ComfyUI Custom Extensions

This is a PuLID node that has been extended with new features.

An all-in-one node for ComfyUI that implements AceStep 1.5 SFT (Supervised Fine-Tuning), a high-quality music generation model. This node replicates the full functionality of the official Gradio pipeline, offering fine control over audio synthesis parameters.

Original repo: [a/https://github.com/luckyhzt/LVCD](https://github.com/luckyhzt/LVCD)

'🔢 Prompt Combinator' is a node that generates all possible combinations of prompts from several lists of strings. '🔢 Prompt Combinator Merger' is a node that enables merging the output of two different '🔢 Prompt Combinator' nodes.

Add an image reference feature to the Cosmos model or models based on it, such as the Anima model

Side by Side Stereoscope node for ComfyUI by SamSeen

I wanted a node to save my prompts and optionally take in an external prompt from a llm and save it, didn't see one, so I made it.

A set of custom nodes for ComfyUI that leverage the Gemini 2.5 Flash Image Preview API to generate images from text prompts, single images, and multiple images.

KV-Edit: Training-Free Image Editing for Precise Background Preservation,you can use it in comfyUI

A comprehensive collection of ComfyUI custom nodes that replicate the functionality of popular Nuke compositing nodes. Includes merge, grade, transform, blur nodes and more for professional compositing workflows.

Wrapper ComfyUI integration for the [a/Flux Omini Kontext](https://github.com/Saquib764/omini-kontext) pipeline, enabling seamless character/object insertion into scenes using FLUX.1-Kontext-dev with LoRA adaptation.

Tile-based refinement nodes for ComfyUI, built around the Hildegard-Refiner reference-latent scheme. Designed for FLUX.2 Klein.

The ComfyUI-fal-Connector is a tool designed to provide an integration between ComfyUI and fal. This extension allows users to execute their ComfyUI workflows directly on [a/fal.ai](https://fal.ai/). This enables users to leverage the computational power and resources provided by fal.ai for running their ComfyUI workflows.

implementation of [a/AniPortrait](https://github.com/Zejun-Yang/AniPortrait) generating of videos, includes self driven, face reenacment and audio driven with a reference image

Direct MiniMax H3 on a timeline instead of cramming everything into one prompt box. Lay shots, camera moves and audio cues out on tracks, give every person, prop, place and look a card holding its reference picture, its description and its voice, and the node compiles the whole piece into the single structured prompt H3 actually reads -- the six-section reference format, task types, dialogue in the model's exact <d> form, frame anchors and on-screen text -- then hands the sampler its conditioning and a clip length it will accept. Ships as a complete workflow with a live compiled-prompt view and a linter.

This node uses YOLO model to obtain bboxes required by ComfyUI's official SDPose node for multi-person processing. (Description by CC)

This node allows using Hugginface remote server for latent decoding. Currently supported models: SD, SDXL, Flux, HunyuanVideo

Nodes:TileSplit, TileMerge.

These custom nodes provides a feature to insert arbitrary inputs through wildcards in the prompt. Additionally, this tool provides features that help simplify workflows, such as VAELoaderDecoder and SimplerSample.

ComfyUI extension to organize nodes

This project is the ComfyUI implementation of the TaylorSeer project [a/https://github.com/Shenyi-Z/TaylorSeer](https://github.com/Shenyi-Z/TaylorSeer).

A collection of AI-powered photography and image generation tools for ComfyUI, featuring the SID_AIPromptGenerator node that uses Anthropic's Claude API to analyze images and generate optimized prompts for various image generation models.

ComfyUI_MangaNinjia is a ComfyUI node of MangaNinja which is a Line Art Colorization with Precise Reference Following method.

This custom node is designed to provide graphical documentation for ComfyUI custom nodes.

ComfyUI toolkit with custom nodes for BBox canvas visualization, image brush mask drawing, and coordinate annotation for debugging and external data bridging. (Description by CC)

A ComfyUI plugin based on SkinTokens (Newer Auto-Rig) from VAST-AI-Research

Nodes: LoadImageFromPath. Load Image From Path loads the image from the source path and does not have such problems.

SIFT-based image alignment, intelligent mask cropping and restoration for ComfyUI

Visualize your textures inside ComfyUI

ComfyUI extension for video-based prompting and processing with support for various models and video processing capabilities

Moondream's gaze detection feature wrapper node.

Cosmos-style rectified-flow sampler nodes for Anima models in ComfyUI.

A minimalist node that calls LLMs, combined with one API, can call all language models, including local models.

The node has been created through vibe coding. The main objective is for identity consistency for FLUX.2 klein 9b models in ComfyUI.

ComfyUI-LightVAE is a collection of LightX2V VAE custom nodes designed for ComfyUI, supporting high-performance video VAE models including LightVAE and LightTAE.

A ComfyUI custom node for Black Forest Labs' FLUX 1.1 [pro] API, supporting both regular and Ultra modes with optional Raw mode.

After Effects-style animation nodes for ComfyUI with timeline-based keyframe control, layer management, and real-time preview rendering. (Description by CC)

IP-Adapter custom node for Anima in ComfyUI that injects reference image features via decoupled cross-attention for character-consistent generation.

ComfyUI Instaswap Node

a custom node for [a/echomimic_v2](https://github.com/antgroup/echomimic_v2)

ComfyUI nodes for MiniMax H3 loading, directing, prompting, acceleration, RTX and video workflows

Nodes: LamaaModelLoad, LamaApply, YamlConfigLoader. a costumer node is realized to remove anything/inpainting anything from a picture by mask inpainting.[w/WARN:This extension includes the entire model, which can result in a very long initial installation time, and there may be some compatibility issues with older dependencies and ComfyUI.]

just 5G VRAM, you can infer 5 min long video,Pushing the Frontier of Long Video Generation Standalone

you can make story in comfyUI using MS-diffusion

An in-app, drag-and-drop dictionary for ComfyUI, designed specifically for absolute beginners and non-coders.

This repository contains custom nodes for ComfyUI that integrate the fal.ai FLUX.1 [dev] with LoRA API, specifically for text-to-image generation. These nodes allow you to use the FLUX.1 model directly within your ComfyUI workflows.

ComfyUI-AniSora is now available in ComfyUI, Index-AniSora is the most powerful open-source animated video generation model. It enables one-click creation of video shots across diverse anime styles including series episodes, Chinese original animations, manga adaptations, VTuber content, anime PVs, mad-style parodies, and more!

DeepExtractV2 – lightning-fast, high-quality audio separator. Instantly isolate vocals, drums, bass, and more from any track. Ideal for creators, DJs, and audio pros.

A new ComfyUI node for OpenAI's ChatGPT API has been added. It currently supports single and multiple image inputs, text input, image generation, and image editing.

Prompt Generator for Video, Audio, Image, and Text. A node for ComfyUI. Including Deepseek, Alibaba Cloud Qwen, Google Gemini, and locally selected models, etc.

ComfyUI-EasyAnimate

A copy of ComfyUI_IPAdapter_plus, Only changed node name to coexist with ComfyUI_IPAdapter_plus v1 version.

Custom node packs for ComfyUI: FolderIncrementer (auto-versioning) + MaskEditControl (pinpoint mask editing with SAM 2.1 / SAM 3, per-axis erode/expand, point editor, bbox tools, video mask propagation).

Google Gemini API integration for ComfyUI - Generate images and text using Google's latest AI models. Provides nodes for Gemini API interactions and batch image processing.

Data research, preparation, and manipulation nodes for model trainers and artists.

Manipulate the details of generations.

Decor8 AI Virtual Staging, Interior Design, and Design Inspirations (Requires API key from www.decor8.ai). Requires a valid pay-as-you go subscription plan or credits bundle. Reach out to [email protected] if you have any questions or need test credits.

ComfyUI Custom Nodes for 'AniDoc: Animation Creation Made Easier'. This approach automates line art video colorization using a novel model that aligns color information from references, ensures temporal consistency, and reduces manual effort in animation production.

Nodes: Range(Step), Range(Num Steps), List Length, Image Overlay, Stack Images, Empty Images, Join Image Lists, Join Float Lists. This extension provides various list manipulation nodes

Fork of the official DF11 ComfyUI custom node that supports a wider variety of model architectures, and provides fixes for compatibility with recent ComfyUI versions. Also, LoRAs are supported for select model architectures.

ComfyUI V3 nodes for the official IndexTTS 2.5 model, by T8star-Aix

A custom node toolkit for ComfyUI covering video generation, pose processing, interactive image operations and common workflow needs.

Safe & consistent QwenImage edit encoders and HQ VAE decode for ComfyUI.

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.

A powerful and feature-rich custom node collection for ComfyUI that integrates the Kokoro TTS (Text-to-Speech) system with advanced voice modification capabilities. This package allows you to generate natural-sounding speech and apply various voice effects within ComfyUI workflows.

This is a UNO ComfyUI plugin implementation that can run the full version with 24GB VRAM, as well as quickly run the FP8 version.

ComfyUI custom nodes for Diffusion Attentive Attribution Maps (DAAM)

Expansion of Efficiency Nodes for ComfyUI. Significant UX improvements.[w/NOTE: This node requires [a/efficiency-nodes-comfyui](https://github.com/jags111/efficiency-nodes-comfyui) and [a/ComfyUI-Custom-Scripts](https://github.com/pythongosssss/ComfyUI-Custom-Scripts); it also requires start.bat to run.]

ComfyUI node pack for HyperFlow [Video Rebirth's] 8-step LoRA for MiniMax-H3 (video + audio), ported onto ComfyUI's native MiniMax-H3 model. No ComfyUI core files are modified; no custom sampler is needed.

Adds a global /workflow/convert API endpoint to convert non-API workflow formats to API format for ComfyUI execution

[DEPRECATED] Extended quantization layouts for ComfyUI (INT8, row/block-wise FP8)

ComfyUI node collection: icon layout & processing, YOLO intelligent cropping, image filters & enhancement, text processing tools, metadata management, mask handling and image classification in one comprehensive toolbox.

This is a custom node for ComfyUI. It reduces colors based on a specified number and allows for adjustments to hue, saturation, and brightness. Features:Each parameter can be set to random, You can toggle masking (not changing colors) using color numbers, Mask inversion can also be toggled on or off.

Stable Diffusion WebUI & ComfyUI extension to post-process the prompt, including sending content from the prompt to the negative prompt and wildcards.

The unofficial implementation of CogView4 project in ComfyUI.

MiniMax H3 generation for ComfyUI with an embedded 9-image, 3-video, and 3-audio reference gallery.

A custom node for ComfyUI that integrates USO (Unified Style and Subject-Driven Generation) for high-quality image generation with style and subject control.

Nodes that allow making the UI interactive, with selectors and switches, etc.. Enables selecting across multiple options with the click of a button to move a workflow forward.

This is a helper extension for ComfyUI that assists with node connections.

A collection of custom nodes for ComfyUI by Mickmumpitz.

集成 Google Gemma 4 与阿里 Qwen 3.5 最新模型，为 ComfyUI 提供原生 LLM 调用能力，支持文本生成、图像理解及多模态工作流编排。

This node is primarily based on Easy-OCR to implement OCR text recognition functionality.

A booru API powered prompt generator for A1111 and ComfyUI with flexible tag filtering system and customizable prompt templates.

This is a straight clone of Azazeal04's all-in-one styler menu, which was removed from gh on Jan 21, 2024. I have made no changes to the files at all.

a custom comfyui node for [a/fish-speech](https://github.com/fishaudio/fish-speech.git)

This ComfyUI extension provides custom nodes for integrating with LM Studio, allowing for loading, managing, and making requests of LLM models through the LMStudio local server and command-line interface.

This ComfyUI node library builds upon the work done to train the [a/Arc2Face](https://github.com/foivospar/Arc2Face) model by foivospar. It provides a set of nodes for ComfyUI that allow users to extract face embeddings, generate images based on these embeddings, and perform image-to-image transformations.

With this quality of life extension, you can save your workflow with a specific name and include additional details such as the author, a description, and the version (in metadata/json). Important: When you share your workflow (via png/json), others will be able to see your information!

ComfyUI custom nodes for AI video/image generation via API relay stations (supports Grok, Veo, Gemini)

Removes the ComfyUI proxy middleman entirely, allowing direct API calls to vendors with your own keys, rates, and data privacy.

These nodes provide a wrapper for calling Draw Things image generations from ComfyUI. Wait, why? The Draw Things app has been optimized for Apple hardware and runs roughly x3 faster than ComfyUI generations. But ComfyUI is a flexible and powerful tools, and has some features - like queuing and face swapping - that haven't been implemented in Draw Things.

NODES:(Down)load MoGe Model, MoGe Process

A powerful audio generation extension for ComfyUI that integrates AudioX models for high-quality audio synthesis from text and video inputs.

A node that aggregates many powerful API features,Easier integration into workflows

Visual effects for ComfyUI links (wires) with various animation styles (Neon, Matrix, Fire) and gravity physics rope simulation. (Description by CC)

This project provides a Tensorrt implementation of Dwpose for ultra fast pose estimation inside ComfyUI

This project is an unofficial ComfyUI implementation of [a/Video Depth Anything](https://github.com/DepthAnything/Video-Depth-Anything), for depth estimation on long videos without compromising quality, consistency, or generalization ability.

a custom node for [a/RealisDance](https://github.com/damo-cv/RealisDance)

A simple and efficient ComfyUI custom node that allows batch processing of multiple prompts in a single queue with automatic model loading optimization.