"description":"If you see this message, your ComfyUI-Manager is outdated.\nLegacy channel provides only the list of the deprecated nodes. If you want to find the complete node list, please go to the Default channel."
"description":"A node that can be dropped into a group. When a node is then clicked within that group, all nodes and connections in that group get greyed out and the connections from the clicked node go bright red."
"description":"A collection of nodes which can be useful for animation in ComfyUI. The main focus of this extension is implementing a mechanism called loopchain. A loopchain in this case is the chain of nodes only executed repeatly in the workflow. If a node chain contains a loop node from this extension, it will become a loop chain."
"description":"Nodes:CRE8IT Serial Prompter, CRE8IT Apply Serial Prompter, CRE8IT Image Sizer. A few simple nodes to facilitate working wiht ComfyUI Workflows"
"description":"The easiest way to run & share any ComfyUI workflow [a/https://comfyrun.com](https://comfyrun.com)\nNOTE: Vulnerability discovered. Not being managed."
"description":"This custom node is largely identical to the usual Save Image but allows saving images also in JPEG and WEBP formats, the latter with both lossless and lossy compression. Metadata is embedded in the images as usual, and the resulting images can be used to load a workflow."
"description":"Nodes: LatentGaussianNoise, MathEncode. An experimental custom node that generates latent noise directly by utilizing the linear characteristics of the latent space."
"description":"ComfyUI Unique3D is custom nodes that running AiuniAI/Unique3D into ComfyUI[w/Please follow readme to install with ComfyUI embedded python.]"
"description":"Goal: To enable folks to rapidly build complex workflows with LLMs\nNOTE:☠️ This is experimental and not recommended to use in a production environment (yet!)"
"description":"Nodes:BatchImageFromList, Load Face Occlusion Model, Create Face Mask, Simple FaceAlign, Cacul FaceAlign, Gen Blurbord, Face Align, Face Rotate, ImageAdd, LoadImageList, SaveImage Plus, RegTextFind"
"description":"These nodes are to edit the text vectors of CLIP models, so to customize how the prompts will be interpreted. You could see it as either customisation, 'one token prompt' up to some limitation and a way to mess with how the text will be interpreted. The edited CLIP can then be saved, or as well the edited tokens themselves. The shared example weights does not contain any image-knowledge but the text vector of the words affected."
"description":"Nodes:UWU TTK Preprocessor, Pixel Perfect Resolution, Generation Resolution From Image, Generation Resolution From Latent, Enchance And Resize Hint Images, ..."
"description":"This custom node for ComfyUI provides full-body animation capabilities, including facial rigging, various lighting styles, and green screen output."
"description":"Unofficial implementation of [a/AnyText](https://github.com/tyxsspa/AnyText/tree/825bcc54687206b15bd7e28ba1a8b095989d58e3) for ComfyUI（EXP）"
"description":"After discovering @storyicon implementation here of Segment Anything, I realized its potential as a powerful tool for ComfyUI if implemented correctly. I delved into the SAM and Dino models. The following is my own adaptation of sam_hq for ComfyUI."
"description":"An alternate trajectory processor for ComfyUI-FLATTEN\nNOTE:When using this trajectory type FLATTEN will use roughly 1/4 VRAM and be ~20% faster at the cost of some consistency (especially when injection_steps are low)."
"description":"This repository contains a custom node for ComfyUI that allows users to save generative image outputs with custom filenames and folder structures. The filenames are padded to four digits, and the positive and negative prompts are embedded in the image metadata."
"description":"Nodes:Attention couple. This is a custom node that manipulates region-specific prompts. While vanilla ComfyUI employs an area specification method based on latent couples, this node divides regions using attention layers within UNet.\nNOTE: This has been integrated with cgem156-ComfyUI."
"description":"Test project for ComfyUI TensorRT Support.\nNOT WORKING YET.\nnot automatic yet, do not use ComfyUI-Manager to install !!!.\nnot beginner-friendly yet, still intended to technical users\nNOTE: The reason for registration in the Manager is for guidance, and for detailed installation instructions, please visit the repository.\nNOTE: Use 'TensorRT Node for ComfyUI' instead of this."
"description":"ComfyUI implementation for [a/AnimateLCM](https://animatelcm.github.io/) [[a/paper](https://arxiv.org/abs/2402.00769)].\b[w/This extension includes a large number of nodes imported from the existing custom nodes, increasing the likelihood of conflicts.]"
"description":"Nodes:DPK - Any Eval, DPK - Extract Array, DPK - Run External Program, DPK - Any Literals, DPK - Set Node States, DPK - Realtime Text Preview, DPK - Dynamic Action, DPK - Object To Json, DPK - Json To Object\n[w/This extension includes the ability to execute arbitrary code and programs.]"
"description":"Nodes: LoadImageWithPrivacy, RemoveImage.[w/This extension is not secure because it provides the capability to delete files from arbitrary paths.]"
"description":"ComfyUI InstantMesh is custom nodes that running TencentARC/InstantMesh into ComfyUI, this extension depends on ComfyUI-3D-Pack. Please refer to Readme carefully to install.\nNOTE: This repo is archived due to ComfyUI-3D-Pack supports InstantMesh, please check 3D-Pack directly if you need it"
"description":"Custom ComfyUI Nodes for interacting with [a/Ollama](https://ollama.com/) using the ollama python client.\nIntegrate the power of LLMs into ComfyUI workflows easily or just experiment with GPT.\nNOTE: To use this properly, you would need a running Ollama server reachable from the host that is running ComfyUI."
"description":"Customize the information saved in file- and folder names. Use the values of sampler parameters as part of file or folder names. Save your positive & negative prompt as entries in a JSON (text) file, in each folder.\n[w/This custom node has not been maintained for a long time. Please use an alternative node from the default channel.]"
"description":"Please note that the ImageTextOverlay project is no longer supported and has been moved to a new repository. For ongoing developments, contributions, and issues, please refer to the new repository at: [a/https://github.com/Big-Idea-Technology/ComfyUI-Book-Tools](https://github.com/Big-Idea-Technology/ComfyUI-Book-Tools)"
"description":"A LaMa prerocessor for ComfyUI. This preprocessor finally enable users to generate coherent inpaint and outpaint prompt-free. The best results are given on landscapes, not so much in drawings/animation."
"description":"Just a comfyui version of [a/Euler Smea Dyn Sampler](https://github.com/Koishi-Star/Euler-Smea-Dyn-Sampler). It adds the sampler directly to existing samplers."
"description":"This extension provides the ability to combine multiple nodes into a single node.\nNOTE:An identical feature now exists in ComfyUI. Additionally, this extension is largely broken with the recent versions of the codebase, so please use the built-in feature for group nodes."
},
{
"author":"ccvv804",
"title":"ComfyUI StableCascade using diffusers for Low VRAM [DEPRECATED]",
"description":"Works with RTX 4070ti 12GB.\nSimple quick wrapper for [a/https://huggingface.co/stabilityai/stable-cascade](https://huggingface.co/stabilityai/stable-cascade)\nComfy is going to implement this properly soon, this repo is just for quick testing for the impatient!"
},
{
"author":"kijai",
"title":"ComfyUI StableCascade using diffusers [DEPRECATED]",
"description":"Simple quick wrapper for [a/https://huggingface.co/stabilityai/stable-cascade](https://huggingface.co/stabilityai/stable-cascade)\nComfy is going to implement this properly soon, this repo is just for quick testing for the impatient!"
"description":"Nodes:Anime_Styler, Fantasy_Styler, Gothic_Styler, Line_Art_Styler, Movie_Poster_Styler, Punk_Styler, Travel_Poster_Styler. This extension offers 8 art style nodes, each of which includes approximately 50 individual style variations.\n\nNOTE: Due to the dynamic nature of node name definitions, ComfyUI-Manager cannot recognize the node list from this extension. The Missing nodes and Badge features are not available for this extension.\nNOTE: This extension is removed. Users who were previously using this node should install ComfyUI-styles-all instead."
"description":"Nodes: KSampler (Advanced + Perp-Neg). Implementation of [a/Perp-Neg](https://perp-neg.github.io/)\nIncludes Tonemap and CFG Rescale optionsComfyUI custom node to convert latent to RGB.[w/WARNING: Experimental code, might have incompatibilities and edge cases.]\nNOTE: In the latest version of ComfyUI, this extension is included as built-in."
"description":"This custom nodes provides loader of the IP-Adapter model.[w/NOTE: To use this extension node, you need to download the [a/ip-adapter_sd15.bin](https://huggingface.co/h94/IP-Adapter/resolve/main/models/ip-adapter_sd15.bin) file and place it in the %%**custom_nodes/IPAdapter-ComfyUI/models**%% directory. Additionally, you need to download the 'Clip vision model' from the 'Install models' menu as well.]\nNOTE: Use ComfyUI_IPAdapter_plus instead of this."
"description":"A comprehensive suite of nodes to enhance your animations. These nodes include some features similar to Deforum, and also some new ideas.<BR>NOTE: This node is merged into Comfyroll Custom Nodes."
"description":"A custom node for comfy ui to read generation data from images (prompt, seed, size...). This could be used when upscaling generated images to use the original prompt and seed."
"description":"A collection of ComfyUI custom nodes to help streamline workflows and reduce total node count.<BR>NOTE: This repository is the original repository but is no longer maintained. Please use the forked version by jags."
"description":"ComfyUI nodes for the roop A1111 webui script. NOTE: Need to download <a href='https://github.com/SumDeusVitae/FaceSwap_v01/raw/main/inswapper_128.onnx' target='blank'/>model</a> to use this node. NOTE: This is removed."
"description":"Nodes: Load U2Net model, U2Net segmentation, To mask, Segmentation to mask, U2NetBaseNormalization, U2NetMaxNormalization. NOTE: This is removed."
},
{
"author":"FizzleDorf",
"title":"AIT",
"reference":"https://github.com/FizzleDorf/AIT",
"files":[
"https://github.com/FizzleDorf/AIT"
],
"install_type":"git-clone",
"description":"Nodes: Load AITemplate, Load AITemplate (ControlNet), VAE Decode (AITemplate), VAE Encode (AITemplate), VAE Encode (AITemplate, Inpaint). Experimental usage of AITemplate. NOTE: This is deprecated extension. Use <b>ComfyUI-AIT</b> instead of this."
"description":"tomeSD(https://github.com/dbolya/tomesd) applied to ComfyUI stable diffusion UI using custom node. <B>Note:In vanilla ComfyUI, the TomePatchModel node is provided as a built-in feature.</B>"
"description":"Nodes: CLIPTextEncodeTaggerDD, ImageTaggerDD. <p style='background-color: black; color: red;'>WARNING: Installing the current version is causing an issue where ComfyUI fails to start.</p>"
"description":"ControlNet Preprocessors. (To use this extension, you need to download the required model file from <B>Install Models</B>)<BR> <p style='background-color: black; color: red;'>NOTE: Please uninstall this custom node and instead install 'ComfyUI's ControlNet Auxiliary Preprocessors' from the default channel.<BR>To use nodes belonging to <B>controlnet v1</b> such as <B>Canny_Edge_Preprocessor, MIDAS_Depth_Map_Preprocessor, Uniformer_SemSegPreprocessor, etc.</B>, you need to copy the <font color='white'>config.yaml.example</font> file to <font color='white'>config.yaml</font> and change <font color='white'>skip_v1: True</font> to <font color='white'>skip_v1: False</font>.</p>"
"description":"ModelSamplerTonemapNoiseTest a node that makes the sampler use a simple tonemapping algorithm to tonemap the noise. It will let you use higher CFG without breaking the image. To using higher CFG lower the multiplier value. Similar to Dynamic Thresholding extension of A1111. "
"description":"RescaleClassifierFreeGuidance improves the problem of images being degraded by high CFG.To using higher CFG lower the multiplier value. Similar to Dynamic Thresholding extension of A1111. (<a href='https://arxiv.org/abs/2305.08891'/>reference paper</a>)<p style='background-color: black; color: red;'>It is recommended to use the integrated custom nodes in the default channel for update support rather than installing individual nodes.</p>"
"description":"This provides a detailed model merge feature based on block weight. ModelMergeBlock, in vanilla ComfyUI, allows for adjusting the ratios of input/middle/output layers, but this node provides ratio adjustments for all blocks within each layer.<p style='background-color: black; color: red;'>It is recommended to use the integrated custom nodes in the default channel for update support rather than installing individual nodes.</p>"
"description":"These nodes provide the capability to merge SDXL base models.<p style='background-color: black; color: red;'>It is recommended to use the integrated custom nodes in the default channel for update support rather than installing individual nodes.</p>"
"description":"This node provides functionality corresponding to Reference only in Controlnet.<p style='background-color: black; color: red;'>It is recommended to use the integrated custom nodes in the default channel for update support rather than installing individual nodes.</p>"
"description":"If you see this message, your ComfyUI-Manager is outdated.\nRecent channel provides only the list of the latest nodes. If you want to find the complete node list, please go to the Default channel.\nMaking LoRA has never been easier!"
"description":"NODES: Get Prompt_Id, Success Callback\nget comfyui task id and Callback for successful image generation, in conjunction with the back-end"
"description":"Provide high-quality video and image generation capabilities, meeting creators' needs for creative content production and management through more convenient operations, richer functionalities, professional parameters, and stunning effects."
"description":"This is the rgb2x wrapper node for ComfyUI. The required models are automatically downloaded on the first run.\noriginal project : [a/https://github.com/zheng95z/rgbx](original project : https://github.com/zheng95z/rgbx)"
"description":"Use [a/Doctor Diffusion's snake oil nLoRAs](https://civitai.com/models/987843) as well as [a/other negative LoRAs](https://civitai.com/models/186617/doctor-diffusions-negative-xl-lora) easily within ComfyUI."
"description":"This node wraps the flux fill model as ComfyUI nodes. Use NF4 flux fill model, support for inpainting and outpainting image. Compared to the flux fill dev model, these nodes can use the flux fill model to perform inpainting and outpainting work under lower VRM conditions."
"description":"ComfyUI-SoundHub is a collection of audio processing nodes designed for ComfyUI, enabling seamless audio processing and generation within your ComfyUI workflows."
"description":"flux patcher for Fill Flux.Dev lora [a/https://civitai.com/models/981615/fluxfill-inpaint-lora](https://civitai.com/models/981615/fluxfill-inpaint-lora)"
"description":"[a/sd-webui-pixelart](https://github.com/mrreplicart/sd-webui-pixelart) are referenced by many webui users, this node is mean to use it in ComfyUI."
"description":"A node for ComfyUI that takes a list of masks and returns a single mask based on your criteria. For example, it can be used to mask the leftmost subject in an image containing more than one subject of the same class. The workflow below demonstrates the difference between Mask Arbiter (top) and traditional Grounding DINO masking (bottom.)"
"description":"This repository contains a custom node for ComfyUI that converts text into a JSON object. The node is designed to be user-friendly and supports multi-line JSON input."
"description":"A translation node for users in Chinese Mainland. (Because of the network firewall in Chinese Mainland, many translation APIs cannot be used normally.)"
"description":"Bytebeat is like composing music with the tools of a programmer’s toolkit. Instead of piano keys, you have operators like >>, |, and &. It’s like giving your CPU a guitar and letting it shred! 🤘"
"description":"A ComfyUI custom node that integrates Mistral AI's Pixtral Large vision model, enabling powerful multimodal AI capabilities within ComfyUI. Pixtral Large is a 124B parameter model (123B decoder + 1B vision encoder) that can analyze up to 30 high-resolution images simultaneously."
"description":"This custom node for ComfyUI is designed to optimize latent generation for use with FLUX, SDXL and SD3. It provides flexible control over aspect ratios, megapixel sizes, and upscale factors, allowing users to dynamically create latents that fit specific tiling and resolution needs."
"description":"This extension offers a new Apply-Style node for Redux that allows for changing the influence of the conditioning image on the final outcome. This effectively allows for changing the style or content of an image using a prompt while using Redux."
"description":"This repository provides custom nodes for ComfyUI designed to process audio files, performing speaker diarization and integrating speaker data into whisper-transcribed segments. These nodes utilize the PyAnnote library for speaker identification and pandas for efficient data handling."
"description":"A custom node that provides enhanced control over style transfer balance when using FLUX style models in ComfyUI. This node offers better control over the influence of text prompts versus style reference images."
"description":"his project is designed to detect whether images generated by ComfyUI are Not Safe For Work (NSFW). It uses a machine learning model to classify images as either safe or not safe for work and returns a confidence score for the NSFW classification."
"description":"ComfyUI supports over [a/rhymes-ai/Allegro](https://huggingface.co/rhymes-ai/Allegro), which uses text prompt to generate short video in relatively high quality, especially comparing to other open source solutions available for now."
"description":"Without fine-tuning, FLUX.1 Dev model cannot understand exact color codes. However, it is known that FLUX.1 Dev can repeatedly produce certain colors with certain prompt(color name). Fortunately, on CIVITAI, [a/“novuschroma” shared 155 pre-tested color names](https://civitai.com/models/879997/color-wildcards-for-flux-and-sdxl) that FLUX.1 Dev can handle. Thanks to his resource, color palette consists exclusively of 155 colors can be configured. ‘ColorPalette’ node from ComfyUI APQNodes converts input hex color code to the most similar color name(from pre-tested 155 color names) of which FLUX.1 Dev is aware."
"description":"This repository packages the latest BiRefNet model as a ComfyUI node for use, supporting chunked loading on both CPU and GPU, as well as model caching features."
"description":"NODES:SignalProcessingPaulStretch, SignalProcessingPadSynth, SignalProcessingFilter, SignalProcessingLoadAudio.\nThis repo contains 4 nodes for ComfyUI that allows for audio filtering"
"description":"LTX-Video is the first DiT-based video generation model capable of generating high-quality videos in real-time. It produces 24 FPS videos at a 768x512 resolution faster than they can be watched. Trained on a large-scale dataset of diverse videos, the model generates high-resolution videos with realistic and varied content.",
"name":"FLUX.1 [Dev] Diffusion model (scaled fp8)",
"type":"diffusion_model",
"base":"FLUX.1",
"save_path":"diffusion_models/FLUX1",
"description":"FLUX.1 [Dev] Diffusion model (scaled fp8)[w/Due to the large size of the model, it is recommended to download it through a browser if possible.]",
"description":"Welcome to ecjojo_example_nodes! This example is specifically designed for beginners who want to learn how to write a simple custom node.\nFeel free to modify this example and make it your own. Experiment with different features and functionalities to enhance your understanding of ComfyUI custom nodes. Don't be afraid to explore and customize the code to suit your needs.\nBy diving into this example and making it your own, you'll gain valuable hands-on experience in creating custom nodes in ComfyUI. Enjoy the process of learning and have fun with your custom node development journey!"
"description":"This project is an `empty` custom node that is already in its own folder. It serves as a base to build any custom node. Whenever you want to create a custom node, you can download that, put it in custom_nodes, then you just have to change the names and fill it with code!"
"description":"This module provides an annotation @ComfyFunc to streamline adding custom node types in ComfyUI. It processes your function's signature to create a wrapped function and custom node definition required for ComfyUI, eliminating all the boilerplate code. In most cases you can just add a @ComfyFunc(\"category\") annotation to your existing function."
"description":"The primitive node and dummy input are required because comfy doesn't accept requests with identical graphs. You'll also need a show text node. I like the one from ComfyUI-Custom-Scripts. I got the generic tetris remake from claude so it may or may not be ripped from somewhere else."
