace, LogConvert, Exposure, Display, CDLTransform, FileTransform, LookTransform, Clip Repair, VAE Decode, VAE Encode.
A ComfyUI custom node to read LoRA tag(s) from text and load it into checkpoint model.
Houdini connection plugins
LowVRAM Animation : txt2video - img2video - video2video , Frame by Frame, compatible with LowVRAM GPUs Included : Prompt Switch, Checkpoint Switch, Cache, Number Count by Frame, Ksampler txt2img & img2img ...
Generate Audio from any video and or text
Productivity enhancement extension for ComfyUI featuring radial menus and mouse flick gestures for efficient node alignment, distribution, and resizing. (Description by CC)
a comfyui custom node for [a/MimicBrush](https://github.com/ali-vilab/MimicBrush),then inpainting with reference image.
An extension that's adds advanced audio processing capabilities to ComfyUI with professional-grade audio effects and AI-powered audio enhancement.
Interactive multi-person camera studio and multi-purpose reference library for Qwen Image 2.1, with 3D, POSE, depth and Canny guides.
[Original] In the field of portrait video generation, the use of single images to generate portrait videos has become increasingly prevalent. A common approach involves leveraging generative models to enhance adapters for controlled generation. However, control signals can vary in strength, including text, audio, image reference, pose, depth map, etc. Among these, weaker conditions often struggle to be effective due to interference from stronger conditions, posing a challenge in balancing these conditions. In our work on portrait video generation, we identified audio signals as particularly weak, often overshadowed by stronger signals such as pose and original image. However, direct training with weak signals often leads to difficulties in convergence. To address this, we propose V-Express, a simple method that balances different control signals through a series of progressive drop operations. Our method gradually enables effective control by weak conditions, thereby achieving generation capabilities that simultaneously take into account pose, input image, and audio. NOTE: You need to downdload [a/model_ckpts](https://huggingface.co/tk93/V-Express/tree/main) manually.
NODES:Canvas View
Using Qwen-2.5 in ComfyUI
ComfyUI custom node that adds NegPiP-style negative prompt weighting support for Krea 2 workflows.
Interactive Gaussian Splatting PLY preview and render nodes for ComfyUI.
A lightweight FirstBlockCache model patch for native ComfyUI MiniMax H3.
Run EbSynth, Fast Example-based Image Synthesis and Style Transfer, in ComfyUI.
ComfyUI nodes to use [a/FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing](https://github.com/yrcong/flatten).
Enhanced Wan2.2 image-to-video node with dual sampler workflow, dynamic enhancement, and intelligent color drift correction for video generation. (Description by CC)
A nodepack powered by LSNet that classifies and clusters artworks by style for fast and efficient style analysis.
This extension offers various nodes that are useful for Deforum-like animations in ComfyUI.
DynamiCrafter that works natively with ComfyUI's nodes, optimizations, ControlNet, and more.
ComfyUI wrapper nodes to use the Diffusers implementation of ELLA
Advanced camera control prompt generator for ComfyUI, optimized for dx8152's MultiAngle LoRA. Simplifies multi-directional movements, rotations, and special views with bilingual output.
A custom ComfyUI node for interactive 360° panorama image previews. Panoramic 360 images are also sometimes known as VR photography (virtual reality), HDRI environments (ex: skyboxes), image spheres, spherical images, 360 pano, and 360 degree photos.
Using Qwen-2 in ComfyUI
Load mp3 files and use the audio nodes to power animations and prompt scheduling. Use with FizzNodes.
This extension currently has two sets of nodes - one set for editing the contrast/color of images and another set for saving images as 16 bit PNG files.
A custom node collection for integrating various LLM (Large Language Model) providers with ComfyUI.
twinflow:Realizing One-step Generation on Large Models with Self-adversarial Flows,you can use it in comfyUI
SegFormer model fine-tuned on ATR dataset for clothes segmentation but can also be used for human segmentation! Download the weight and put it under checkpoints: [a/https://huggingface.co/mattmdjaga/segformer_b2_clothes](https://huggingface.co/mattmdjaga/segformer_b2_clothes)
Local YuE2 generation, MuLaCover rearrangement, notation, transcription, training, and voice workflows for ComfyUI
A mobile-friendly user interface for ComfyUI mounted in parallel with the main frontend at /mobile/.
Transform your images with cinematic lighting effects in a single click! ReLight is a powerful ComfyUI node that adds professional-grade lighting capabilities including multiple light sources, rim lighting, and 3D lighting simulation.
Nodes:MZ_CogVideoXLoader
Actively maintained fork of ComfyUI-GGUF node pack with support for new models, INT8/INT4 GGUFs and optionally ComfyUI Dynamic VRAM
ComfyUI custom nodes for Foundation-1 | structured text-to-sample generation for music production
Non-native [a/AttentionDistillation](https://github.com/xugao97/AttentionDistillation) for ComfyUI. Official ComfyUI demo for the paper AttentionDistillation, implemented as an extension of ComfyUI. Note that this extension incorporates AttentionDistillation using diffusers.
Without fine-tuning, FLUX.1 Dev model cannot understand exact color codes. However, it is known that FLUX.1 Dev can repeatedly produce certain colors with certain prompt(color name). Fortunately, on CIVITAI, [a/“novuschroma” shared 155 pre-tested color names](https://civitai.com/models/879997/color-wildcards-for-flux-and-sdxl) that FLUX.1 Dev can handle. Thanks to his resource, color palette consists exclusively of 155 colors can be configured. ‘ColorPalette’ node from ComfyUI APQNodes converts input hex color code to the most similar color name(from pre-tested 155 color names) of which FLUX.1 Dev is aware.
Advanced image input and output: EXR, 32 bit support and more
Moondream image to text query node with batch support
ComfyUI small node toolkit, this toolkit is mainly to update some practical small nodes, to make a contribution to the comfyui ecosystem, PS: 'LMCQ' is the abbreviation of the team name NOTE: The files in the repo are not organized, which may lead to update issues.
ComfyUI Open Sora NOTE:only supports Linux now
MatAnyone in ComfyUI (Remove background)
ComfyUI Custom Nodes for 'TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching'. This generates high-quality 44.1kHz audio up to 30 seconds using just a text prompt.
Added Lora Loader - Tag node, originally by badjeff
Enhanced image-to-video node for Wan2.2 optimized for 4-step LoRAs that fixes slow-motion issues by increasing motion amplitude by 15-50%, with camera movement enhancement. (Description by CC)
Tara is a powerful node for ComfyUI that integrates Large Language Models (LLMs) to enhance and automate workflow processes. With Tara, you can create complex, intelligent workflows that refine and generate content, manage API keys, and seamlessly integrate various LLMs into your projects.
A custom node for ComfyUI, which can select one or some of images from a batch.
you can using stable makeup when use comfyUI
ComfyUI has spaghetti issues. Cable management for the node graph: daisy-chained links, PCB-style routing, ribbon cables, and proper right-to-left wrapping support.
My Workflows + Auxiliary nodes for Stable Video Diffusion (SVD)
Custom node for ComfyUI that integrates a local LLM via OpenAI-compatible API to engineer optimal prompts for Z-Image Turbo workflows. (Description by CC)
Advanced face swapping for ComfyUI with local ONNX inference - no API required!
Nodes: Various nodes to handle SDXL Resolutions, SDXL Basic Settings, IP Adapter Settings, Revision Settings, SDXL Prompt Styler, Crop Image to Square, Crop Image to Target Size, Get Date-Time String, Resolution Multiply, Largest Integer, 5-to-1 Switches for Integer, Images, Latents, Conditioning, Model, VAE, ControlNet
This custom node provides various tools for resizing images. The goal is resizing without distorting proportions, yet without having to perform any calculations with the size of the original image. If a mask is present, it is resized and modified along with the image.
Convert to nvfp4, support Z-image-turbo, flux.1 and more
Triple-stage KSampler for Wan2.2 split models with Lightning LoRA
ComfyUI Chatterbox TTS & Voice Conversion Node
These custom nodes provide a variety of customized prompt stylers based on [a/twri/SDXL Prompt Styler](https://github.com/twri/sdxl_prompt_styler).
Redux style adds more controls
ComfyUI Civitai Gallery is a powerful custom node for ComfyUI that integrates a seamless image browser for the Civitai website directly into your workflow. This node allows you to browse, search, and select images from Civitai and instantly import their prompts, negative prompts, and full-resolution images into your workflow. It is designed to significantly speed up your creative process by eliminating the need to switch between your browser and ComfyUI.
This extension offers various audio generation tools
ComfyUI custom nodes providing LTXV audio-video separation sampling and latent preparation capabilities for professional video generation workflows.
ComfyUI-Index-TTS2 is a custom node plugin for ComfyUI that packages the core functionality of IndexTTS2 (long-form, multi-speaker, multi-dialect podcast voice generation) into a visual workflow
Official set of custom nodes of AcademiaSD.
This toolkit is designed for a wide range of audio tasks, from podcast enhancement and text-to-speech to creative music manipulation and fully automated, batch-processed audio-reactive visual generation.
ComfyUI Sampler testing & benchmarking tool for testing Stable Diffusion samplers, schedulers, CFG scales, prompts, img2img denoise values, and LoRA combinations. Features infinite-canvas dashboard image grids with virtual scrolling that can handle thousands of images, multi-model comparison, automatic resume on interrupt, and real-time visualization. Test entire checkpoint folders, stack multiple LoRAs, generate random seed variations, and export optimized configs. Includes fullscreen mode, keyboard navigation, smart filtering by parameters, and one-click regeneration workflow. Perfect for sampler output optimization and hyperparameter tuning.
ComfyUI node for AudioSR - Versatile Audio Super Resolution upscales audio to 48kHz using latent diffusion
SVFR is a unified framework for face video restoration that supports tasks such as BFR, Colorization, Inpainting,you can use it in ComfyUI
ComfyUI-DeepSeek-JanusPro
Character face swap with LoRA and embeddings.
Nodes: SamplerCustomNoise, SamplerCustomNoiseDuo, SamplerCustomModelMixtureDuo, SamplerRES_Momentumized, SamplerDPMPP_DualSDE_Momentumized, SamplerCLYB_4M_SDE_Momentumized, SamplerTTM, SamplerLCMCustom This extension provides various custom samplers not offered by the default nodes in ComfyUI.
A ComfyUI custom node that provides fine-grained control over style transfer using Redux style models.
Nodes:Tiled KSampler, Asymmetric Tiled KSampler, Circular VAEDecode.
A timeline video editor for MiniMax H3 inside ComfyUI: write shots, render them, and cut them together with sound. With H3 Take, a node for one shot with pinned frames, references and held video or sound.
Custom face detection and segmentation for ComfyUI with automatic face fixing, intelligent color grading, and iterative refinement. Custom-trained models optimized for realistic, anime, and NSFW content.
Add Image Save nodes for TIFF 16 bit and EXR 32 bit formats. Probably only useful if you're applying a LUT or other color corrections, and care about preserving as much color accuracy as possible.
QKV/RoPE/MLP activation chunking for ComfyUI MiniMax H3 with selectable CK, SLA, Sol, and Hybrid attention paths.
This is a node group kit that covers multiple nodes such as local refinement, tag management, random prompt words, text processing, image processing, mask processing, etc
Node to enable seamless multiuser workflow collaboration, run on local and remote comfy servers.
Generate transition frames between two character posture images. The prerequisite for running is to have installed comfyui_controlnet_aux, using its Open Pose or DWPose preprocessor
Advanced DWPose-based body proportion changer for ComfyUI
Custom ComfyUI node performing selective latent denoising and detail enhancement using Fourier Transform (FFT) to separate and enhance image frequencies while suppressing noise. (Description by CC)
ComfyUI nodes for YuE2-3B: a style description and lyrics become a readable score and then a complete 48 kHz stereo song, generated locally.
ComfyUI custom nodes and workflows for HyperFlow H3 Flash GGUF and INT8 convrot checkpoints.
Unofficial Simple And Rough Implementation Of [a/AnyText](https://github.com/tyxsspa/AnyText) and [a/Glyph-ByT5] (https://github.com/AIGText/Glyph-ByT5) and [a/JoyType](https://github.com/jdh-algo/JoyType)
model merging nodes powered by sd-mecha, a memory efficient state dict recipe merger.
This extension provides image generation features based on Fooocus.
A ComfyUI node that generates a VACE control video and mask for a smooth transition between two videos
Color Grading for Stable Diffusion
Nodes to use the OneVision LLaVA models: [a/https://github.com/LLaVA-VL/LLaVA-NeXT](https://github.com/LLaVA-VL/LLaVA-NeXT)
A custom front-end UX node that creates a visual library of all your LoRAs. It's designed to be fast, slim, and make using LoRAs in Comfy a lot more fun for visual users - especially if you have lots of LoRAs. Should make people used to A1111 and other UI heavy platforms feel more at home. If you've got lots of LoRAs, this sidebar could be your new best friend!
ComfyUI-MiniMax-Remover is a custom node for ComfyUI that enables fast and efficient object removal using minimax optimization. It works in two stages: first, it trains a remover with a simplified DiT model; then it distills a robust version using CFG guidance and fewer inference steps.
ComfyUI powertools for SD1.5 and SDXL model merging.
make [a/DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio) available in ComfyUI