ComfyUI Custom Extensions
Browse 9,420 ComfyUI extensions and 73,215 custom nodes.
NODES: EasyHRFix, EasyHRFix_Context, JKAnythingToString, JKBigContext, JKDynamicThresholdingMultiModel, JKEasyCheckpointLoader, JKEasyDetailer, JKEasyDetailer_Context, JKEasyKSampler_Context, JKEasyWatermark, JKInspireSchedulerAdapter, JKLilContext, JKMultiModelSamplerUnpatch, JKStringEmpty, JKStringEquals, JKStringNotEmpty, JKStringNotEquals, JKStringToSamplerAdapter
Batch samplers, schedulers, cfg, shift and steps tester custom node, automatic looping functionality for Ksampler node
Implementation of Fast Fourier Transform in COMFYUI
Utility nodes for some randomness in your workflows, like random latent sizes. A few modifications to a few existing nodes, includes nodes for sampler and model parameters. Also includes two schedulers and four samplers that can be used with any KSampler node.
Watermark removal project
ComfyUI nodes to use FluxCustomId Original repo: [a/https://github.com/damo-cv/FLUX-customID](https://github.com/damo-cv/FLUX-customID)
A ComfyUI custom node for face detection and cropping using OpenCV Haar cascades, with full ComfyUI v3 schema support and backward compatibility.
Advanced seed generator for ComfyUI with multiple modes, state persistence, and cross-library synchronization
Simple resuluition calculator to convert pixel resolution and aspect ratio to laten friendlt pixel width and height size.
Nodes that support Stable Diffusion 3 Medium better.
ComfyUI nodes to use [a/4D-Humans](ComfyUI nodes to use 4D-Humans)
Nodes:Split Masks, Mask Selection Of Masks, Mask Region Info
MagoStudio Nodes for ComfyUI
Easily download and install 2D to 3D and Flux models from Hugging Face.
Extension nodes for ComfyUI that improves automatic segmentation using bounding boxes generated by Florence 2 and segmentation from Segment Anything 2 (SAM2). Currently just an enhancement of nodes from [a/Kijai](https://github.com/kijai/ComfyUI-segment-anything-2).
Simple, no-nonsense LLM chat nodes for ComfyUI. Support OpenAI, Claude, Gemini and NoASS Roleplay.
Standalone LTX 2.3 AV director with infinite chunking, visual timeline editor, lipsync, layered audio, and per-segment prompts. No external dependencies.
FluxPseudoNegative is an advanced custom node for ComfyUI that converts negative prompts into positive ones. It's designed to enhance prompt engineering for image generation models that don't natively support negative prompts or where using negative prompts significantly increases generation time. So instead of hacking CFG we simply invert your negative words and find their antonyms!
PromptJSON is a custom node for ComfyUI that structures natural language prompts and generates prompts for external LLM nodes in image generation workflows. It aids in creating consistent, schema-based image descriptions.
A visual prompt construction system for ComfyUI. Build prompts with draggable color-coded categories, tag pills, age slider, free text blocks, tag groups, live preview with tag and character count, and full state persistence.
ComfyUI-LTX13B-Blockswap This is a simple LTX block swap node for ComfyUI native nodes for 13B model, works by swapping upto 47 blocks to the CPU to reduce VRAM.
ComfyUI implementation of '[a/Blind Image Restoration via Fast Diffusion Inversion](https://github.com/hamadichihaoui/BIRD)' Original [a/article](https://arxiv.org/abs/2405.19572)
A standalone custom node that creates a Prometheus-compatible metrics endpoint within the ComfyUI installation.
Custom nodes for ComfyUI in order to expose AI workflows to external applications (particularly image, video and audio editors) so workflows can be integrated as plugins
VFX-oriented nodes for ComfyUI: HDR LogC3 / LogC4 decode, EXR I/O, and an interactive ACEScct color grading panel powered by exr-viewer.
Convert sRGB images to Ultra HDR JPEG (ISO 21496-1)
Rewrite part of a finished MiniMax H3 clip - a rectangle, a time span, or the audio alone - by masking the latent instead of regenerating it. Ten nodes, no decode/re-encode round trip.
Reproject an image or clip through its MoGe geometry along a camera path authored in an interactive 3D editor.
A simple, quick, and dirty implementation of multiple workspaces within ComfyUI.
Load Image Media Browser for ComfyUI
UniversalLLMNode is a custom node for ComfyUI that provides a unified interface to use multiple major LLM APIs, including OpenAI, Anthropic (Claude), Google Gemini, Groq, and Mistral. It is ideal for tasks such as automatically generating high-quality SDXL prompts for image generation.
Professional image saturation control with artifact and highlight protection.
This is a ComfyUI port of PoseRetarget, originally implemented in Wan2.2-Animation. Please use it together with WanVideoWrapper.
Nodes:RR_Date_Folder_Format, RR_Image_Metadata_Overlay, RR_VideoPathMetaExtraction, RR_DisplayMetaOptions. This extension provides nodes designed to enhance the Animatediff workflow.
A collection of ComfyUI nodes for interfacing with the Vectorizer.ai API. Manipulate the results with options for scaling the SVG result back to raster image with increased resolution. Includes a background remover node to remove a prevalent background color from raster images. Enter credentials in config.json or directly within the node.
LUT post-processing for ComfyUI: .cube files, RGB curve, photo filters, color corrections.
Native ComfyUI adapter nodes for RUM FLUX.2-Klein with extra SDXL CLIP conditioning.
Extract the first and last frame from any video file or image batch in ComfyUI.
Simple Node to make panoramic images
FlexiLoRALoader - A ComfyUI custom node for dynamic LoRA weight management. Apply multiple LoRAs with flexible weight patterns and randomization features for creative AI image generation. Features: • Multiple LoRA handling (up to 3) • Weight pattern presets • Random/Sequential mode • Debug logging support
ComfyUI-PromptEnhancer is a custom node for Hunyuan PromptEnhancer
ComfyUI custom nodes for WavTTS zero-shot text-to-speech with real ComfyUI memory tracking
A custom ComfyUI node for integrating with the Fal Kontext API for advanced image editing and generation.
This custom node for ComfyUI allows you to save images in multiple formats, including PNG, JPG, WebP, and ICO. [w/ComfyUI-Save-Multi-Format is renamed to SaveAs. Remove previous one and reinstall to this.]
NODES:Custom Resolution Latent Node, Style Selector This Custom node offers various experimental nodes to make it easier to use ComfyUI.
Text Editor node with Markdown editing plus quick shortcuts, Text Viewer node, with extra features plus Text Merge, Text Save and Load Text from anywhere nodes.
A ComfyUI custom node wrapper for JoyHallo - One-Shot Audio-Driven Talking Head Generation.
An implementation of Frequency-Decoupled Guidance (FDG) in pure Pytorch.
This extension adapts the [a/InstantX IP-Adapter for SD3.5-Large](https://huggingface.co/InstantX/SD3.5-Large-IP-Adapter) to work with Wan 2.1 and other UNet-based video/image models in ComfyUI. Unlike the original SD3 version (which depends on joint_blocks from MMDiT), this version performs sampling-time identity conditioning by dynamically injecting into attention layers — making it compatible with models like Wan 2.1, AnimateDiff, and other non-SD3 pipelines.
This is a custom node for ComfyUI that retrieves detailed information about an image, including its name, format (extension), DPI, dimensions, long side, short side, file size, and EXIF data. It also supports image saving
FlowRVS锛孌eforming Videos to Masks: Flow Matching for Referring Video Segmentation锛寉ou can use it in comfyUI when use this node.
OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion,this node ,you can use it in comfyUI
NODES:CXH_DeepLX_Free, CXH_DeepLX_translate
Run ByteDance Lance-3B (unified image/video generation, editing, and understanding) in ComfyUI, with dynamic VRAM streaming for low-VRAM GPUs.
A package of useful ComfyUI nodes optimizing user experience.
Local Index-Translate text translation node for ComfyUI, by T8star-Aix
Simple nodes for ComfyUI - Token Counter - Optimal Empty Latent
Displays a large draggable floating window with live denoising step previews as your image generates, similar to A1111 and Forge.
A metadata-aware, verified model asset installer for ComfyUI with Xet-accelerated Hugging Face downloads and Civitai analysis.
Timed .lrc lyrics for generated songs, saved beside the audio, with a player that highlights each line as it is sung.
Provide two custom nodes to load and save images with captions as separate files.
Custom node for ComfyUI that fixes an existing node [a/comfyui-dynamicprompts](https://github.com/adieyal/comfyui-dynamicprompts).
A local, ChatGPT-like extension for iterative image creation and editing in ComfyUI with help from a local LLM
Comfy UI nodes for IMtalker to run native weights. With Automatic model downloads.
Nodes: image_layering, color_correction, model_router
This repo contains nodes for ComfyUI that implement some helpful operations on tensors, such as normalization.
ComfyUI Memory Management and VRAM Optimization Custom Node - Free VRAM with sequential model loading support
Custom nodes to enable ViewComfy app functionalities
A node pack for pausing execution asynchronously and notifying the user
This repo cast Recursive Generalization Transformer for Image Super-Resolution to ComfyUI, the original [a/paper link](https://arxiv.org/abs/2303.06373) and [a/github link](https://github.com/zhengchen1999/RGT)
ComfyUI nodes for HairDeck: animation-ready stylized hair cards and spring bones from a single image, as GLB, rigged GLB or VRM.
Generate images and videos in ComfyUI with your own Higgsfield API credentials. Includes reference images, Seedance video generation, resumable requests, and local outputs. By Sherif Oneway.
A matting toolkit based on ComfyUI, supporting multiple matting models and detail processing methods.
Auto-detect seams in stitched grid/carousel/collage images and split into panels — no model, any resolution, even/uneven/irregular layouts.
ComfyUI nodes for fast H3 video (with synced audio) generation: 4-step FastVideo FastH3 + Native VSA (Video Sparse Attention). Text-to-Video / Image-to-Video / Multi-reference / 4K Upscale.
Frequency-aware RoPE reference-attention modulation for Flux/Flux.2 models in ComfyUI.
Integrated N-chunk continuation for ComfyUI native MiniMax H3 video and audio
Frequency-aware RoPE reference-attention modulation for Flux/Flux.2 and MiniMax H3 in ComfyUI.
Ultra Tools: 12 ComfyUI utility nodes - Textbox, Translator, Prompt Styler, Prompt Composer, Image Load, Text/Image Watermark, two Model Viewers, Wildcard Browser, Workflow Timer, Audio Fade.
A collection of custom nodes for ComfyUI that provide dynamic input selection and intelligent upscaling functionality.
ComfyUI nodes for OrpheusTTS model.
Nodes:visual_anagrams_sample, visual_anagrams_animate
Automatic prompt translation to Chinese, custom prompt management, AI-based prompt expansion and translation, AI-generated image/video record management (file browser), and cloud storage upload management.
ComfyUI custom nodes for mosaic detection and creation.
A ComfyUI custom node for formatting Anima prompts.
An intuitive, all-in-one node for ComfyUI that brings a powerful, layer-based regional prompting workflow directly into your graph. Say goodbye to managing countless Conditioning (Set Area) nodes and hello to drawing your creative vision.
Save and reload ComfyUI latent tensors from the output folder.
ComfyUI模型加载带预览图功能节点 是一款专为 ComfyUI 用户打造的高效可视化模型加载插件,通过直观的缩略图预览和强大的分类搜索功能,将繁琐的模型选择过程转化为愉悦的视觉体验。
Nodes:ImageOverlap-badger, FloatToInt-badger, IntToString-badger, FloatToString-badger, ImageNormalization-badger, ImageScaleToSide-badger, NovelToFizz-badger.
ComfyUI-TrashNodes-DownloadHuggingface is a ComfyUI node designed to facilitate the download of models you have just trained and uploaded to Hugging Face. This node is particularly useful for users who employ Google Colab for training and need to quickly download their models for deployment.
CURRENTLY IN ACTIVE DEVELOPMENT (BETA)! IF THINGS BREAK ITS BECAUSE I BROKE IT.... This my implemenation of a `pipe` in ComfyUI. Is it better or worse than others? No idea. (also has some utility nodes)
ComfyUI custom node for MIDI lyrics editing. Replace lyrics in MIDI JSON with auto-generated phonemes (Chinese pinyin / English phonemes), or extract lyrics text. Works with ComfyUI_RH_SoulX-Singer for custom song generation.
ComfyUI custom tool node collection with batch image loading, prompt queuing, text processing, video frame extraction, and prompt templating. (Description by CC)
These nodes are mainly used to translate prompt words from other languages into English. PromptTranslateToText implements prompt word translation based on Helsinki NLP translation model.It doesn't require internet connection。
A powerful ComfyUI custom node that extracts workflow metadata from PNG images and video files generated by ComfyUI.
Danbooru-based tags generator pack. - Tags Generator, Tags Extractor, Character Tags Generator, Tags Conflict Filter, Classify Tags, Weight Tags - [a/Workflow](https://github.com/alchemine/comfyui-generator-pack/blob/main/workflows/comfyui-generator-pack-workflow.png)
This extension contains a custom node for ComfyUI. The node, called 'Bounding Box Crop', is designed to compute the top-left coordinates of a cropped bounding box based on input coordinates and dimensions of the final cropped image. It does so computing the center of the cropping area and then computing where the top-left coordinates would be.
all art styles
A ComfyUI image enhancement node with JPEG degradation, noise, blur, sharpening, contrast, and color controls.
Honest float32 out of any ComfyUI VAE. Decode without the [0,1] clamp and in float32 instead of bfloat16, measure what the stock path throws away, catch tiling artefacts, and write real float32 EXR. By Andromediastudio (andromediastudio.com). Ten nodes: Video QC (ingest report for generated video), VAE Decode (float32, no clamp), VAE Encode (float32), Image Range Stats, Image Compare (numeric), Tile Seam Check, Remap Range, Save EXR (float32), Load Audio (optional), Audio Latent Switch (generated / external).