ComfyUI Custom Extensions

This is a set of custom nodes for ComfyUI. The nodes utilize the [a/face parsing model](https://huggingface.co/jonathandinu/face-parsing) to provide detailed segmantation of face. To improve face segmantation accuracy, [a/yolov8 face model](https://huggingface.co/Bingsu/adetailer/) is used to first extract face from an image. There are also auxiliary nodes for image and mask processing. A guided filter is also provided for skin smoothing.

Integrates Mesh2motion into ComfyUI for 3D model animation rigging

ComfyUI nodes and workflows for MiniMax H3 image generation and editing.

Edit images in the Photopea editor directly within ComfyUI.

ComfyUI Nodes for SongBloom

Autocomplete and Related Tag display for ComfyUI

[a/YuE](https://github.com/multimodal-art-projection/YuE) is a groundbreaking series of open-source foundation models designed for music generation, specifically for transforming lyrics into full songs (lyrics2song). you can use it in comfyUI

Faster workflows for ComfyUI users on Mac with Apple silicon

This is a toolset designed for ComfyUI by LAOGOU-666, providing a series of practical sampling nodes, making our operation more intuitive and convenient

Custom ComfyUI nodes providing unified image and mask resizing with multiple scaling modes, aspect-ratio preservation, center crop alignment, and stable tensor-based mask transformations.

A comprehensive ComfyUI theme plugin with stunning cyberpunk aesthetics and powerful customization features

Warning, uses experimental package `comfy-env` to attempt a one click isolated install. Will download and use pixi package manager. ComfyUI wrapper for SAM3DObjects: extract 3D meshes/gaussians from pictures

Nodes: Prompt With Style, Prompt With SDXL, Resize Image for SDXL, Save Image With Prompt Data, HaldCLUT, Empty Latent Ratio Select/Custom SDXL

Match two faces' shape before using other face swap nodes Face-swapping tools typically only replace facial features during the swap, without altering the facial shape. When there is a significant difference in facial shape between the target person and the person in the original photo, the result of the face swap is less satisfactory. This project is a small script that can first liquefy and stretch the face in the original photo according to the horizontal and vertical proportions of the target person's facial contour. The resulting image can be used as input for other face-swapping nodes.

These nodes include my wrapper for the original diffusers pipeline, as well as work in progress native ComfyUI implementation. For the diffusers wrapper models should be downloaded automatically, for the native version you can get the unet [a/here](https://huggingface.co/Kijai/ControlNeXt-SVD-V2-Comfy/blob/main/controlnext-svd_v2-unet-fp16_converted.safetensors).

ComfyUI extension for Ollama, Gemini, OpenAI, Claude, and Qwen with video and audio support

These are nodes to animate an image with a reference video using UniAnimate.

This is a trainer for AnimateDiff MotionLoRAs, based on the implementation of MotionDirector by ExponentialML. NOTE:[a/ADMotionDirector](https://github.com/ExponentialML/AnimateDiff-MotionDirector)

ComfyUI pi-Flow nodes for fast few-step sampling.

This extension enables the use of the diffuser pipeline in ComfyUI. It also includes nodes related to Stream Diffusion.

A ComfyUI custom node package based on the BAGEL-7B-MoT multimodal model.

ComfyUI EasyControl Nodes is a collection of nodes for ComfyUI that allows you to load and use EasyControl models.

Nodes: Image Remove Background (rembg)

YuE2 music generation, piano roll editing, and joint AR/NAR LoRA training for ComfyUI

[a/InstantCharacter](https://github.com/Tencent/InstantCharacter) ComfyUI Warpper

ComfyUI custom nodes for UltraShape - Image-guided 3D mesh refinement

Provide powerful frontend and backend integration node packages for ComfyUI - this is an exceptionally robust integration extension.

Professional image adjustment tools for ComfyUI - Curves, Levels, HSL, and Camera Raw adjustments with real-time preview

This extension contains a set of custom nodes for ComfyUI that allow you to use Core ML models in your ComfyUI workflows. The models can be obtained here, or you can convert your own models using coremltools. The main motivation behind using Core ML models in ComfyUI is to allow you to utilize the ANE (Apple Neural Engine) on Apple Silicon (M1/M2) machines to improve performance.

A version of ComfyUI-to-Python-Extension that works as a custom node. Adds a button in the UI that saves the current workflow as a Python file, a CLI for converting workflows, and slightly better custom node support.

These custom nodes provide a rotation aware face extraction, paste back, and various face related masking options.

A set of custom nodes to perform image 2 image functions in ComfyUI.

Multi-monitor image preview, Variable Assigment/Wireless Nodes, Prompt Tweaking, Command Palette, Pinned favourite nodes, Node navigation, Fuzzy search, Node time tracking, Organizing and Error management. For more info visit: [a/https://comfyui.ma.pe/](https://comfyui.ma.pe/)

You can use TRELLIS in comfyUI [a/TRELLIS](https://github.com/microsoft/TRELLIS/tree/main), Structured 3D Latents for Scalable and Versatile 3D Generation

the LyingSigmaSampler is a very useful node, as many users find it difficult to understand complex parameters. For these users, they might only need a simple, lightweight, and easy-to-use node. However, I have observed that LyingSigmaSampler does not control the noise mask smoothly enough, or in other words, it cannot control it more precisely. LyingSigmaSampler has a great advantage, of course, other nodes are also great. They can be applied to most models, including SD3.5, and they work well, which is a challenge for users because they have to deal with different noise masks. Therefore, I have added smoothing processing to LyingSigmaSampler in the hope of helping more people.

[a/DreamO](https://github.com/bytedance/DreamO) ComfyUI native implementation.

StableZero123 is a node wrapper that uses the model and technique provided [here](https://github.com/SUDO-AI-3D/zero123plus/). It uses the Zero123plus model to generate 3D views using just one image.

A set of nodes including a universal bus, an Inpainting By Mask and a large Upscaler/Refiner [AnyBus,McInpainty,McBoaty]

Korean-friendly practical custom nodes for ComfyUI

An unofficial ComfyUI custom node for [a/Zero-Shot Material Transfer from a Single Image](https://ttchengab.github.io/zest), Given an input image (e.g., a photo of an apple) and a single material exemplar image (e.g., a golden bowl), ZeST can transfer the gold material from the exemplar onto the apple with accurate lighting cues while making everything else consistent.

Provide high-quality video and image generation capabilities, meeting creators' needs for creative content production and management through more convenient operations, richer functionalities, professional parameters, and stunning effects.

openAI suite, String suite, Latent Tools, Image Tools: These custom nodes provide expanded functionality for image and string processing, latent processing, as well as the ability to interface with models such as ChatGPT/DallE-2. NOTE: Currently, this extension does not support the new OpenAI API, leading to compatibility issues.

A set of community node including a universal bus and a large Upscaler/Refiner

Extensions for ComfyUI

Train Image Loras on both sd1.5 and SDXL. This repo git clones the pieces needed to train. It pops open a second terminal window do do the training. It will also display the inference samples in the node itself so you can track the results.

This is a ComfyUI custom node wrapper for the HunyuanVideo-Foley model, which generates realistic audio from video and text descriptions.

VFX control for AI pipelines: art-direct generation with light, camera, depth, 3D placement and perspective. Relight, lens blur, lens distortion, 3D/splat preview, fSpy camera solve, perspective unwarp

ComfyUI-NodeAligner is a lightweight ComfyUI layout plugin that includes features such as node alignment, distribution, and resizing. This plugin is designed to simplify layout adjustments in visual node editors or custom UI components, making node arrangement more convenient and efficient.

ComfyUI node collection: text processing tools, image processing nodes, prompt generators and system prompt loaders, ect.

ComfyUI nodes for image editing prompt generation with visual annotation and AI assistance

ComfyUI nodes for image editing prompt generation with visual canvas annotation and multi-model AI assistance

node color customization, custom colors, dot reroutes, link rendering options, straight lines, group freezing, node pinning, automated arrangement of nodes, copy image [w/failfast-comfyui-extensions is renamed to blibla-comfyui-extensions. Please resintall to this.]

A set of nodes to perform multi-object prompting with InstanceDiffusion

Comfyui-CatVTON This repository is the modified official Comfyui node of CatVTON, which is a simple and efficient virtual try-on diffusion model with 1) Lightweight Network (899.06M parameters totally), 2) Parameter-Efficient Training (49.57M parameters trainable) 3) Simplified Inference (< 8G VRAM for 1024X768 resolution). The original GitHub project is [a/https://github.com/Zheng-Chong/CatVTON](https://github.com/Zheng-Chong/CatVTON)

ComfyUI custom node for flexible and efficient image color correction and post-processing.

Enhance first and last frames for smooth video loop generation in ComfyUI. Based on WAN Video workflow.

A powerful ComfyUI custom node that extends the standard text encoder with persistent prompt storage, advanced search capabilities, and an automatic image gallery system using SQLite.

SDMatte is an interactive image matting method based on stable diffusion, which supports three types of visual prompts (points, boxes, and masks) for accurately extracting target objects from natural images.

A ComfyUI node set and frontend extension for interactive 360 panorama workflows.

Tired of manually downloading and moving models, LoRAs, and more to the right places? Sick of scouring Civitai for that one mystical LoRA someone was using to make that cool image? Want to be share a fully reproducable workflow?

Talking avatars MemoAvatar Memory-Guided Diffusion for Expressive Talking Video Generation

ComfyUI nodes to use Lotus depth/normal prediction. NOTE:The necessary models can be downloaded from ComfyUI-Manager.

ComfyUI_NTCosyVoice is a plugin of ComfyUI for Cosysvoice2

Convert your workflows into node and chain them.

The Wav2Lip node is a custom node for ComfyUI that allows you to perform lip-syncing on videos using the Wav2Lip model. It takes an input video and an audio file and generates a lip-synced output video.

An all-in-one, multi-pass generative upscaling and post-processing node designed to simplify complex workflows and add a professional finish to your images.

A ComfyUI node for 3D lighting angle control, outputs lighting prompts for relighting image generation

A Text To Speech node using Step-Audio-TTS in ComfyUI. Can speak, rap, sing, or clone voice.

Preliminary use of SVD in ComfyUI. NOTE: Quick Implementation, Unstable. See details on repositories.

Swap a large text encoder for a small one with a learned linear projection. Cuts MiniMax H3 conditioning from 15.7 GB to 5.2 GB.

Calculate the execution time of all nodes.

Auto-optimizer node for combining multiple LoRAs via diff-based merging with TIES conflict resolution

A custom node for ComfyUI designed to facilitate the real-time transmission of rendered images, videos, or 3D models to TouchDesigner.

A ComfyUI custom node extension integrating Meta's Segment Anything Model 3 (SAM 3) for advanced image and video segmentation with text-prompt, point-based, and mask-driven capabilities. Provides production-ready nodes compatible with ComfyUI's Impact Pack SEGS format, depth map generation, and support for Python 3.13+ with CUDA and CPU support.

This is a simple Wan block swap node for ComfyUI native nodes, works by swapping upto 40 blocks to the CPU to reduce VRAM.

A prompt-generator or prompt-improvement node for ComfyUI, utilizing the power of a language model to turn a provided text-to-image prompt into a more detailed and improved prompt.

FreeLong spectral blending for consistent motion and prompt adherence in Wan 2.2 video generation with chunked generation support.

Upscaling stable diffusion latents using a small neural network.

Latent Color Space (LCS) manipulation for ComfyUI — brightness, tone, sharpness, and diversity tools.

Use RetinaFace to detect and automatically crop faces.

Comfy Nodes that make utilizing resources from Civitas easy as copying and pasting

Port of [a/https://github.com/huchenlei/sd-webui-openpose-editor](https://github.com/huchenlei/sd-webui-openpose-editor) in ComfyUI

Node to use [a/DDColor](https://github.com/piddnad/DDColor) in ComfyUI.

This project implements the comfyui for long-clip, currently supporting the replacement of clip-l. For SD1.5, the SeaArtLongClip module can be used to replace the original clip in the model, expanding the token length from 77 to 248.

[a/SongGeneration](https://github.com/tencent-ailab/SongGeneration):High-Quality Song Generation with Multi-Preference Alignment (SOTA),you can try VRAM>12G

ComfyUI InstantMesh is custom nodes that running InstantMesh into ComfyUI

A very simple ComfyUI node to remove item with mask.

Nodes to generate noise from video for https://github.com/Eyeline-Research/Go-with-the-Flow

A simple custom node for ComfyUI that allows you to save and reuse prompts, organized into different categories

Quality-preserving per-layer conditioning control for Krea 2 - ComfyUI custom node (enhanced fork of nova452/ComfyUI-ConditioningKrea2Rebalance).

ComfyUI Implementaion of ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

[a/DenseDiffusion](https://github.com/naver-ai/DenseDiffusion) custom node for ComfyUI.

Creating subgraph and Calling subgraphs.

一个打包comfyui节点，用于把像素转矢量 a wrap-up comfyui nodes for concerting pix to raster

Jerry Davos Custom Nodes for Saving Latents in Directory (BatchLatentSave) , Importing Latent from directory (BatchLatentLoadFromDir) , List to string, string to list, get any file list from directory which give filepath, filename, move any files from any directory to any other directory, VHS Video combine file mover, rebatch list of strings, batch image load from any dir, load image batch from any directory and other custom nodes.

a wrap-up of ComfyUI nodes for converting pixels to raster, sent out to [a/Vtracer](https://github.com/visioncortex/vtracer)!

Run Local and API LLMs, Features Conditioning manipulation via Omost, supports Ollama, LlamaCPP LMstudio, Koboldcpp, TextGen, Transformers or via APIs Anthropic, Groq, OpenAI, Google Gemini, Mistral, xAI and create your own charcters assistants (SystemPrompts) with custom presets and muchmore

About TBG Enhanced Tiled Upscaler and Refiner Pro! We at TBG Think. Build. Generate. Pro AI upscaling & image enrichment are excited to make our TBG Enhanced Tiled Upscaler and Refiner Pro available to you for free non-commercial use. We believe in empowering creators and innovators, which is why anything you create or generate using our software

This repository provides a temporary ComfyUI node implementation of the Stand-In preprocessor, aiming to correct the misunderstanding of Stand-In’s preprocessing logic in [a/ComfyUI-WanVideoWrapper](https://github.com/kijai/ComfyUI-WanVideoWrapper). [w/We strongly recommend using the workflows provided in this repo to ensure proper compatibility and the best identity-preserving performance.]