zhangp365/ComfyUI-utils-nodes offers a suite of utility nodes for ComfyUI, including LoadImageWithSwitch, ImageBatchOneOrMore, ModifyTextGender, ImageCompositeMaskedWithSwitch, ColorCorrectOfUtils, SplitMask, MaskFastGrow, CheckpointLoaderSimpleWithSwitch, ImageResizeTo8x, and MatchImageRatioToPreset, enhancing image processing and manipulation capabilities.
ComfyUI_NYJY enhances ComfyUI with nodes like Translate, JoyTag, and JoyCaption, enabling advanced text processing and tagging functionalities.
LF Nodes enhance user experience with custom nodes, offering features like history for primitives, JSON manipulation, logic switches with visual feedback, and LLM chat integration.
ComfyUI CogVideoX Wrapper integrates CogVideoX models with Diffusers, enabling seamless video generation and manipulation within the ComfyUI framework.
LNL Frame Selector for ComfyUI enables precise frame and sequence selection within the UI, enhancing user control over visual content. It streamlines the process of choosing specific frames, optimizing workflow efficiency.
AegisFlow Utility Nodes streamline image and latent data processing in ComfyUI. They include an image passer, latent passer, and Preprocessor chooser, enabling seamless data transfer and integration with AegisFlow Shima and controlnets.
ComfyUI_BiRefNet_ll integrates BiRefNet for enhanced functionality, featuring nodes like AutoDownloadBiRefNetModel, LoadRembgByBiRefNetModel, and RembgByBiRefNet to streamline model downloading and background removal processes.
ControlFlowUtils offers custom nodes to enhance flow control and logic in ComfyUI, along with various utilities to boost overall functionality.
qq-nodes-comfyui is an extension for ComfyUI that introduces various nodes like Any List, Image Accumulator Start/End, Load Lines From Text File, and XY Grid Helper. It enhances functionality by enabling list slicing, axis conversion, and more.
ComfyUI-WA integrates WhatsApp functionality into ComfyUI, allowing users to manage WhatsApp interactions directly within the ComfyUI environment.
ComfyUI_Qwen2-VL-Instruct enables text, video, single-image, and multi-image queries to generate captions or responses, integrating Qwen2-VL-Instruct with ComfyUI for versatile query support.
ComfyUI-fal-Connector integrates ComfyUI with fal, enabling users to execute ComfyUI workflows directly on fal.ai, thus leveraging fal.ai's computational power and resources.
Compositor Node allows users to pass up to 8 images, visually place, rotate, and scale them for ideal composition. It supports group move/rescale, remembers positions/scaling across generations, and includes a buffer zone for asset management.
pre_cfg_comfy_nodes_for_ComfyUI provides a set of nodes designed to prepare noise predictions before executing the CFG function, enhancing the accuracy and efficiency of the process.
The Flux blocks patcher sampler is an advanced, experimental custom node for ComfyUI. It enables iterative adjustments of Flux model block weights, allowing users to observe the impact of each value change.
ComfyUI-BiRefNet-Hugo integrates the advanced BiRefNet model into ComfyUI nodes, enhancing matting accuracy significantly over previous versions.
ComfyUI Sequential Image Loader is an extension node for ComfyUI that enables bulk loading of video frames, allowing users to perform masking and sketching on each frame via a graphical user interface.
Qwen2-VL wrapper for ComfyUI enables text-based and single-image queries, enhancing ComfyUI's functionality by allowing users to interact with the interface through versatile input methods.
ComfyUI Visual Area Nodes is a collection of nodes designed to assist in managing area conditionings efficiently.
ComfyUI-LumaAI-API is a custom node for ComfyUI, integrating the Luma Dream Machine API to enhance functionality and streamline processes within the ComfyUI environment.
ComfyUI-GlifNodes is a custom set of nodes used by glif.app to create mini apps powered by tailored Comfy workflows, enhancing app-building capabilities with specialized functionalities.
comfyui_overly_complicated_sampling offers experimental and mathematically unsound sampling for ComfyUI, designed for advanced users. It is in flux and may frequently change or disrupt workflows, providing a fun yet unstable experience.
HivisionIDPhotos-ComfyUI is a custom node designed for integration with the HivisionIDPhotos project, enhancing its functionality within the ComfyUI framework.
ComfyUI-NegiTools enhances ComfyUI with nodes for OpenAI DALLe3, English translation, string functions, and seed generation, providing advanced AI capabilities for creative and functional tasks.
ComfyUI_DeepFakeDefenders enables users to predict whether an image is a DeepFake within the ComfyUI interface, enhancing image authenticity verification.
Eden.art LoRa Trainer is a highly efficient and optimized tool for training SDXL and SD15 models, maintained by Eden.art. It offers rapid performance and fine-tuned capabilities for superior model training.
ComfyS3 integrates Amazon S3 with ComfyUI, offering custom nodes for easy loading and saving of images, videos, and checkpoint models directly from S3 buckets within the ComfyUI graph interface.
ComfyUI PickScore Nodes enable image scoring within ComfyUI by using PickScore to evaluate a batch of images, predicting which ones best match a specified prompt.
Flux Prompt Enhance Node for ComfyUI integrates the Flux-Prompt-Enhance model, enabling users to directly enhance prompts within their ComfyUI workflows for improved functionality and efficiency.
Searge-LLM for ComfyUI v1.0 is a prompt-generator node that leverages a language model to enhance text-to-image prompts, transforming them into more detailed and improved versions for better results.
The ezXY scripts and nodes extension for ComfyUI links float and integer inputs/outputs, auto-casting and clamping values to the correct type and range. It includes nodes for generating XY plots, though compatibility issues may arise with certain ComfyUI versions.
ComfyUI-eesahesNodes integrates InstantX's Flux union ControlNet loader and implementation, enhancing ComfyUI with advanced control and loading capabilities for streamlined user experience.
ComfyUI-MotionThiefExperiment is an experimental node pack designed to utilize reference videos to capture and apply their motion.
Comfyui_MiniCPMv2_6-prompt-generator by ComfyUI enables single-image captioning, prompt generation from uploaded images, and batch-image prompt generation, enhancing image-to-text capabilities.
ComfyUI_pose_inter generates transition frames between two character posture images. It requires the installation of comfyui_controlnet_aux and utilizes its Open Pose or DWPose preprocessor for functionality.
Embedding Picker helps users manage and select embeddings by providing an easy-to-use interface, preventing misspellings and forgotten names, and allowing efficient access to multiple installed embeddings.
Adaptive Guidance for ComfyUI enhances the user interface by dynamically adjusting guidance based on user interactions, improving usability and efficiency. This implementation tailors the UI experience to individual needs, optimizing workflow.
ComfyUI Llava-OneVision integrates OneVision LLaVA models into ComfyUI, enhancing visual-language tasks by leveraging advanced AI capabilities.
RyanOnTheInside is a ComfyUI extension that adds custom nodes for particle simulations, optical flow, and temporal masks, enhancing visual effects and dynamic content creation.
Flux Prompt Generator for ComfyUI is a versatile tool designed to create detailed and imaginative prompts for image generation models within the ComfyUI framework, enhancing the creative process with customizable options.
WAS Node Suite for ComfyUI introduces a variety of new nodes, enhancing capabilities in image and text processing, among other functionalities.
Comfyui-ergouzi-kaiguan enables group switching control with a single click, allowing users to ignore and disable multiple groups simultaneously. It also supports wired switch combination nodes for flexible annotation name switching.
ComfyUI-KepOpenAI is a user-friendly node interfacing with the GPT-4 with Vision (GPT-4V) API, enabling image and text prompt processing to generate contextually relevant text completions using OpenAI's capabilities.
ComfyUI Easy Use optimizes and integrates several commonly used nodes to enhance the usability of ComfyUI, streamlining the user experience and improving functionality.
ComfyUI-GGUF adds GGUF quantization support for native ComfyUI models, enabling efficient performance on low-end GPUs by using lower bits per weight variable bitrate quants, particularly for transformer/DiT models.
ComfyUI is a robust and modular diffusion model GUI, API, and backend featuring a graph/nodes interface, designed for enhanced functionality and flexibility in model management.
ComfyUI_StoryDiffusion is a specialized node within ComfyUI designed to facilitate the creation and manipulation of story-based content. It integrates seamlessly into the ComfyUI framework, enhancing narrative development capabilities.
Mecha Merge Node Pack offers model merging nodes utilizing sd-mecha, a memory-efficient state dict recipe merger, enhancing performance and resource management in model integration tasks.
SD-PPP is a custom node for ComfyUI that facilitates seamless interoperability with Photoshop, allowing users to easily send and receive layers between the two applications.
☁️BizyAir Nodes are versatile ComfyUI extensions designed to operate seamlessly across various environments, enhancing functionality and adaptability for diverse applications.
ComfyUI-0246 introduces random nodes designed to address specific challenges within ComfyUI, such as pipe and process issues, offering varying quality solutions.
ComfyUI-BiRefNet integrates the Bilateral Reference Network, which excels in multi Salient Object Segmentation, into ComfyUI nodes, simplifying the use of this state-of-the-art model for users.
ComfyUI-EbSynth enables fast example-based image synthesis and style transfer within the ComfyUI framework, allowing users to efficiently apply artistic styles to images.
ComfyUI Impact Pack enhances facial details with detector and detailer nodes, and includes an iterative upscaler for improved image quality.
The ComfyUI Inspire Pack extension offers nodes for Lora Block Weight and Impact Pack support, enabling diverse regional features and Variation Seed applications for enhanced functionality.
ComfyUI-RK-Sampler enhances ComfyUI with batched Runge-Kutta samplers, optimizing the sampling process for improved performance and efficiency in computational tasks.
ComfyUI-VideoHelperSuite enhances video workflows by providing nodes like VHS_VideoCombine, streamlining video processing within the ComfyUI framework.
The ComfyUI - Text Overlay Plugin allows users to superimpose text on images, offering options to select font types, set text size, choose color, and adjust the text's position for customized overlays.
ComfyUI_CatVTON_Wrapper integrates the CatVTON model into ComfyUI, enabling advanced virtual try-on capabilities within the user interface. This extension facilitates seamless clothing visualization and fitting simulations.
ComfyUI Layer Style is a set of nodes for ComfyUI designed to generate images similar to Adobe Photoshop's Layer Style. The first completed node is Drop Shadow, with additional features currently in development.
ComfyUI_MiniCPM-V-2_6-int4 is an implementation by ComfyUI that supports text, video, single-image, and multi-image queries to generate captions or responses.
ComfyUI Deploy is an open-source platform designed for deploying ComfyUI, akin to Vercel but tailored for generative workflow infrastructure.
comfyui-mixlab-nodes offers diverse functionalities including 3D rendering, screen sharing, floating video, speech recognition and synthesis, GPT integration, local image loading, and layered node management for enhanced UI experiences.
comfyui_LLM_party is a set of block-based LLM agent node libraries for ComfyUI, enabling users to efficiently construct and integrate LLM workflows into existing SD workflows.
ComfyUI's ControlNet Auxiliary Preprocessors reworks the original preprocessors using ControlNet auxiliary models, replacing most v1 preprocessors with v1.1 versions. It maintains compatibility with old workflows but advises against using the controlnet preprocessor to avoid conflicts.
ComfyUI jank HiDiffusion is an experimental implementation of HiDiffusion for ComfyUI, aiming to integrate advanced diffusion techniques into the user interface.
rgthree's ComfyUI Nodes offers custom nodes like Seed, Reroute, Context, Lora Loader Stack, Context Switch, and Fast Muter to streamline and organize complex workflow construction in ComfyUI.
Perturbed-Attention Guidance for ComfyUI enhances image generation by manipulating attention maps, allowing for refined control over visual outputs. This extension adjusts attention mechanisms to improve detail and coherence in generated images.
x-flux-comfyui enhances ComfyUI with nodes for loading and applying Flux LoRA and Flux ControlNet, and includes the Xlabs Sampler for advanced sampling capabilities.
AnimateDiff Evolved enhances ComfyUI by integrating improved motion models from sd-webui-animatediff. Users can download and use original or finetuned models, placing them in the specified directory for seamless workflow sharing.
ComfyUI Bringing Old Photos Back to Life enhances old or low-quality images with features like automatic scratch removal and face enhancement, based on Microsoft's Bringing-Old-Photos-Back-to-Life.
pythongosssss/ComfyUI-Custom-Scripts enhances ComfyUI with features like Auto Arrange Graph, Workflow SVG, Favicon Status, Image Feed, Latent Upscale, Lock Nodes & Groups, Lora Subfolders, Preset Text, Touch Support, and Workflow Management.
ComfyUI-Dev-Utils enhances ComfyUI with execution time analysis, improved reroute functionality, and a node collection tailored for developers, streamlining development and debugging processes.
ComfyUI-ELLA integrates ComfyUI with ELLA, a tool developed by TencentQQGYLab, enhancing user interface capabilities for streamlined and efficient operations.
ComfyUI-FluxExt-MZ provides nodes like MZ_Flux1PartialLoad_Patch, focusing on tools related to flux1 within the ComfyUI framework.
ComfyUI Image Saver enables saving images with generation metadata compatible with Civitai, supporting png, jpeg, and webp formats. It also stores LoRAs, models, and embeddings hashes for resource recognition.
ComfyUI-Logic is an extension for ComfyUI that adds logic nodes and conditional rendering features, enhancing the UI's functionality by enabling dynamic content display based on specific conditions.
ComfyUI-Long-CLIP enhances the comfyui by supporting the replacement of clip-l, specifically for SD1.5. It uses the SeaArtLongClip module to expand token length from 77 to 248, improving model performance.
ComfyUI_Fill-Nodes introduces the FL Image Randomizer, aiming to enhance ComfyUI by addressing gaps in nodes and functionality. This extension is the initial step in an ongoing effort to expand and improve the ComfyUI experience.
Comfy-groqchat enables content generation in ComfyUI using open-source models through the Graq API, streamlining the integration and utilization of these models for efficient and effective content creation.
ComfyUI_Mira enhances ComfyUI with nodes like Integer Multiplier, Float Multiplier, Convert Numeral to String, Create Canvas Advanced, Create PNG Mask, and Color Mask to HEX String, boosting functionality and versatility.
ComfyUI Essentials provides essential nodes missing from ComfyUI core, introducing new features rather than common utilities. This temporary repository aims to integrate these nodes into ComfyUI eventually.
ComfyUI_tinyterraNodes provides diverse pipe nodes, comprehensive XYZ plotting, a fullscreen image viewer with node history, dynamic widgets, and interface customization, enhancing the functionality and user experience of ComfyUI.
Image chooser is a custom node that halts the workflow, allowing users to select an image or latent to continue the process.
Use Everywhere (UE Nodes) is a set of nodes designed to broadcast data to multiple unconnected inputs, significantly reducing the complexity and clutter of link spaghetti in workflows.
ComfyUI Inpaint Nodes are experimental nodes designed to enhance inpainting with ComfyUI. They introduce two nodes that enable the use of the Fooocus inpaint model, transforming any SDXL checkpoint into an inpaint model for improved functionality.
Comfyui-photoshop integrates a Photoshop node within ComfyUI, enabling seamless data exchange between ComfyUI and Photoshop.
Deforum Nodes offer an official animation pipeline for creating frame-by-frame generative motion art, enabling unique and dynamic visual content creation.
LoraInfo displays Lora data from CivitAI, providing trigger words and example prompts for users.
ComfyUI-Advanced-ControlNet enhances ComfyUI with advanced ControlNet functionalities, including nodes like ControlNetLoaderAdvanced, DiffControlNetLoaderAdvanced, and various weight customization options such as ScaledSoftControlNetWeights and CustomControlNetWeights.
ComfyUI nodes for ControlNext-SVD v2 provide a wrapper for the original diffusers pipeline and a native ComfyUI implementation. The diffusers wrapper auto-downloads models, while the native version requires manual unet download.
Core ML Suite for ComfyUI integrates custom nodes into ComfyUI workflows, enabling the use of Core ML models. It leverages the Apple Neural Engine on Apple Silicon (M1/M2) for enhanced performance, supporting both pre-obtained and user-converted models.
ComfyUI-DynamiCrafterWrapper integrates DynamiCrafter's image2video and frame interpolation models into ComfyUI, also supporting ToonCrafter for enhanced animation and video creation capabilities.
ComfyUI-Fast-Style-Transfer is a ComfyUI node enabling rapid neural style transfer, adapted from the fast-neural-style-pytorch project. It currently supports basic inference functionality for efficient style transformations.
ComfyUI Griptape Nodes integrates the Griptape Python Framework with ComfyUI, creating a series of nodes that enhance your workflow by incorporating AI capabilities.
KJNodes for ComfyUI enhances usability with various quality-of-life nodes, primarily focusing on visual improvements.
ComfyUI Serving toolkit enables seamless integration of workflows, such as through a Discord bot, by adding nodes for easy service deployment.
ComfyUI-TrainTools-MZ provides nodes for fine-tuning lora within ComfyUI, leveraging training tools like kohya-ss/sd-scripts to enhance customization and performance.
UniAnimate Nodes for ComfyUI enable image animation using a reference video through UniAnimate. Note: They conflict with AIFSH/ComfyUI-UniAnimate and cannot be installed simultaneously.
ComfyUI Universal Styler is a custom node for AI research using the ComfyUI visual editor, focusing on Stable Diffusion local processing. It offers diverse prompting scenarios with public and private models, integrated learning, and workflows.
ComfyUI-mxToolkit enhances ComfyUI with nodes for seed randomization, pausing generation, and saving values. It includes slider nodes for input control and an alternative Reroute node, streamlining the user experience.
Comfyui-SAL-VTON enables virtual try-on for models in ComfyUI by linking garments with persons using semantically associated landmarks, based on the 2023 paper by Keyu Y. and Tingwei G.
ComfyUI Fooocus Nodes is an extension that enhances image generation capabilities by integrating Fooocus technology into ComfyUI, enabling advanced and efficient image creation.
Plush-for-ComfyUI enhances ComfyUI with two OpenAI-enabled nodes: Style Prompt, which generates art-style-specific prompts using ChatGPT3 or 4 for Stable Diffusion, and OAI Dall_e 3, which creates images based on user prompts and parameters.
ComfyUI prompt control offers nodes for easy prompt editing, enabling users to manage basic generations within ComfyUI entirely through prompt adjustments.
SDXL Auto Prompter in ComfyUI Extension simplifies the creation of diverse random art and photos, enabling effortless generation of endless unique visual pieces.
ComfyUI-IC-Light-Native integrates the IC-Light framework directly into ComfyUI, enhancing its functionality with native support for IC-Light's features.
ComfyUI-Inpaint-CropAndStitch features two nodes: 'Inpaint Crop' for cropping images before sampling using a mask, expand pixels, or expand factor, and 'Inpaint Stitch' for seamlessly reintegrating the inpainted image into the original without affecting unmasked areas.
ComfyUI-Prompt-Combinator is a node that generates all possible combinations of prompts from multiple string lists. The ComfyUI-Prompt-Combinator Merger node allows merging outputs from two different ComfyUI-Prompt-Combinator nodes.
ComfyUI-Prompt-MZ leverages llama.cpp to generate nodes for tasks related to prompt word processing within the ComfyUI framework, enhancing efficiency and functionality in prompt management.
ComfyUI-RefUNet provides a set of nodes designed to integrate Reference UNets into the ComfyUI framework, enhancing its functionality by enabling advanced neural network operations.
ComfyUI SAM2(Segment Anything 2) integrates features from comfyui_segment_anything, enhancing its segmentation capabilities. This adaptation builds on the foundational work by continue-revolution, improving functionality and performance.
ComfyUI-SEGAttention integrates Smoothed Energy Guidance (SEG) into ComfyUI, enhancing its functionality with advanced energy-based guidance techniques for improved performance and results.
ComfyUI-Video-Matting integrates Robust Video Matting (RVM) into ComfyUI, providing a streamlined solution for video matting tasks. This extension focuses on efficient and minimalistic implementation, enhancing video editing workflows.
ComfyUI WD 1.4 Tagger is an extension for ComfyUI that enables users to extract and analyze booru tags from images, facilitating efficient image tagging and categorization.
ComfyUI-ppm enhances ComfyUI with fixed AttentionCouple/NegPip for negative weights in prompts and introduces additional CFG++ samplers, improving the overall functionality and customization options.
🐰 MaraScott Nodes offers a versatile set of nodes for ComfyUI, featuring a universal bus, an Inpainting By Mask tool, and a comprehensive Upscaler/Refiner. Key components include AnyBus, McInpainty, and McBoaty.
Comfyui_CXH_joy_caption enhances ComfyUI with nodes Joy_caption_load and Joy_caption, enabling advanced captioning functionalities. It streamlines the process of loading and generating captions within the ComfyUI framework.
BilboX's ComfyUI Custom Nodes offer a tool called BilboX's PromptGeek Photo Prompt, enabling users to easily create photorealistic prompts within ComfyUI.
comfyUI-tool-2lab is a toolset designed for developing workflows and publishing them to a web API server, streamlining the process of creating and deploying web-based applications.
Dream Video Batches offers tools for batch video generation workflows, including AnimateDiff and Stable Video Diffusion, enhancing efficiency and automation in video creation processes.
Comfyui-easyapi-nodes provides nodes for converting between Base64 and images, including Base64 To Image, Image To Base64, and Load Image To Base64, facilitating seamless data transformation within the ComfyUI framework.
GLSL Nodes: A collection of nodes designed to integrate GLSL shaders into workflows, enhancing visual effects and rendering capabilities within the system.
ComfyUI-DepthAnythingV2 integrates DepthAnythingV2 models into ComfyUI, enabling automatic model downloads to enhance depth-related functionalities within the ComfyUI framework.
ComfyUI_FL-Trainer enables training of Image Loras on sd1.5 and SDXL by cloning necessary components and opening a secondary terminal for training. It displays inference samples within the node for result tracking.
Jovimetrix Composition Nodes offer extensive multimedia support, including webcam, MIDI, Spout, and GLSL shaders. They enable animation via tick, parameter manipulation with wave generators, and various image operations like shape mask generation, channel operations, and batch processing.
One Button Prompt is a prompt generation tool designed for both beginners and advanced users seeking inspiration. It creates complete prompts from scratch with controlled randomness. Just load the script, press generate, and get surprised.
SD Prompt Reader is a ComfyUI node designed for efficient management of image metadata and ensuring compatibility across multiple tools. It streamlines the process of handling and integrating image-related data.
comfyui_tag_filter is a custom node for ComfyUI that categorizes and filters tags generated by tools like WD14Tagger, returning the refined results based on each category.
Various custom nodes by Eden.art offers a collection of specialized nodes designed for diverse applications, maintained by Eden.art. These custom nodes enhance functionality and provide tailored solutions for specific tasks.
The noise latent perlinpinpin extension features the NoisyLatentPerlin node, enabling the creation of latent spaces filled with Perlin-based noise, which can be utilized effectively by samplers.
ComfyUI-AutoCropFaces leverages RetinaFace technology to detect and automatically crop faces in images, streamlining the process of isolating facial features for further analysis or processing.
Tripo for ComfyUI integrates custom nodes into ComfyUI, enabling users to generate 3D models from text and image prompts using Tripo's advanced 3D creation capabilities.
ComfyUI-moondream is an image-to-text query node with batch processing capabilities, enabling efficient conversion of multiple images to text within the ComfyUI framework.
ComfyUI_NAIDGenerator is an extension designed to facilitate image generation using the NAI framework, streamlining the process for users seeking efficient and high-quality visual outputs.
ComfyUI-IDM-VTON [WIP] is an adaptation of IDM-VTON for virtual try-on, enabling users to visualize clothing on different body types using the ComfyUI interface.
ComfyUI-JNodes enhances ComfyUI with features like a Lora/Embedding picker, web extension manager, text prompt control, image/video viewer, metadata viewer, token counter, and font control, while allowing easy enable/disable of extensions.
ComfyUI_toyxyz_test_nodes enables real-time webcam streaming to ComfyUI, optimized for use with LCM.
Vector_Sculptor_ComfyUI enhances compositions by adjusting conditioning towards similar concepts for enrichment or precision. It uses cosine similarity scores to gather pre-conditioning vectors, stopping when scores increase, thus setting a relative direction for similar concepts.
cgem156-ComfyUI🍌 integrates custom nodes from laksjdjf into its node pack, featuring the attention couple functionality for enhanced performance.
ComfyUI-ProPost offers custom nodes for ComfyUI, enabling basic post-processing effects like Film Grain and Vignette to enhance AI imagery, making it appear more natural and less artificial.
Comfy Couple is a custom node designed to draw two distinct characters together without blending their features, ensuring clear and separate visual representation for each character.
ComfyUI Portrait Master is a node designed to assist AI image creators in generating prompts specifically for human portraits.
Dynamic Thresholding Extension for ComfyUI introduces nodes for Dynamic Thresholding, CFG scheduling, and associated techniques, enhancing control and flexibility in processing tasks.
ComfyQR is an extension for ComfyUI that enables QR code generation, offering nodes for creating basic QR images and advanced QR masking techniques, enhancing workflow versatility.
ComfyUI-Prompter-fofrAI is a prompt helper that integrates templates from prompter.fofr.ai into ComfyUI, enhancing the user experience by providing ready-to-use prompt templates.
ComfyUI-post-processing-nodes is a collection of nodes designed for post-processing tasks within ComfyUI. Users can easily integrate these nodes by downloading the repository and dragging them into their project.
AlekPet/ComfyUI_Custom_Nodes_AlekPet provides specialized nodes like PoseNode, PainterNode, and various translation nodes for text and CLIP text encoding. Note that ComfyUI-Manager cannot recognize these nodes, so some features are unavailable.
ComfyUI Extension comfyui-replicate enables seamless integration of Replicate models within the ComfyUI framework, allowing users to run and manage these models directly through the ComfyUI interface.
ComfyUI Nodes for External Tooling offers nodes like Load Image (Base64), Load Mask (Base64), Send Image (WebSocket), Crop Image, and Apply Mask to Image, enabling ComfyUI to function as a backend for external tools.
The img2txt-comfyui-nodes extension integrates BLIP/Llava Multimodel Tagger into ComfyUI, enabling efficient image-to-text conversion. It enhances ComfyUI's functionality by providing advanced tagging capabilities for images.
ComfyUI-AudioScheduler enables loading mp3 files to drive animations and prompt scheduling using audio nodes, designed for integration with FizzNodes.
ComfyUI_EchoMimic enables lifelike audio-driven portrait animations in ComfyUI by utilizing editable landmark conditioning, allowing for realistic and dynamic facial movements synchronized with audio input.
ComfyUI_IPAdapter_plus integrates IPAdapter models into ComfyUI, adapting code from the original IPAdapter repository and laksjdjf's implementation to align with ComfyUI's design principles.
Jags_VectorMagic is a ComfyUI extension featuring a collection of nodes designed for advanced vector and image manipulation, enabling users to explore and enhance their graphic design capabilities.
MTB Nodes offers a variety of functionalities including Face Swap, Film Interpolation, Latent Lerp, and ImageBlur. It also supports operations like Bounding Box, Crop, Uncrop, Denoise, Color Correct, and more, enhancing image processing capabilities.
ComfyUI-liveportrait integrates the LivePortrait functionality into the ComfyUI framework, enabling users to create dynamic, animated portraits with ease. This extension enhances user experience by providing seamless animation capabilities within the ComfyUI environment.
ComfyUI Extension comfyui_bmab enhances the ComfyUI interface by integrating BMAB functionality. Users should remove 'custom_nodes/comfyui-bmab' from their directory and reinstall to update to comfyui_bmab.
Mikey Nodes offers functionalities like Prompt With Style, Prompt With SDXL, Resize Image for SDXL, Save Image With Prompt Data, HaldCLUT, and Empty Latent Ratio Select/Custom SDXL, enhancing image processing and prompt management.
ComfyUI-AdvancedLivePortrait is an advanced tool featuring a facial expression editor, enabling users to create and modify live portraits with detailed facial expressions.
ComfyUI ExLlamaV2 Nodes is a local text generator for ComfyUI, leveraging the ExLlamaV2 model. It requires manual package installation and provides efficient text generation capabilities within the ComfyUI framework.
ComfyUI-FLATTEN provides nodes for integrating optical flow-guided attention, enabling consistent text-to-video editing within the ComfyUI framework.
ComfyUI-MimicMotionWrapper provides optimized wrapper nodes for integrating MimicMotion, enhancing motion mimicry capabilities within the ComfyUI framework.
Advanced CLIP Text Encode provides A1111-like prompt functionality, essential for users requiring advanced text encoding capabilities. Note that the Cutoff node already includes this feature.
Extra Models for ComfyUI enhances ComfyUI by integrating support for diverse random image diffusion models, expanding its functionality and creative potential.
Efficiency Nodes for ComfyUI Version 2.0+ streamline workflows and reduce node count in ComfyUI. Originally created by LucianoCirino, the nodes are now maintained by a new developer. Uninstall the original and reinstall the forked version.
Arc2Face ComfyUI Node Library enhances ComfyUI by integrating nodes that utilize the Arc2Face model to extract face embeddings, generate images from these embeddings, and perform image-to-image transformations.
Dimensional Latent Perlin for ComfyUI is a custom node that generates Perlin noise in the latent space, enhancing image generation by working seamlessly with various diffusion models as an alternative or complement to standard random noise generators.
ComfyUI-Kolors-MZ integrates Kolors into ComfyUI, leveraging ComfyUI's native sampling for enhanced color management.
ComfyUI-MimicMotion is a custom node for ComfyUI that integrates Tencent's MimicMotion, enabling advanced motion imitation capabilities within the ComfyUI framework.
ComfyUI Whisper enables audio transcription and video subtitling within ComfyUI, streamlining the process of converting spoken content into text and adding accurate subtitles to video files.
ComfyUI_ColorMod enhances image editing by providing nodes for adjusting contrast and color, and includes functionality for saving images as 16-bit PNG files.
ComfyUI_Seamless_Patten enables the creation of seamless patterns from text-to-image processes, ensuring smooth, continuous designs without visible edges or interruptions.
Latent-Interposer is a custom node for ComfyUI that enables direct conversion of latents between SDXL and SD v1.5, bypassing the VAE decoding/encoding process.
Skimmed_CFG is a robust anti-burn tool for ComfyUI, enabling significantly higher CFG scales in latent diffusion models.
ComfyUI Ollama integrates custom nodes into ComfyUI workflows, leveraging the Ollama Python client to seamlessly incorporate the capabilities of large language models (LLMs).
comfyui_facetools offers custom nodes for rotation-aware face extraction, pasting, and diverse face masking options, enhancing facial image manipulation and editing capabilities.
ComfyUI-DiffSynth-Studio integrates DiffSynth-Studio into ComfyUI, enabling users to access and utilize DiffSynth-Studio's features directly within the ComfyUI interface for enhanced functionality.
ComfyUI-EasyOCR integrates Easy-OCR to provide robust OCR text recognition capabilities within the ComfyUI framework, enhancing its ability to accurately identify and process text from images.
ComfyUI-Florence2 integrates Microsoft's Florence2 vision model into ComfyUI, enabling functionalities like captioning, object detection, and segmentation.
ComfyUI-Image-Filters provides image and matte filtering nodes for ComfyUI, enabling advanced image processing and enhancement within the ComfyUI framework.
ComfyUI-LivePortraitKJ integrates nodes for LivePortrait, requiring insightface, to enhance portrait animation capabilities within the ComfyUI framework.
ComfyUI PhotoMaker Plus integrates PhotoMaker models into ComfyUI, enhancing photo editing capabilities. Users must delete the old custom_nodes/ComfyUI-PhotoMaker directory and reinstall due to a repository name change.
ComfyUI Video Player is an extension designed to integrate video playback capabilities within the ComfyUI interface, aiming to streamline and centralize multimedia functions, potentially reducing the need for multiple software applications.
ComfyUI-segment-anything-2 provides nodes for utilizing the segment-anything-2 tool by Facebook Research, enabling efficient image and video segmentation within the ComfyUI framework.
Lora-Training-in-Comfy simplifies the creation of LoRA models within ComfyUI. It ensures users have access to the latest nodes for efficient model training, enhancing the overall user experience.
ComfyUI-AutomaticCFG is a self-rescaling CFG tool designed to enhance image quality by preventing burned images and artifacts. Set your CFG at 8 for optimal results, with improved sensitivity and quality even at lower scales like 4.
Seamless tiling Node for ComfyUI generates nearly seamless textures, inspired by a similar feature in A1111. This node enhances texture creation by ensuring continuity and smooth transitions, ideal for various design applications.
ComfyUI_omost integrates the Omost framework into ComfyUI, enabling advanced regional prompt functionalities. Note: ComfyUI_densediffusion installation is required for this node to operate.
Cyclist is an extension that offers tools to iterate and refine generation results across multiple runs, focusing on cyclical processes to enhance output quality.
ComfyUI-Image-Selector is a custom node for ComfyUI that enables users to select specific images from a batch, enhancing image management and selection within the interface.
ComfyUI-NSFW-Detection integrates NSFW content detection into ComfyUI, enabling the identification and filtering of inappropriate material within the user interface.
ComfyUI-mnemic-nodes offers functionalities like saving text files, downloading images from URLs, interfacing with Groq LLM API, and generating experimental negative prompts, enhancing ComfyUI's capabilities.
ComfyUI_AnyDoor allows users to modify images by changing clothes or objects within them. This extension for ComfyUI provides tools for seamless image editing, enhancing customization and creativity.
FizzNodes offers scheduled prompts, float/int values, and wave function nodes for animations and utility in ComfyUI. It supports audio-synced animations via compatibility with framesync and keyframe-string-generator tools.
Comfyui lama remover is a straightforward ComfyUI node designed to eliminate items using a mask.
AuraSR-ComfyUI integrates the Aura-SR model into ComfyUI, enhancing image super-resolution capabilities within the user interface. It leverages advanced algorithms to improve image quality and detail.
ComfUI-EGAdapterMadAssistant is an auxiliary project of IPAdapter, featuring a slider for quick hierarchical weight control and options for fully random and semi-random modes.
ComfyUI-DataSet offers data research, preparation, and manipulation nodes for model trainers, artists, designers, and animators, featuring tools like captions, visualizer, and text manipulator.
ComfyUI-JDCN offers custom nodes for efficient file and data management, including saving and importing latents, converting lists to strings, moving files, and batch loading images, enhancing ComfyUI's functionality.
The Styles CSV Loader Extension for ComfyUI enables users to import styles from a CSV file, facilitating the migration of styles from the automatic1111 Stable Diffusion web UI to ComfyUI.
ComfyUI-YOLO integrates Ultralytics-powered object recognition into ComfyUI, enhancing its capabilities with advanced detection and identification features. This extension leverages YOLO models for precise and efficient object recognition.
ComfyUI-sampler-lcm-alternative introduces custom nodes—LCMScheduler, SamplerLCMAlternative, and SamplerLCMCycle—enhancing ComfyUI with advanced LCM sampler functions for improved performance.
ComfyUI-CreaPrompt enables users to effortlessly generate random prompts, streamlining the creative process by providing instant, varied suggestions.
ComfyUI_FaceShaper adjusts the facial shape in photos to match the target person's proportions before face-swapping, ensuring more satisfactory results by liquefying and stretching the original face to align with the target's contour.
ComfyUI_MagicClothing integrates garment and prompt functionalities into ComfyUI, enhancing the user interface with advanced clothing design and customization features.
smZNodes enables ComfyUI to generate identical embeddings as stable-diffusion-webui using the CLIP Text Encode++ node.
ComfyUI Diffusion Color Grading is a ComfyUI extension developed from joint research by Haoming02 and TimothyAlexisVass. It enhances image processing by applying advanced color grading techniques within the ComfyUI framework.
Floodgate is a ComfyUI extension node enabling dynamic switching between execution flows. It enhances workflow flexibility by allowing conditional branching, optimizing process control within the user interface.
ComfyUI ReSharpen is an extension for ComfyUI that enables users to adjust the level of detail in the Stable Diffusion pipeline, allowing for both enhancement and reduction of generated details.
Bmad Nodes provides API support for setting up requests, computer vision capabilities for masking and collages, and general utilities to streamline workflows and implement essential missing features.
Animatediff MotionLoRA Trainer is a tool for training AnimateDiff MotionLoRAs, leveraging the MotionDirector implementation by ExponentialML. It focuses on enhancing motion dynamics in animations through advanced training techniques.
ComfyUI-Book-Tools Nodes for ComfyUI enables users to add customizable text overlays to images in their projects using Python Imaging Library (PIL) and PyTorch. It supports various customization options like font size, alignment, color, and padding, and includes features for looping parameters, prompt batch scheduling, and automatic queue ending.
BrushNet for ComfyUI enables image inpainting through custom nodes, utilizing a decomposed dual-branch diffusion model for seamless plug-and-play functionality.
ComfyUI CrewAI integrates Crew AI's multi-agent collaboration framework into ComfyUI, merging role-based AI agent systems with an intuitive interface to manage and execute complex AI tasks seamlessly.
Crystools enhances ComfyUI with features like resource monitoring, progress tracking, and metadata viewing. It allows image and JSON comparisons, displays values, and offers improved nodes for loading/saving images and previews, revealing hidden data seamlessly.
ComfyUI-DareMerge allows users to merge two checkpoint models using a method inspired by dare ties, facilitating model integration and enhancing functionality.
ComfyUI Frame Interpolation enhances animation by using the KSampler node to gradually increase denoising, resulting in smoother transitions between frames. This efficient method improves visual quality in animated sequences.
ComfyUI-IC-Light provides native nodes for the ComfyUI interface, enhancing its functionality and integration capabilities.
ComfyUI-MagickWand integrates ImageMagick's powerful image editing and manipulation capabilities into ComfyUI via the wandpy library, enhancing digital image processing. Note: ImageMagick must be installed manually.
Marigold depth estimation in ComfyUI is a wrapper node utilizing the same diffusers pipeline as the original Marigold implementation. It requires a model in diffusers format to function effectively within ComfyUI.
ComfyUI MotionDiff integrates MDM, MotionDiffuse, and ReMoDiffuse into ComfyUI, enhancing its capabilities for motion diffusion modeling and rendering.
ComfyUI-SUPIR integrates SUPIR upscaling into ComfyUI via wrapper nodes, enhancing image resolution within the interface.
ComfyUI_Bxb converts ComfyUI workflows into WeChat Mini Program, Douyin Mini Program, and H5 formats with a single click, also enabling payment support.
ComfyUI_DanTagGen is a ComfyUI node for Kohaku's DanTagGen Demo, designed to generate tags efficiently. It integrates seamlessly with ComfyUI, enhancing tag generation capabilities for various applications.
Primere nodes for ComfyUI offer diverse utility nodes, including Inputs (prompt, styles, dynamic, merger), Outputs (style pile), Dashboard (selectors, loader, switch), Networks (LORA, Embedding, Hypernetwork), and Visuals (visual selectors).
Comfy-Topaz is a custom node for ComfyUI that integrates Topaz Photo AI to enhance images by upscaling, sharpening, and denoising, making these traditionally asynchronous steps part of ComfyUI workflows.
Anyline is a ControlNet line preprocessor that swiftly and accurately extracts object edges, image details, and text from various images, producing clear, detailed line drawings for conditional generation in Stable Diffusion.
ComfyUI-CADS integrates the CADS model into ComfyUI, inspired by the A1111 implementation. It aims to enhance ComfyUI's capabilities by leveraging the CADS framework for improved performance and functionality.
ComfyUI-Dream-Interpreter interprets your dreams and immerses you within them, providing a unique, interactive experience based on your dream narratives.
ComfyUI-Inspyrenet-Rembg is a ComfyUI node designed for efficient background removal, utilizing the InSPyReNet framework to enhance image processing capabilities.
ComfyUI-J offers a distinct set of nodes based on Diffusers, enhancing model import, weighted prompts, inpainting, reference-only modes, and controlnet functionalities, differing from Comfy's KSampler series.
ComfyUI-KwaiKolorsWrapper is a basic tool that integrates the Kwai-Kolors text-to-image pipeline with diffusers, enabling users to generate images from text descriptions.
ComfyUI-LuminaWrapper integrates Lumina models into ComfyUI, providing specialized wrapper nodes to enhance functionality and streamline model usage within the ComfyUI framework.
ComfyUI-NuA-FlashFace is a ComfyUI extension for human image personalization, ensuring high-fidelity identity preservation. Users must manually download the required models to utilize this functionality.
ComfyUI-openpose-editor is a port of the sd-webui-openpose-editor, integrated into ComfyUI. It enables users to edit OpenPose skeletons within the ComfyUI environment, enhancing pose customization and control.
ComfyUI PixelArt Detector is a node that optimizes pixel art images by performing operations like downscaling, palette changes, and upscaling to ensure they appear pixel perfect.
ComfyUI-SD3LatentSelectRes introduces a new node, SD3 Latent Select Resolution, allowing users to choose x and y dimensions from a predefined list, enhancing customization and control over resolution settings.
ComfyUI-SuperBeasts offers custom HDR effect nodes for ComfyUI, developed by SuperBeasts.AI. These nodes enhance the user interface with advanced visual effects, tailored for creative projects.
ComfyUI-TCD integrates ComfyUI with the TCD framework, enhancing user interface capabilities by leveraging TCD's features. This extension streamlines UI development, offering a seamless experience for developers.
ComfyUI-Tara-LLM-Integration is a robust node for ComfyUI that incorporates Large Language Models (LLMs) to streamline and automate workflows, enabling the creation of intelligent processes for content generation, API key management, and seamless LLM integration.
ComfyUI-Texture-Simple allows users to visualize textures directly within the ComfyUI interface, enhancing the design process by providing immediate visual feedback on texture application.
ComfyUI-layerdiffuse (layerdiffusion) integrates LayerDiffusion into ComfyUI, enhancing image processing capabilities by enabling advanced diffusion techniques for improved visual outputs.
ComfyUI_ChatGLM_API enables users to utilize Chatglm's API within ComfyUI for translating and describing images, functioning similarly to OpenAI's API.
Face Analysis for ComfyUI leverages DLib to compute Euclidean and Cosine distances between faces, requiring the installation of the Shape Predictor and Face Recognition model from the Install models menu.
ComfyUI_HiDiffusion_Pro is a specialized node for ComfyUI, enhancing its capabilities by integrating advanced diffusion techniques. It optimizes the user interface for smoother, more efficient workflows in complex diffusion processes.
ComfyUI InstantID (Native Support) integrates InstantID directly into ComfyUI without using diffusers, offering a unique native implementation. Currently in beta, it seeks user feedback for further refinement.
ComfyUI_Stable_Makeup allows users to apply makeup to characters within the ComfyUI interface, enhancing their appearance with customizable cosmetic effects.
VLM_nodes offers custom nodes for Vision Language Models (VLM) and Large Language Models (LLM), enabling image captioning, automatic prompt generation, creative and consistent prompt suggestions, and keyword extraction.
😸 YFG Comical Nodes generates image histograms, providing visual representations of input image data. Key nodes include img2histograms and img2histogramsSelf, which output sets of histogram images for analysis.
Comfyui-MusePose is an image-to-video generation framework that creates virtual human animations based on control signals like pose. Users must manually download the necessary weights from Hugging Face for optimal functionality.
FreeU_Advanced is a custom node offering enhanced settings for FreeU, enabling users to fine-tune and optimize their configurations for improved performance and functionality.
Power Noise Suite for ComfyUI offers nodes for managing latent noise input, diffusion, and latent adjustments, enhancing the control and manipulation of noise within the ComfyUI framework.
PuLID_ComfyUI is a native implementation of the PuLID framework within ComfyUI, designed to enhance user interface functionality and integration. It streamlines UI processes, offering improved performance and user experience.
The a-person-mask-generator extension for Automatic1111 and ComfyUI automatically generates masks for background, hair, body, face, and clothes in Img2Img, streamlining the image editing process.
Comfyui-art-venture enhances ComfyUI with nodes like ImagesConcat, LoadImageFromUrl, and AV_UploadImage, enabling seamless image concatenation, URL-based image loading, and image uploading functionalities.
Dream Project Animation Nodes provides essential nodes for creating Deforum-like animations within ComfyUI, enhancing animation capabilities and streamlining the animation process.
Save Image Extended for ComfyUI enhances the Save File node by allowing customization of subfolders and file names using checkpoint names or any desired sampler attribute. This forked version replaces the unmaintained original, requiring uninstallation of the old version before reinstalling.
ComfyUI-BiRefNet-ZHO enhances the BiRefNet integration within ComfyUI, supporting both image and video processing for improved performance and functionality.
ComfyUI Hallo is an unofficial implementation of the Hallo project for ComfyUI, designed to integrate advanced generative vision capabilities from the original Hallo framework into the ComfyUI environment.
ComfyUI-Chibi-Nodes enhances ComfyUI with nodes like Loader, Prompts, ImageTool, Wildcards, LoadEmbedding, ConditionText, and SaveImages, streamlining image processing and prompt management for efficient workflow customization.
Stable Projectorz Bridge integrates Stable Projectorz with ComfyUI, allowing seamless interaction through custom nodes.
CosyVoice-ComfyUI is a custom node for ComfyUI, designed to integrate with the CosyVoice project by FunAudioLLM. It enhances ComfyUI's functionality by enabling seamless interaction with CosyVoice's audio processing capabilities.
ComfyUI-Depth-Visualization integrates with any Depth Map to display the applied version within ComfyUI, enhancing depth data interpretation and visualization.
ComfyUI Thumbnails enables users to load and view image thumbnails within the ComfyUI interface, enhancing visual navigation and accessibility by providing quick previews of images directly in the UI.
ComfyUI-UltraPixel integrates UltraPixel technology into ComfyUI, enhancing image processing capabilities. This extension optimizes pixel manipulation, providing superior visual quality and performance within the ComfyUI framework.
ComfyUI_TGate is the reference implementation for T-GATE, a tool designed to enhance user interface experiences. It integrates T-GATE functionalities into ComfyUI, providing advanced UI capabilities.
ComfyUI DenseDiffusion is a custom node for ComfyUI, designed to enhance image generation by leveraging dense diffusion models. It integrates advanced AI techniques to produce high-quality, detailed visuals within the ComfyUI framework.
Various ComfyUI Nodes by Type offers a collection of nodes like JWInteger, JWFloat, JWString, JWImageLoadRGB, and JWImageResize, designed to enhance ComfyUI's functionality by providing diverse data handling and image processing capabilities.
ComfyUI-AI-Assistant integrates AI-Assistant directly into ComfyUI, enhancing its functionality with advanced AI capabilities for improved user interaction and automation within the ComfyUI environment.
ComfyUI_yanc enhances ComfyUI by adding a collection of useful nodes, expanding its functionality. For more details, visit the GitHub page.
Comfyroll Studio offers custom nodes for SDXL and SD1.5, including Multi-ControlNet, LoRA, Aspect Ratio, and Process Switches. Maintained by Suzie1, it enhances functionality but requires up-to-date versions to avoid issues.
GraftingRayman in ComfyUI offers advanced image manipulation nodes, enabling users to perform complex edits and transformations on images within the ComfyUI framework.
audio-separation-nodes-comfyui enables users to separate an audio track into distinct stems such as vocals, bass, drums, and other elements. It also provides tools for recombining, tempo matching, and slicing/cropping audio.
ComfyUI-Sub-Nodes enables the creation and invocation of subgraphs within ComfyUI, streamlining complex workflows by encapsulating and reusing node groups.
ComfyUI Extra Samplers offers a range of custom samplers, including SamplerCustomNoise, SamplerCustomNoiseDuo, and SamplerCustomModelMixtureDuo, enhancing the default capabilities of ComfyUI with specialized sampling options.
ComfyUI_Gemini_Flash is a custom node for ComfyUI that integrates the Gemini 1.5 Flash model, enabling users to analyze and adapt images to text prompts for text2image tasks using both text and vision-based inputs.
ComfyUI-Florence-2 is a versatile extension supporting large or base models, enabling captioning and bounding box (bbox) task modes, with additional features planned for future updates.
ComfyUI-FrameFX offers custom nodes for frame interpolation and video processing within ComfyUI, enhancing video editing capabilities by enabling smoother transitions and advanced frame manipulation.
ComfyUI-Miaoshouai-Tagger is a node designed for efficient image tagging and captioning, utilizing the Florence-2-base-PromptGen model to generate accurate and relevant tags and descriptions for images.
ComfyUI-Open-Sora is a Linux-exclusive extension for ComfyUI, enhancing its functionality with advanced features and improved user experience.
ZZX Nodes offers essential tools for video processing and editing, including StreamRecorder for capturing streams, VideoFormatConverter for format changes, and ZZX_PaintsUndo for undoing paint actions.
ComfyUI-IF_AI_tools offers various AI tools for Comfy UI, starting with visual language (VL) and prompt creation tools using Ollma as the backend, with plans for further development as time permits.
ComfyUI-ToonCrafter integrates ToonCrafter with ComfyUI, enabling generative keyframe animation. It supports animation rendering and prediction in Blender, enhancing animation workflows.
DiffMorpher-ComfyUI is a custom node for integrating DiffMorpher into ComfyUI, enabling advanced workflow functionalities. It enhances the base workflow, providing seamless compatibility and extended features for users.
Tiled Diffusion & VAE for ComfyUI allows large image drawing and upscaling with limited VRAM using advanced diffusion tiling algorithms, Mixture of Diffusers and MultiDiffusion, along with pkuliyi2015's Tiled VAE algorithm.
ComfyUI-Ollama-Describer is an extension for ComfyUI enabling the use of LLM models from Ollama, including Gemma, Llava, Llama2, Llama3, and Mistral. Notably, the LLaVa model excels in image comprehension and question answering, akin to multimodal models like GPT-4.
ComfyUI OOTDiffusion is a custom node for ComfyUI that seamlessly integrates the OOTDiffusion functionality, enhancing the user interface with advanced diffusion capabilities.
ComfyUi-Ollama-YN integrates custom ComfyUI Nodes with the Ollama Python client to enhance interaction and provide improved prompt descriptors for stable diffusion.
ComfyUI Extension's 'segment anything' leverages GroundingDino and SAM to use semantic strings for segmenting any element within an image, offering a specialized version of sd-webui-segment-anything.
ComfyUI-Documents is an extension for ComfyUI that enhances workflows by enabling advanced document processing. It supports loading, parsing, and converting various document types (PDF, TXT, DOC, DOCX), extracting text, and converting PDF pages to images, integrating seamlessly with ComfyUI projects.
ComfyUI-UltraEdit-ZHO is an unofficial implementation of UltraEdit (Diffusers) for ComfyUI, enhancing the user interface with advanced editing capabilities.
ComfyUI Browser is an image, video, and workflow manager for ComfyUI, allowing users to add these elements to collections and load them into ComfyUI, ensuring collections are accessible everywhere.
Stable-Diffusion-temperature-settings allows users to adjust the temperature settings for both UNET and CLIP within the ComfyUI interface, enhancing control over the diffusion process.
Uncond-Zero-for-ComfyUI enables sampling in Stable Diffusion without generating any unconditional outputs, streamlining the process and enhancing efficiency.
Comfyui-prompt-composer is a tool suite for managing prompts, allowing users to sequence and group strings using nodes. These nodes can be chained in any order, facilitating flexible and logical prompt creation.
ComfyUI Iterative Mixing Nodes enhance image generation by iteratively refining outputs. Key nodes include Iterative Mixing KSampler, Batch Unsampler, and Iterative Mixing KSampler Advanced, optimizing the sampling process for improved results.
DynamicPrompts Custom Nodes for ComfyUI include Random Prompts, Combinatorial Prompts, I'm Feeling Lucky, Magic Prompt, and Jinja2 Templates. This library integrates with ComfyUI, enabling dynamic prompt generation within the interface.
ComfyUI ProPainter Nodes is a custom node implementation of the ProPainter framework designed for video inpainting, enhancing video editing capabilities within the ComfyUI environment.
ComfyUI AnyNode: Any Node you ask for enables the auto-generation of functional nodes using LLMs, allowing for the creation of complex workflows. It supports API compatibility with OpenAI, LocalLLMs, and Gemini.
Cozy Human Parser is a ComfyUI node designed to automatically extract masks for body regions and clothing/fashion items, developed by the CozyMantis squad.
Cozy Reference Pose Generator enables effortless creation of OpenPose face and body reference poses within ComfyUI, developed by the CozyMantis team.
The Recommended Resolution Calculator automatically sets the initial SDXL ratio/size and Upscale Factor based on your desired final resolution, ensuring optimal output. It also offers 2x/4x reverse Upscale Factor options to avoid poor initial ratios/resolutions.
ComfyUI-ZeroShot-MTrans is an unofficial ComfyUI custom node enabling Zero-Shot Material Transfer from a single image. It transfers material properties (e.g., gold) from an exemplar image to an input image (e.g., an apple) while maintaining accurate lighting and consistency.
Comfyui-sound-lab integrates nodes like Music Gen, Audio Play, and Stable Audio to enhance audio processing capabilities within the ComfyUI framework, enabling advanced music generation and playback functionalities.
ComfyUI-OpenDiTWrapper provides wrapper nodes for OpenDiT, enabling support for Open-Sora's text-to-image (t2i) and image-to-image (i2i) functionalities within the ComfyUI framework.
ComfyUI-I2V-Adapter is a custom node for ComfyUI that integrates the I2V-Adapter, enhancing image-to-video conversion capabilities within the ComfyUI framework.
ComfyUI-MARS5-TTS is a custom node for ComfyUI, integrating the MARS5-TTS text-to-speech system. It enhances ComfyUI by enabling advanced TTS functionalities, leveraging MARS5-TTS's capabilities for improved speech synthesis.
LoRA Power-Merger ComfyUI is an extension designed for merging LoRAs, featuring various merge techniques, including dare, and supports XY plots, which require efficiency nodes.
ComfyUI-Keyframed integrates the [a/keyframed](https://github.com/dmarx/keyframed) library into ComfyUI, enabling users to define and manipulate parameter curves through a ComfyUI interface, facilitating parameter and prompt keyframing.
Runtime44 ComfyUI Nodes offer a suite of tools including Runtime44Upscaler, ColorMatch, DynamicKSampler, ImageOverlay, ImageResizer, ImageToNoise, MaskSampler, TiledMaskSampler, IterativeUpscaleFactor, ImageEnhance, and FilmGrain, enhancing image processing and manipulation capabilities.
Phi-3-mini in ComfyUI integrates nodes like Phi3mini_4k_ModelLoader_Zho, Phi3mini_4k_Zho, and Phi3mini_4k_Chat_Zho, enhancing model loading, processing, and chat functionalities within the ComfyUI framework.
ComfyUI-UniAnimate is a custom node for ComfyUI that integrates UniAnimate, enhancing animation capabilities within the ComfyUI framework. It streamlines the animation process, offering advanced features for creating dynamic content.
Sketch2Manga in ComfyUI Extension applies screentone effects to line drawings or colored illustrations using advanced diffusion models, enhancing the manga-style appearance of your artwork.
A8R8 ComfyUI Nodes provide Base64Image Input and Output Nodes, enabling seamless integration with ComfyUI for handling Base64 image data.
SaltAI_AudioViz integrates ComfyUI nodes to create intricate audio-reactive visualizations, enhancing visual experiences by dynamically responding to audio inputs.
ComfyUI-CCSR is an upscaler node for ComfyUI, designed to enhance image resolution. It integrates seamlessly into the ComfyUI framework, providing users with advanced upscaling capabilities for improved image quality.
Comfyui-ergouzi-samplers offers a partial redraw sampler and a variant seed sampler, enhancing image processing by allowing selective redrawing and generating diverse outputs from different seed variations.
AIFSH/ComfyUI-AuraSR integrates AuraSR into ComfyUI, providing a node for advanced super-resolution tasks. This extension enhances image quality by leveraging AuraSR's capabilities within the ComfyUI framework.
mape's helpers enhance ComfyUI with multi-monitor image preview, variable assignment/wireless nodes, prompt tweaking, command palette, pinned favorite nodes, node navigation, fuzzy search, node time tracking, and error management.
V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation balances control signals like pose, image, and audio in portrait video generation. It uses progressive dropout to enhance weak signals, ensuring effective convergence and controlled generation.
ComfyUI_Aniportrait enables video generation through self-driven, face reenactment, and audio-driven methods using a reference image, leveraging the AniPortrait framework for dynamic and realistic animations.
ComfyUI-FaceChain enhances reasoning speed and offers advanced custom process controls, making it a powerful tool for efficient and tailored operations within the ComfyUI framework.
ComfyUI_Llama3_8B integrates Llama3_8B into ComfyUI, utilizing a pipeline workflow to enhance functionality and streamline processes.
ComfyUI-Hallo is a custom node for ComfyUI, designed to integrate with the Hallo project from Fudan Generative Vision. It enhances ComfyUI's functionality by incorporating Hallo's advanced generative vision capabilities.
ComfyUI-SD3-Powerlab enhances image processing with nodes like Render SD3 Attention, SD3 Attention To Image, and SD3 Image Into Attention, optimizing attention mechanisms for superior visual outputs.
ComfyUI-Transformers integrates computer vision and natural language processing to develop intuitive, user-friendly interfaces, enhancing accessibility and engagement in technology.
Derfuu_ComfyUI_ModdedNodes automates calculations based on image sizes or specific user-defined parameters, enhancing workflow efficiency within the ComfyUI environment.
LoadLoraWithTags: This ComfyUI extension allows users to save and load trigger words for loras from a JSON file and automatically fetch missing ones from Civitai.
Comfyui-ultralytics-yolo integrates YOLO object detection into ComfyUI, enabling users to detect objects by label within the interface. This extension enhances ComfyUI's functionality by adding precise object recognition capabilities.
The ComfyUI Extension sigmas_tools_and_the_golden_scheduler provides nodes for mixing sigmas and a custom scheduler utilizing phi. It also includes a feature using eval() for scheduling with custom formulas.
ComfyUI-HQ-Image-Save adds Image Save nodes for TIFF 16-bit and EXR 32-bit formats, ideal for users applying LUTs or color corrections, ensuring maximum color accuracy preservation.
ComfyUI 3D Pose Editor enables users to manipulate and edit 3D character poses within the ComfyUI framework. It provides intuitive tools for adjusting joint positions and orientations, enhancing the precision and creativity in 3D modeling projects.
Prompt Injection Node for ComfyUI enables precise control over image generation by injecting specific prompts into Stable Diffusion UNet blocks, particularly MID0 and MID1. It offers three node variations for flexible integration, customizable learning rates for targeted adjustments, and potential for a 'Mix of Experts' approach by dynamically swapping blocks based on prompt content.
ComfyUI-BrushNet-Wrapper integrates Diffusers' BrushNet into ComfyUI via wrapper nodes, enabling seamless use of BrushNet's features within the ComfyUI environment.
ComfyUI-Lora-Auto-Trigger-Words is a project forked from LoadLoraWithTags, designed to provide custom nodes for easy access to tags that trigger a lora.
ComfyUI-Openpose-Editor-Plus enhances the Openpose Editor with advanced node functionalities, enabling more precise and efficient pose editing within the ComfyUI framework.
ComfyUI-UVR5 is a custom code extension for the Ultimate Vocal Remover GUI (UVR5) designed to efficiently separate vocals from background music, enhancing audio processing capabilities.
comfyui's gaffer(ComfyUI native implementation of IC-Light. ) provides nodes for loading IC-Light models, applying IC-Light effects, creating simple light sources, and calculating normal maps, enhancing lighting and shading in 3D graphics.
Masquerade Nodes is a low-dependency node pack focused on handling masks. The author suggests using Impact-Pack for better functionality unless dependency issues arise.
The wlsh_nodes extension for ComfyUI includes nodes like Checkpoint Loader with Name, Save Prompt Info, Outpaint to Image, CLIP Positive-Negative, SDXL Quick Empty Latent, and more, enhancing functionality and workflow efficiency.
ComfyUI-B-LoRA enables the loading and application of B-LoRA models, specifically designed to work with SDXL (sdxl_base_1.0).
ComfyUI-MimicBrush is a custom node for ComfyUI that integrates MimicBrush, enabling inpainting using a reference image.
DZ-FaceDetailer is a custom node for ComfyUI, inspired by the !After Detailer extension from auto1111. It uses Mediapipe and YOLOv8n to detect faces and create masks for enhanced facial detail.
WAS_Extras provides nodes for advanced image processing, including Conditioning (Blend), Inpainting VAE Encode (WAS), and VividSharpen, along with experimental and auxiliary helper nodes for enhanced functionality.
comfyui_lumaAPI is an unofficial extension of the Luma API for ComfyUI, designed for educational purposes. It integrates Luma API functionalities into ComfyUI, enhancing its capabilities for learning and experimentation.
ComfyUI-Flowty-TripoSR integrates the TripoSR model into ComfyUI, enabling fast feedforward 3D reconstruction from a single image. Developed by Tripo AI and Stability AI, it simplifies creating 3D models directly within ComfyUI.
Comfy-Photoshop-SD enhances Photoshop with nodes for loading images, generating latent noise, combining latents, and applying ControlNet scripts. It supports metadata, base64 strings, Loras prompts, and auto-seeding for streamlined workflows.
ComfyI2I enhances ComfyUI with custom nodes for advanced image-to-image processing, enabling users to perform complex transformations and manipulations within the interface.
ComfyUI-AnimateAnyone-Evolved enhances AnimateAnyone by using image sequences and reference images to create stylized videos. It aims for pose-to-video results at 1+ FPS on GPUs like RTX 3080 or better.
ComfyUI-AnimateAnyone-reproduction is a custom node for ComfyUI that integrates the animate-anyone-reproduction functionality, enabling seamless animation capabilities within the ComfyUI framework.
ComfyUI-Animated-optical-illusions enables the creation of dynamic optical illusions within the ComfyUI framework, enhancing visual experiences by integrating animated elements that manipulate perception.
ComfyUI-DragAnything is an extension for ComfyUI that enables users to intuitively manipulate UI elements by dragging and dropping. It enhances user interaction by allowing seamless repositioning and customization of interface components.
ComfyUI-DynamiCrafter enhances ComfyUI with improved dynamic capabilities, higher resolution outputs, and stronger coherence in visual elements, providing a more refined and cohesive user interface experience.
ComfyUI-Flowty-CRM is a custom node for ComfyUI that integrates Convolutional Reconstruction Models, enabling high-fidelity feed-forward single image-to-3D generation directly within the interface.
ComfyUI-Flowty-LDSR is a custom node for ComfyUI that integrates Latent Diffusion Super Resolution (LDSR) models, enhancing image resolution capabilities within the interface.
ComfyUI-Hangover-Moondream is a lightweight multimodal large language model extension for ComfyUI. It requires downloading and executing additional Python code from Huggingface, emphasizing the need to trust the creator for secure use.
ComfyUI-Hangover-Nodes includes MS kosmos-2 Interrogator, Save Image w/o Metadata, and Image Scale Bounding Box nodes, implementing Microsoft's kosmos-2 image-to-text transformer for enhanced image processing and metadata management.
ComfyUI-Latent-Modifiers enhances the diffusion process in ComfyUI by providing nodes that modify latent variables, including adjustments for sharpness, tonemap, rescale, and extra noise.
ComfyUI-MotionCtrl-SVD enhances ComfyUI by integrating MotionCtrl-SVD weights, enabling advanced motion control capabilities. Users need to download the weights and place them in the ComfyUI models checkpoints directory.
ComfyUI-MotionCtrl enables motion control in ComfyUI by integrating specific weights. Users must download the MotionCtrl weights and place them in the ComfyUI models checkpoints directory to activate this functionality.
OpenAINode integrates with ComfyUI to connect seamlessly to OpenAI API-based servers, enabling efficient interaction and data exchange.
ComfyUI-Qwen-2 integrates Qwen-2 models into ComfyUI, enabling advanced AI functionalities. It supports seamless model loading, configuration, and execution within the ComfyUI interface, enhancing user experience and efficiency.
ComfyUI-RAFT integrates RAFT into ComfyUI to create motion brushes, enabling dynamic motion effects in user interfaces.
ComfyUI-ToSVG converts raster images to SVG format using the a/VTracer library, aiding designers and developers in programmatically handling vector graphics.
ComfyUI-WhisperX is a custom node for ComfyUI that facilitates audio subtitling by integrating functionalities from WhisperX and Translators repositories.
ComfyUI-fastblend enhances ComfyUI with nodes for video-to-video processing, including image rebatching and openpose integration, optimizing video editing workflows.
ComfyUI_Mexx_Poster is an extension for ComfyUI that introduces specialized nodes designed to enhance poster creation workflows. It streamlines the process, offering tools tailored for efficient and creative poster design.
ComfyUI_StreamingT2V is an extension for ComfyUI that enables real-time text-to-video generation. It leverages advanced algorithms to convert textual descriptions into dynamic video content, enhancing user interaction and content creation.
Batch Rembg for ComfyUI is a tool designed to efficiently remove backgrounds from multiple images simultaneously, streamlining the process for users who need to edit large batches of images within the ComfyUI interface.
comfyUI_FrequencySeparation_RGB-HSV offers a set of straightforward nodes designed for frequency separation and recombination using both RGB and HSV methods, enhancing image processing capabilities within the ComfyUI framework.
ComfyUI Portrait Master 简体中文版 (comfyui-portrait-master-zh-cn) is a user-friendly extension designed to enhance portrait editing capabilities within the ComfyUI framework, providing simplified Chinese language support for improved accessibility and usability.
ComfyUI-ArtGallery is an extension for ComfyUI that enables prompt visualization and art gallery features. Note that installation requires 2GB of space and may involve a lengthy download time.
ComfyUI Noise extension offers 6 nodes for ComfyUI, enhancing control and flexibility over noise management.
Stability API nodes for ComfyUI include Stability SD3, Outpainting, Search and Replace, Image Core, Inpainting, Remove Background, and Creative Upscale. Configure these nodes by setting the API key via environment variable, file, or node-specific override.
Image-Captioning-in-ComfyUI provides custom nodes for captioning images, preparing them for LoRA training.
Quality of life Suit:V2 enhances image and string processing with custom nodes for latent tools and model interfacing, including ChatGPT/DallE-2. Note: It currently lacks support for the new OpenAI API, causing compatibility issues.
ComfyUI-Text_Image-Composite [WIP] is a tool that integrates various nodes like Text_Image_Zho, Text_Image_Multiline_Zho, RGB_Image_Zho, and AlphaChanelAddByMask to enable advanced text and image compositing functionalities.
ImagesGrid is a tool featuring a viewer node that enables users to check multiple outputs simultaneously in a grid format, akin to the X/Y Plot extension.
StyleAligned for ComfyUI enables consistent styling across image batches by using the first image as a style reference, ensuring uniformity in the appearance of all subsequent images in the batch.
ComfyUI-Mana-Nodes enhances ComfyUI with features like font animation, speech recognition, caption generation, and text-to-speech (TTS), providing advanced multimedia capabilities for dynamic user interfaces.
Geowizard depth and normal estimation in ComfyUI is a diffusers (0.27.2) wrapper node that automatically downloads the Geowizard model from Huggingface to ComfyUI/models/diffusers/geowizard, enabling depth and normal estimation functionalities.
Chaosaiart-Nodes enables LowVRAM animation creation, including txt2video, img2video, and video2video, with frame-by-frame processing. It features prompt and checkpoint switches, caching, frame counting, and Ksampler for txt2img and img2img.
ComfyUI_zfkun is a node collection for ComfyUI, offering tools like text preview, multi-platform and multi-language text translation, image loading, and webcamera capture functionalities.
ComfyUI_WordCloud generates visual word clouds from text data using nodes like Word Cloud and Load Text File, enabling users to create graphical representations of word frequency and importance within a given text.
✨ Clarity AI - Creative Image Upscaler and Enhancer for ComfyUI is a tool designed to enhance and upscale images to high resolution. It serves as a Magnific AI alternative for ComfyUI, requiring an API key for functionality.
ComfyUI-FishSpeech is a custom node for ComfyUI, designed to integrate with the fish-speech project by fishaudio. It enhances ComfyUI's functionality by enabling speech-related features from the fish-speech repository.
ResAdapter for ComfyUI integrates the ResAdapter node into ComfyUI, enabling users to utilize the ResAdapter functionality seamlessly within the ComfyUI environment.
ComfyUI-StylizePhoto-MZ is a stylized node for ComfyUI that uses I2I and lora to apply a clay style effect to photos. It features simple operation and includes a watermark function.
ComfyUI StoryCreater generates short stories using nodes like story_sampler_simple, text2, and kosmos2_sampler. It employs a custom dataset and a fine-tuned Phi-3 model for enhanced storytelling.
ComfyUI_StreamDiffusion is a straightforward implementation of StreamDiffusion, designed to enable real-time interactive generation within the ComfyUI framework.
ComfyUI_VisualStylePrompting integrates Visual Style Prompting with Swapping Self-Attention into ComfyUI, enhancing image generation by allowing dynamic style changes through self-attention mechanisms.
SuperPrompter Node for ComfyUI leverages the SuperPrompt-v1 model from Hugging Face to generate text from user prompts, offering multiple parameters to fine-tune the text generation process.
comfyUI_TJ_NormalLighting is a custom node for comfyUI that utilizes normal maps to apply virtual lighting effects to images, enhancing visual depth and realism.
Rembg Background Removal Node for ComfyUI (Better) enhances the original node by allowing users to select ONNX models, offering improved background removal capabilities within the ComfyUI framework.
Character Face Swap utilizes LoRA and embeddings to seamlessly exchange faces between characters, enhancing visual content creation by allowing precise and realistic face replacements.
APISR IN COMFYUI is an unofficial implementation designed to enhance both image and video processing within the ComfyUI framework.
Allor Plugin enhances ComfyUI by prioritizing transparency and performance, ensuring a seamless and efficient user experience.
ComfyUI-AniPortrait is an extension designed to enhance ComfyUI by integrating AniPortrait features. It focuses on improving user interface aesthetics and functionality, providing a seamless experience for creating and managing animated portraits.
ComfyUI-BRIA_AI-RMBG is an unofficial implementation of the BRIA RMBG Model designed for ComfyUI, focusing on enhancing user interface functionality.
ComfyUI-Chat-GPT-Integration is an extension that enhances ComfyUI by integrating ChatGPT using the new OpenAI API, based on the ComfyUI-QualityOfLifeSuit_Omar92 extension.
ComfyUI - Apply LoRA Stacker with DARE is an experimental tool designed to integrate multiple LoRAs using the DARE method, enhancing the efficiency and performance of LoRA applications.
DepthFM IN COMFYUI is an unofficial implementation of DepthFM, designed to integrate depth-based feature mapping into the ComfyUI framework, enhancing its capability to process and visualize depth information in images.
ComfyUI-Diffusers integrates the diffuser pipeline into ComfyUI, enhancing its functionality by allowing users to utilize advanced diffusion techniques within the ComfyUI framework.
ComfyUI-Gemini integrates Gemini-pro and Gemini-pro-vision into ComfyUI, enhancing its functionality with advanced features and improved user experience.
ComfyUI HiDiffusion offers simple custom nodes for testing and utilizing HiDiffusion technology, enhancing the functionality and experimentation capabilities within the ComfyUI framework.
ComfyUI-IF_AI_WishperSpeechNode is a Text-to-Speech (TTS) application utilizing Whisper Speech for voice synthesis, enabling users to train voice models quickly. Built on ComfyUI, it supports rapid training and inference.
ComfyUI-IPAnimate generates high-definition, controllable videos frame by frame using IPAdapter+ControlNet, avoiding the blurriness associated with AnimateDiff.
ComfyUI-Img2Img-Turbo enhances image-to-image processing by optimizing speed and efficiency within the ComfyUI framework. It leverages advanced algorithms to deliver faster results without compromising quality, making it ideal for high-performance image manipulation tasks.
InstanceDiffusion Nodes enable multi-object prompting within ComfyUI, allowing users to manage and manipulate multiple objects in a single diffusion process efficiently.
ComfyUI-InstantID is an unofficial implementation of InstantID for ComfyUI, designed to integrate InstantID's functionalities into the ComfyUI framework, enhancing its capabilities.
ComfyUI for InstructIR enhances image restoration by integrating advanced algorithms from InstructIR, providing a user-friendly interface for improved image quality and restoration efficiency.
ComfyBreakAnim is a ComfyUI extension featuring nodes like BreakFrames, GetKeyFrames, and MakeGrid, designed to enhance animation workflows by breaking down frames, extracting keyframes, and creating grids for efficient animation management.
ComfyUI-MuseV is an extension for ComfyUI that enhances user interface design by integrating advanced visual elements and interactive features. It streamlines the creation of visually appealing and user-friendly interfaces.
ComfyUI PhotoMaker (ZHO) is an unofficial implementation of TencentARC's PhotoMaker for ComfyUI, designed to enhance photo editing capabilities within the ComfyUI framework.
ComfyUI PiperTTS enables Text-to-Speech conversion within ComfyUI using the Piper library, facilitating seamless integration for generating speech from text inputs.
ComfyUI-PixArt-alpha-Diffusers is an unofficial implementation of PixArt-alpha-Diffusers designed for integration with ComfyUI, enhancing its functionality by incorporating advanced diffusion techniques from PixArt-alpha.
ComfyUI-Portrait-Maker enhances portrait images using nodes like RetainFace, FaceFusion, and SkinRetouching. It merges, masks, and refines facial features, ensuring high-quality, detailed portrait enhancements.
ComfyUI-Prompt-Expansion enhances dynamic prompt generation using GPT-2, running locally on your device, to create more engaging and varied text outputs.
ComfyUI-Qwen-VL-API integrates QWen-VL-Plus and QWen-VL-Max into ComfyUI, enhancing its visual language processing capabilities. This extension optimizes image and text analysis within the ComfyUI framework.
ComfyUI-RAVE is an unofficial implementation of RAVE within the ComfyUI framework, designed to integrate RAVE's video processing capabilities into ComfyUI, enhancing its functionality for video-related tasks.
ComfyUI-SVD-ZHO (WIP) provides workflows and auxiliary nodes designed to enhance Stable Video Diffusion (SVD) processes, optimizing video generation and editing within the ComfyUI framework.
ComfyUI SegMoE is an unofficial implementation of Segmind's Mixture of Diffusion Experts for ComfyUI, enhancing image processing by integrating advanced diffusion models to improve segmentation tasks.
ComfyUI-bleh enhances TAESD previews and introduces BlehHyperTile for improved user experience.
ComfyUI-depth-fm provides fast and accurate monocular depth estimation, enhancing image analysis by determining depth from single images efficiently.
ComfyUI-safety-checker is a node for ComfyUI designed to identify and filter NSFW content, ensuring safety and appropriateness in user-generated outputs.
ComfyUI-sonar is a momentum-based sampling extension for ComfyUI, implementing Sonar sampling to enhance the user interface experience.
ComfyUI-sudo-latent-upscale enables direct upscaling within the latent space, optimized for SD1.5 and drawn content. Inspired by city96/SD-Latent-Upscaler and Ttl/ComfyUi_NNLatentUpscale, it may include new architectures or model updates in the future.
ComfyUI Cutoff enhances text prompt control by offering custom nodes that refine and manage the effects of input prompts, ensuring more precise and tailored outcomes in the user interface.
ComfyUI_GLM4Node integrates GLM4 Vision into ComfyUI, enhancing visual processing capabilities. It leverages advanced machine learning models to improve image recognition and analysis within the ComfyUI framework.
ComfyUI_GradientDeepShrink enhances image processing by integrating the GradientPatchModelAddDownscale (Kohya Deep Shrink) node, optimizing gradient-based downscaling for improved visual quality in ComfyUI.
JPS Custom Nodes for ComfyUI offers a range of nodes for managing SDXL resolutions, basic settings, IP adapter settings, revision settings, and prompt styling. It includes tools for cropping images, generating date-time strings, multiplying resolutions, and various 5-to-1 switches for integers, images, latents, conditioning, models, VAE, and ControlNet.
ComfyUI_NetDist enables running ComfyUI workflows across multiple local GPUs or networked machines, featuring nodes for remote images and local remote control.
SeeCoder [WIP] enables the generation of CLIP from image inputs, differing from unCLIP by functioning across all models. Users must download the necessary model file from the **Install Models** section to utilize this extension.
SimpleTiles is a ComfyUI extension featuring TileSplit and TileMerge nodes, designed to facilitate the splitting and merging of image tiles for efficient processing and manipulation within the ComfyUI framework.
Tiled sampling for ComfyUI enables denoising of larger images by splitting them into smaller tiles and processing each tile incrementally. This method minimizes seams in the final image by randomizing tile positions and denoising one step at a time.
ComfyUI_experiments offers a suite of nodes including ModelSamplerTonemapNoiseTest, TonemapNoiseWithRescaleCFG, and various ModelMerge options, enhancing model sampling, tonemapping, noise testing, and classifier-free guidance rescaling.
ComfyUI fabric integrates nodes from the paper "FABRIC: Personalizing Diffusion Models with Iterative Feedback," enabling personalized diffusion models through iterative feedback and attention-based reference image conditioning.
The simple wildcard for ComfyUI extension allows users to insert arbitrary inputs into prompts using wildcards, enhancing workflow efficiency. It includes features like VAELoaderDecoder and SimplerSample to streamline processes.
Restart Sampling in ComfyUI enhances generative processes by implementing nodes based on the 'Restart Sampling for Improving Generative Processes' paper. This technique refines outputs by periodically restarting the sampling process, improving overall quality.
ComfyUi-NoodleWebcam is a node that captures and records frames from a webcam, sending them to your preferred node for further processing or integration.
ComfyUI Neural Network Latent Upscale is a custom ComfyUI node, NNLatentUpscale, designed for fast latent upscaling via a compact neural network, bypassing the need for VAE-based decoding and encoding.
SDXL Prompt Styler (customized version by wolfden) offers custom nodes that enhance prompt styling capabilities, building on the original SDXL Prompt Styler by twri.
Comfyui_image2prompt is an extension for ComfyUI that converts images to text using nodes like Image to Text and Loader Image to Text Model. It facilitates seamless image-to-text transformation within the ComfyUI framework.
ControlNet-LLLite-ComfyUI integrates the LLLiteLoader node into ComfyUI, enhancing its functionality by enabling lightweight, efficient control mechanisms for UI elements.
SD-Latent-Upscaler enhances stable diffusion latents by utilizing a compact neural network for upscaling, improving image resolution and quality efficiently.
SeargeSDXL offers custom nodes for ComfyUI, streamlining the use of SDXL with an img2img workflow that leverages both base and refiner checkpoints for enhanced image processing.
StableZero123-comfyui is a node wrapper leveraging the Zero123plus model to generate 3D views from a single image, enhancing 3D visualization capabilities.
Avatar Graph integrates nodes for sam + bpy operations, enabling the creation of workflows for generative 2D character rigging.
Canvas Tab offers a comprehensive image editor with mask support, featuring nodes for receiving and sending images to the editor, enabling seamless image manipulation within the extension.
Save Image with Generation Metadata for ComfyUI enables saving images along with their generation metadata. It supports auto-detection of geninfo from Civitai and Prompthero, and is compatible with png, jpeg, and webp formats.
Comfy-plasma is a ComfyUI extension featuring nodes like Plasma Noise, Random Noise, Greyscale Noise, Pink Noise, Brown Noise, and Plasma KSampler, enhancing noise generation and sampling capabilities.
Pixelization is a ComfyUI node designed to pixelize images, transforming them into a mosaic-like appearance by converting fine details into larger, uniform blocks of color.
AnimateDiff integration for ComfyUI adapts from sd-webui-animatediff, requiring the download of either mm_sd_v14.ckpt or mm_sd_v15.ckpt. Place the model weights in the specified directory without altering the filenames.
Comfyui-fitsize offers nodes like Fit Size, Load and Resize, Pick Image, Crop, and Mask, enabling images to fit within a bounding box efficiently.
ComfyUI InstantID Faceswapper integrates InstantID's faceswap technology into ComfyUI, enabling efficient face-swapping using LCM Lora for high-quality results in minimal steps. It is compatible exclusively with SDXL checkpoints.
The comfyui-job-iterator extension enables iteration over sequences within a single workflow run, replacing ComfyUI's execution for iterative processing functionality.
ComfyUI - Mask Bounding Box allows users to select specific size masks from images, enabling the replacement of any part of an SDXL image with an SD1.5 output when used with ClipSEG.
ComfyUI Optical Flow provides three nodes to compute optical flow between image pairs, visualize the flow, and apply it to another image of the same dimensions, primarily for adjacent video frames. It utilizes code from Deforum and is released under the MIT license.
comfyui-previewlatent is a ComfyUI plugin that allows users to preview latent images without VAE decoding, providing faster intermediate result previews and an efficient 'preview image' option.
ComfyUI-TCD-scheduler integrates custom sampler nodes implementing Zheng et al.'s Trajectory Consistency Distillation, enhancing ComfyUI with advanced sampling techniques for improved performance.
LoRA Tag Loader for ComfyUI is a custom node for ComfyUI that reads LoRA tags from text and integrates them into the checkpoint model, streamlining the process of loading specific tags efficiently.
Cute Comfy adds a configurable folder watcher that auto-converts Comfy metadata into a Civitai-friendly format for seamless resource tagging during image uploads, while enhancing your UI. 💜
Demofusion-comfyui is a custom node that integrates Ruoyi Du's DemoFusion technique into the ComfyUI environment, enabling seamless adaptation and implementation of DemoFusion's functionalities within ComfyUI.
Facerestore CF (Code Former) is a ComfyUI extension node designed to restore faces in images, similar to the face restore option in AUTOMATIC1111 webui. It supports the CodeFormer Fidelity parameter and requires downloading specific face restoration and detection models.
komojini-comfyui-nodes provides custom nodes for ComfyUI, specifically designed for video generation, including a YouTube Video Loader node.
Rembg Background Removal Node for ComfyUI enables users to efficiently remove backgrounds from images within the ComfyUI interface, streamlining the image editing process by integrating advanced background removal capabilities directly into the UI.
SDXL Prompt Styler is a node that styles prompts using predefined templates from a JSON file, enhancing prompt customization and consistency.
stability-ComfyUI-nodes includes ColorBlend, ControlLoraSave, and GetImageSize nodes, essential for tasks like the Control-LoRA recolor example, enhancing image processing and manipulation capabilities.
The ComfyUI Extension 'tiled_ksampler' includes nodes like Tiled KSampler, Asymmetric Tiled KSampler, and Circular VAEDecode, enhancing image sampling and decoding capabilities for more efficient and varied outputs.
ymc-node-suite-comfyui is an extension for ComfyUI, featuring nodes that offer utility functions including text handling, region management, and input/output operations.
ComfyUI-APISR integrates APISR upscale models into ComfyUI, enhancing image resolution capabilities. Note: The repository name has been updated to ComfyUI-APISR-KJ.
ComfyUI-DDColor integrates the DDColor tool into ComfyUI, enabling users to utilize advanced color manipulation features within the ComfyUI environment.
DiffusionLight implementation for ComfyUI simplifies the creation of light probes using the DiffusionLight method. It requires placing the included LoRA, converted from the original diffusers, into the ComfyUI/loras folder.
ComfyUI-LightGlue integrates LightGlue into ComfyUI to create motion brush effects, enhancing visual dynamics in user interfaces.
Image Resize for ComfyUI offers tools to resize images while maintaining their proportions, eliminating the need for manual calculations. It also ensures that any accompanying mask is resized and adjusted in sync with the image.
ComfyUI Loopchain is an extension for ComfyUI featuring nodes designed for animation. Its core function is the loopchain mechanism, where a chain of nodes, including a loop node, executes repeatedly within the workflow.
Latent Consistency Model for ComfyUI is a custom node that integrates a Latent Consistency Model sampler into the ComfyUI framework, enhancing its sampling capabilities.
m957ymj75urz/ComfyUI-Custom-Nodes offers specialized nodes like RawText, RawTextCLIPEncode, RawTextCombine, and RawTextReplace, along with the m957ymj75urz.colors extension, enhancing text processing and customization in ComfyUI.
ComfyMath enhances ComfyUI with Math Nodes, enabling Boolean Logic, Integer and Floating Point Arithmetic, and Vec2, Vec3, and Vec4 operations and functions.
© Copyright 2024 RunComfy. All Rights Reserved.