ComfyUI Custom Extensions

A custom node for ComfyUI that enables smooth, keyframe-based animations for image generation. Create dynamic sequences with control over motion, zoom, rotation, and easing effects. Ideal for AI-assisted animation and video content creation.

A custom node for ComfyUI that integrates DeepSeek's powerful chat and instruction API, enabling seamless AI interactions within your ComfyUI workflows.

The ComfyUI_pixtral_vision is a powerful ComfyUI node designed to integrate seamlessly with the Mistral Pixtral API. It facilitates the analysis of images through deep learning models, interpreting and describing the visual content. Users can input an image directly and provide prompts for context, utilizing an API key for authentication.

A collection of nodes and improvements created for general ease and lora management. These are just nodes I made and found useful, they should work with most other nodes. Most nodes that take in a prompt are made with booru tags in mind and might not work as expected with other prompts.

NVIDIA PiD (Pixel Diffusion Decoder) as a drop-in replacement for VAE Decode on Anima / Qwen-Image latents.

Quantization-aware native FP16 loader and exact-math overflow fix for ComfyUI MiniMax H3 on pre-BF16 GPUs.

Phi-3.5-vision-instruct fast talk with image ! Fast , Fast ,Fast! 1.Phi-3.5-vision-instruct

NODES:CXH_Gemini2_TX, CXH_Gemini2_Vision, CXH_Local_Prompt

ToriiGate-0.5 image captioning nodes with local GGUF support for ComfyUI.

NODES:StoryMakerSinglePortraitNode, StoryMakerTwoPortraitNode, StoryMakerSwapClothNode.

This project implements a set of custom nodes for ComfyUI, integrating some of the API interfaces provided by [a/TAMS](https://tams.tensor.art/).

Wrapper for EvTexture Video Upscaler: [a/https://github.com/DachunKai/EvTexture](https://github.com/DachunKai/EvTexture)

LockPixel is a ComfyUI custom node pack for Qwen-Image-Edit workflows where pixel drift, small shifts, or subtle zoom-like deformation must be avoided.

It allows you to control complex graphs by unbypass/unmute and bypass/mute entire groups of nodes, just by adding tags in the title of your nodes, no connection required.

Fix banding artifacts by re-sampling the latent with a low denoise strength.

A slightly different Resolution Selector node, allowing to freely change base resolution and aspect ratio, with options to maintain the pixel count or use the base resolution as the highest or lowest dimension.

This extension provides two nodes to use with my experimental [a/ip-adapter finetune](https://civitai.com/models/1233692?modelVersionId=1390253) for NoobAI-XL style transfer. [a/Here](https://github.com/vahlok-alunmid/reForge-preprocessor_bigG_448) is the counterpart extension for Reforge WebUI.

A toolset for Hunyuan Video (mainly), with some additional nodes applicable to Framepack Video and WAN Video

Kandinsky 5 DiT. High-quality T2V with advanced text conditioning.

A collection of utility nodes primarily for interacting with comfy via automated systems

Nodes:Combine HDMasks, Cover HDMasks, HD FaceIndex, HD SmoothEdge, HD GetMaskArea, HD Image Levels, HD Ultimate SD Upscale

Compatible with alimama's SD3-ControlNet Demo on ComfyUI.

Custom nodes for ComfyUI by Comflowy.

Nodes:abyz22_Padding Image, abyz22_ImpactWildcardEncode, abyz22_setimageinfo, abyz22_SaveImage, abyz22_ImpactWildcardEncode_GetPrompt, abyz22_SetQueue, abyz22_drawmask, abyz22_FirstNonNull, abyz22_blendimages, abyz22_blend_onecolor. Please check workflow in [a/https://github.com/abyz22/image_control](https://github.com/abyz22/image_control)

a custom node for [a/DiffMorpher](https://github.com/Kevin-thu/DiffMorpher),you can find base workflow in [a/doc](https://github.com/AIFSH/DiffMorpher-ComfyUI/blob/main/doc)

Huggingface Api Serverless request

Nodes:Asymmetric_Tiling_KSampler.

Prompt-only Krea moodboard search and style nodes for ComfyUI.

Manual tapered context noising for MiniMax H3 Motion Context (character-swap continuation)

Manual tapered context noising for MiniMax H3 Motion Context (character-swap continuation)

Simple node for setting the sigma values directly. Note, for a full denoise the last sigma should be zero.

Generate high-fidelity, synchronized foley audio for any video directly within ComfyUI, powered by Tencent's HunyuanVideo-Foley model.

Scaled Uniform Noise for Ancestral and Stochastic samplers

ComfyUI workflow preset switching plugin allowing quick toggle of multiple presets in a single workflow via index value. (Description by CC)

ComfyUI workflow preset switching plugin that allows quick toggling between multiple presets in a single workflow using an index value.

ComfyUI 3d engine

Investigating the Effectiveness of Cross Attention to Unlock Zero-Shot Editing of Text-to-Video Diffusion Models

Unofficial implementation of [a/deepseek-ai/Janus](https://github.com/deepseek-ai/Janus) in ComfyUI.

Generate audio-reactive SCAIL pose sequences for character animation without requiring input video tracking. Now supports Multi-Character Choreography. (Description by CC)

Improved Pose & Face Detection for Wan Video 2.2 Animate based on GitHub Issue #1410 (WanVideoPreProcessor) and #10 (WanAnimatePreProcessor). (Special thanks: @kijai and @steven850)

This extension integrates ebsynth_utility into comfyui, and I've written some of my own nodes for secondary use.

This node allows the execution of Node.js application within ComfyUI by leveraging the ComfyUI-NODEJS, which starts alongside ComfyUI and facilitates the installation of Node.js. The integration enables Python subprocesses to execute Node.js scripts.

Alt+H spotlight for ComfyUI: hide or dim every link that doesn't touch the selected node. Frontend-only, zero nodes, zero dependencies.

An extended Load Image node with an aspect-ratio-locked, WYSIWYG crop rectangle that outputs the cropped IMAGE and MASK.

Simple wan-video wrapper.

This is a node to detect the similarity between two faces

Nodes:Neural Neighbor, CAST, EFDM, MicroAST, Coral Color Transfer.

A custom node designed for ComfyUI that can load multiple artist names simultaneously and intelligently combine them into the prompt, with support for independent weight control and real-time preview.

ComfyUI nodes for StableAnimator

Parler TTS is a zeroshot voice synthesis with emotion and entonations, you can control the voice style via text prompt

Nodes: P2LDGAN. This integrates P2LDGAN into ComfyUI. P2LDGAN extracts lineart from input images. [w/To use this extension, you need to download the [a/p2ldgan model](https://drive.google.com/file/d/1To4V_Btc3QhCLBWZ0PdSNgC1cbm3isHP) and save it in the %%ComfyUI/custom_nodes/comfyui-p2ldgan/checkpoints%% directory.]

A multimodal API workflow toolkit for ComfyUI with image, video, audio, text, batch generation, asset cards, and an integrated chat assistant.

This repo is a simple implementation of [a/Paint-by-Example](https://github.com/Fantasy-Studio/Paint-by-Example) based on its [a/huggingface pipeline](https://huggingface.co/Fantasy-Studio/Paint-by-Example).

Workflow management and generation UI plugin. Browse, organize, and execute workflows with auto-generated parameter editing, AI prompt assistant (Ollama), JSON syntax highlighting, Eagle integration, and multi-language support (EN/JA/ZH).

A new ComfyUI node for integrating Topaz Photo AI's powerful image enhancement capabilities.

Merge up to 4 LoRA models with balanced, order-independent logic. Inspired by WebUI SuperMerger.

NODES: Webpage Screenshot, Camera Watermark, Template To Image

NODES: Save Weight As Kolors Unet, Save Kolors

This ComfyUI custom node, named ControlNet Auxiliar, is designed to provide auxiliary functionalities for image processing tasks. It is particularly useful for various image manipulation and enhancement operations. The node is integrated with functionalities for converting images between different formats and applying various image processing techniques.

A wild collection of custom nodes for ComfyUI including noise schedulers, samplers, audio preview, latent visualizers, and more — built for maximal creative chaos.

A collection of utility nodes for ComfyUI that enhance workflow efficiency and flexibility.

Front end ComfyUI nodes for CartoonSegmentation Based upon the work of the CartoonSegmentation repository this project will provide a front end to some of the features.

Performs various processing on images containing NSFW content within ComfyUI. The model used for detecting NSFW content can be selected.

Non-destructive visual image composition helper tool node for ComfyUI with minimal requirements, works with larger images too.

'Real-time golden ratio pattern composition evaluation tool node for ComfyUI. This does nothing else - but you can move, rotate and scale then pattern to find new things and structures in your images.

This repository contains custom nodes for ComfyUI created and used by Mario Klingemann (@Quasimondo on Twitter and Instagram)

NRS seeks to replace the 'naive' linear interpolation of Classifier Free Guidance with a more nuanced and composable steering of the generation process with better mathematical basis.

Makes the prompts for generating anime images more detailed by upsampling Danbooru tags.

Rui's workflow-specific custom node, written using GPT.

Advanced merging methods.

set denoise strength for keyframe

A prompt generator and CLIP encoder using AI provided by Ollama.

Virtual try-on for creating a personal brand wardrobe collection.

A custom node for ComfyUI that enables coherent video generation while maintaining efficient memory usage, specifically optimized for heavy models like Flux.

You can make emoji from a video and a image in comfyui

Timeline video editor for ComfyUI in a single node. Arrange video, images, and audio on tracks, set first and last frames, schedule prompts over time, transfer motion from a pose video, and regenerate any section in place. Work is organized into projects, and every result lands in a searchable asset gallery.

Experimental native Qwen-Image-2.1 block cache, spectral forecasting, and attention adapters.

Nodes: Fans Styler (Max 10 Style), Fans Text Concat (Until 10 text), Fans Prompt Styler Postive (Can replace {prompt} word in your csv files), Fans Prompt Styler Negative (With sentence structure).

A node which takes in x, y, width, height, total width, and total height, in order to accurately represent the area of an image which is covered by area-based conditioning.

A collection of advanced edge detection nodes for ComfyUI that generate high-quality edge maps / contours for usage with ControlNet Canny / Anyline guidance.

I'm SD-VJ. (share SD-generating-process in realtime by gpu)

A ComfyUI custom node pack implementing Diff-Aid-inspired inference-time text-conditioning patches for Flux and SDXL models.

VDN-H3-Plus hybrid attention for ComfyUI MiniMax-H3 with pre-quantized or self-built INT8 ConvRot VDN stages

YinChao Music provides ComfyUI V3 nodes for lyric generation, prompt-to-song generation, reference-based generation, and song extension via the YinChao API. Results are decoded to native AUDIO for direct use in audio, video, and subtitle workflows.

Native ComfyUI nodes for EverAnimate-style chunked WanAnimate workflows, including master/chunk settings, chunk calculation, image carry-over, and boundary color correction.

ComfyUI-Direct3D‑S2 is now available in ComfyUI, Direct3D‑S2 - Gigascale 3D Generation Made Easy with Spatial Sparse Attention. Direct3D‑S2 is a scalable 3D generation framework based on sparse volumes that achieves superior output quality with dramatically reduced training costs.

A powerful OCR node for ComfyUI that integrates the DeepSeek-OCR model from Hugging Face.

Autocomplete and Related Tag display for ComfyUI

Intelligent FFMPEG agent node for ComfyUI with natural language video editing

Exact activation-only multi-GPU attention head sharding for MiniMax H3 in ComfyUI.

a comfyui custom node for [a/3d-photo-inpainting](https://github.com/vt-vl-lab/3d-photo-inpainting),then you can render one image to zoom-in/dolly zoom/swing motion/circle motion video

a custom node for SenseVoice

这是一个多功能节点，主要功能有Qwen提示词，显存控制，批量流程节点，This is a multifunctional node, with main functions including Qwen prompt words, video memory control, and batch process nodes

A ComfyUI custom node for llama-swap the hot-swap model manager for llama.cpp.

Custom javascript extensions for better UX for ComfyUI. Supported nodes: PreviewImage, SaveImage. Double click on image to open.

A custom node for ComfyUI that provides the ability to clear the cache directly from your workflow.

Custom nodes for performing basic math operations

Intel XPU dynamic model unloader for ComfyUI, reimplements NVIDIA CUDA VRAM management for Arc B series GPUs. (Description by CC)