ComfyUI Custom Nodes

ComfyUI-Manager is a powerful extension for ComfyUI that offers comprehensive node management, allowing users to install, remove, disable, and enable custom nodes. It supports multiple installation methods, provides three database modes for installation, enables workflow sharing, and features snapshot management, command - line tools, and component sharing. The extension can be customized via `config.ini` and comes with troubleshooting guidance. It has had several updates, including support for `uv` and the Comfy Registry.

controlnet aux pre-processor

ComfyUI-Impact-Pack is a custom node pack for ComfyUI that enhances images with features like detection, detailing, upscaling, and more. It requires ComfyUI version after April 8, 2024, and the UltralyticsDetectorProvider node needs a separate sub - pack. Key updates include changes in installation methods and feature support across versions. Installation can be done via ComfyUI - Manager or manually. It offers various core features such as detector nodes for different models, ControlNet and IPAdapter integration, mask operations, detailer nodes for image refinement, SEGS manipulation, iterative upscaling, wildcard and logic handling, and regional sampling, along with tutorials and a troubleshooting guide.

ComfyUI Frame Interpolation is a custom node set for video frame interpolation in ComfyUI. It has improved memory management, taking less RAM and VRAM. VFI nodes accept scheduling multiplier values. It offers various VFI nodes like GMFSS Fortuna VFI and RIFE VFI. Installation can be done via ComfyUI Manager or command - line. It supports non - CUDA devices experimentally. All VFI nodes are in the 'ComfyUI - Frame - Interpolation/VFI' category and require at least 2 frames. It also provides simple and complex workflow examples and cites relevant research for each VFI node.

The ComfyUI TensorRT Node enhances GPU performance for Stable Diffusion on NVIDIA RTX™ GPUs by integrating TensorRT technology. It supports models like Stable Diffusion 1.5/2.1/3.0, SDXL, SVD, etc., with specific system requirements. Installation can be done via ComfyUI Manager or manually. There are dynamic and static engine types, with dynamic preferred generally. Workflow instructions include building and using TensorRT engines. Current limitations involve ControlNet/LoRA incompatibility, and future updates are planned. The main function is to optimize Stable Diffusion performance on NVIDIA RTX™ GPUs using TensorRT, having support for multiple models, different engine types, and clear installation, workflow guidance while facing some limitations to be addressed later.\n\nThe ComfyUI TensorRT Node optimizes Stable Diffusion performance on NVIDIA RTX™ GPUs by integrating TensorRT, supports multiple models with specific VRAM requirements, offers dynamic and static engine types, provides installation and workflow guides, and has limitations like ControlNet/LoRA incompatibility to be resolved in future updates.

This repository offers a set of specialized extension nodes for ComfyUI to complement the Impact Pack, providing unique features and optimizations for AI image generation workflows. It has compatibility requirements across different versions, and includes key node categories like Lora Block Weight Management, SEGS Support Nodes, and more, covering advanced control, sampling, prompt processing, regional processing, etc., and builds on several open - source projects with a need to keep dependencies updated for optimal performance.

ComfyUI_Cutoff is an implementation of the cutoff script in ComfyUI. It allows users to limit the influence of specific words in a prompt to certain regions. By masking tokens and calculating vector differences, it can isolate color and other relations in the embedding. It introduces four nodes: Cutoff BasePrompt, Cutoff Set Region, Cutoff Regions To Conditioning, and Cutoff Regions To Conditioning (ADV). The nodes can be found under `conditioning>cutoff`, and while they work with SDXL, the effect might not be ideal for version 0.9.

This repo provides 4 ComfyUI nodes for more control over prompt weighting. The CLIP Text Encode (Advanced) node has two settings: 'token_normalization' with options like 'none', 'mean' etc., and 'weight_interpretation' including 'comfy', 'A1111' etc. It visualizes up - weighting methods and explains Compel's down - weighting. The Mix Clip Embeddings node is deprecated. For SDXL support, there are nodes like BNK_CLIPTextEncodeSDXLAdvanced with a 'balance' setting, BNK_AddCLIPSDXLParams to add SDXL parameters, and BNK_AddCLIPSDXLRParams to add refiner parameters.

This is a tiled sampler for ComfyUI. It can denoise larger images by splitting them into smaller tiles. It has additional settings like tile width, height, and tiling strategy. There are four tiling strategies: random (reduces seams by randomizing tile positions but has overhead), random strict (avoids cropping border tiles with masking), padded (gives tiles more context via padding, compatible with uni - samplers), and simple (divides image into a static grid). The roadmap includes features like latent masks, control nets, and adaptors, with tile - wide control nets and adaptors still to be implemented.

ComfyUI Noise provides 6 nodes for ComfyUI, offering more control and flexibility over noise. It includes nodes for generating noise, duplicating batch samples, mixing latents, calculating noise strength, injecting noise, and reversing sampling. For example, it can generate variations of an image by slerping different noises, and find the noise for a given image using the unsampler. It also comes with example workflows to demonstrate usage.

These are custom nodes for ComfyUI. Clone the repository into `ComfyUI/custom_nodes`, with the final path being `ComfyUI/custom_nodes/stability-ComfyUI-nodes`. For standalone installations, run `standalone_install_requirements.bat`; for manual installations, use `pip install -r requirements.txt`. The nodes appear under "stability" in ComfyUI. The "ControlLoraSave" node creates a Control LoRA by analyzing the weight difference between a base model and a ControlNet and saves the differential data in LoRA format. Main features include maintained heading hierarchy, preserved links, kept technical terms for SEO, simplified phrasing, added clarifications, and unchanged installation commands.

This product offers a minimalistic implementation of Robust Video Matting (RVM) and BRAIAI - RVMBG v1.4 in ComfyUI. It provides an example workflow in JSON format and a corresponding visual illustration. There are also demonstration links for both RVM and Braiai on GitHub, which can help users quickly understand and use these video matting functions in ComfyUI, achieving efficient video matting effects.

The ComfyUI-Impact-Subpack Node Package is an extension for the ComfyUI Impact Pack, featuring the UltralyticsDetectorProvider. It has core nodes like UltralyticsDetectorProvider to generate detector outputs, manages models by type in specific directories sourced from multiple channels, allows path customization and has security protocols, can be installed via ComfyUI-Manager or manually, and credits ComfyUI and various model resources. Its main functions include enhancing ComfyUI Impact Pack functionality, providing detector outputs, managing models, and ensuring secure model loading with multiple installation options.

ComfyUI MotionDiff integrates 4DHuman, MotionGPT, MDM, MotionDiffuse and ReMoDiffuse into ComfyUI. It offers multiple installation methods. The product can perform 3D pose estimation from 4DHuman and generate and render motions. It outputs two types of stickmen: pseudo - openpose (faster but with limitations) and real openpose (better but needs gradient - based optimization). Key parameters like frames, smplifiy_iters, etc., can be adjusted. It also supports saving and loading SMPL data, with nodes for saving as.pt files, exporting meshes, and loading from the input folder.

These are experimental custom nodes for ComfyUI. Install by copying .py files to the custom_nodes folder, and they\'ll appear under custom_node_experiments/. Features include: sampler_tonemap.py with ModelSamplerTonemapNoiseTest for tonemapping noise during sampling to allow higher CFG values; sampler_rescalecfg.py implementing Rescale Classifier - Free Guidance; advanced_model_merging.py offering block - level model merging; sdxl_model_merging.py for SDXL base model merging; and reference_only.py with an implementation of "reference only controlnet" and sample workflows.

ComfyUI MagickWand integrates ImageMagick into ComfyUI using wandpy, supporting batch values. It offers 99 image - editing methods across 11 categories like Effect, Resize, Threshold, etc. Installation involves installing ImageMagick on different systems (Windows, Debian/Ubuntu, Fedora/CentOS, Mac) and the custom node suite via ComfyUI - Manager or command - line. Example workflows and input images are provided for testing.

Power Noise Suite is a plugin for ComfyUI, succeeding PPF_Noise_ComfyUI. It focuses on latent noise input, diffusion, and latent adjustments. Key updates include an overhauled Power - Law Noise system and a tonal guide image for the Power KSampler. It offers various nodes like Perlin Power Fractal Noise, Power Law Noise, etc., each with specific parameters to generate different noise patterns. The nodes support multiple resampling methods, and some allow for optional VAE encoding. It also provides blending and adjustment functions for latent images, and advanced sampling capabilities with limited sampler compatibility.

The text details the Stability API integration for ComfyUI, including ways to configure the API key (environment variable, text file, or direct input), offers complete integration with v2 endpoints, lists various function modules like image upscalers, erasers, and generators, and outlines the MIT software licensing terms allowing users to use the software package with certain rights and disclaimers. It provides a comprehensive solution for API integration with a wide range of image - related function modules under an MIT license.

This is a GitHub page for the ComfyUI_SeeCoder repository. It offers two experimental nodes for ComfyUI to use SeeCoders. Users can find SeeCoders on Hugging Face and place them in the 'models/seecoders' directory. The SEECoderImageEncode node can create embeddings from images, and the ConcatConditioning node can concatenate different embeddings. The repo is public, with 38 stars and 7 forks, and has 3 issues and 2 pull - requests.

## **ComfyUI_Preset_Merger**, a tool designed to merge checkpoint models using presets. It includes a single node named `ModelMergeByPreset`, which will be accessible within the `advanced/model_merging` section. ## Sine Examples **Note**: 

This is a ComfyUI node for integrating BLIP into CLIPTextEncode. It's now officially integrated. Dependencies include Fairscale, Transformers, Timm, and Gitpython, with Fairscale needing installation. Local installation involves running commands in specific directories, and Google Colab installation requires adding specific code cells. To use it, add the CLIPTextEncodeBLIP node, connect it to an image and set min_length and max_length. Optionally, embed BLIP text in a prompt using the keyword 'BLIP_TEXT'. Its implementation relies on resources from BLIP, ALBEF, Huggingface Transformers, and timm.

The ComfyUI Connection Helper Extension offers convenient tools to simplify node connections. When the mouse hovers over a node, connection assistance icons appear. Its features include the left - button automatically linking the nearest compatible output to the target node's inputs, the center - button duplicating input connections while preserving existing links for matching names, and the right - button fully cloning all input and output connections (requiring unconnected slots). It accelerates workflow creation, maintains connection accuracy, and uses an intuitive button system to ensure efficient node linking without disrupting configurations.

This repository provides two custom nodes for ComfyUI. The CLIPSeg node uses the CLIPSeg model to generate a binary mask and heatmap overlay for an input image based on a text prompt, with options to control blur, threshold, and dilation. The CombineSegMasks node combines two or three masks into one. Installation involves cloning the repo and placing a file in the custom_nodes directory. Usage examples are provided in a JSON file. Requirements include PyTorch, CLIPSeg, OpenCV, numpy, and matplotlib.

This product is a set of nodes for ComfyUI. It can generate Perlin power fractal noise and cross - hatch power fractal noise patterns, with adjustable parameters like batch size, width, height, resampling method, etc. It also provides a blending function for two latent tensors with multiple blending operations. Additionally, it can convert images to latent format. The parameters have specific value ranges, allowing users to customize details, complexity, intensity, contrast, etc. of the output.

The WAS Node Suite (Revised) is a comprehensive node collection for ComfyUI, featuring advanced image processing, text manipulation, and workflow enhancement tools. It offers a wide range of nodes including vision processing, image composition, workflow management, text processing, special effects, and media production, with features like BlenderNeko integration, dynamic prompting, and a token system for filenaming. Installation guides for different methods, configuration options, technical requirements, and community resources are also provided.

This is a fix for ComfyUI - nodes - hnmr by hnmr293. It offers multiple workflow examples like X/Y/Z - plot, merge, and latent visualization. The node list includes various types such as latent, sampling, model, image, and other utility nodes. Each node has defined input and output types, enabling functions like random latent image generation, VAE encoding/decoding, model merging, and image blending. It aims to provide a seamless experience for the community to use these tools without issues.