ComfyUI Custom Extensions
Browse 9,420 ComfyUI extensions and 73,215 custom nodes.
Guided prompt writing and reference media handling for the MiniMax H3 video model: fillable templates for every mode, live checking against MiniMax's prompt guide, and a drag-and-drop media loader that keeps reference tags straight.
Nodes such as CLIP Text Encode++ to achieve identical embeddings from stable-diffusion-webui for ComfyUI.
A ComfyUI custom node that integrates Google's Gemini Flash 2.0 Experimental model, enabling multimodal analysis of text, images, video frames, and audio directly within ComfyUI workflows.
Custom node to convert the lantents between SDXL and SD v1.5 directly without the VAE decoding/encoding step.
Warning, uses experimental package `comfy-env` to attempt a one click isolated install. Will download and use pixi package manager. Motion Capture nodes for ComfyUI: SMPL data/retargeting using GVHMR
ComfyUI node for VOSR 2.0 (one-step 1.4B) image super-resolution.
Long-form MiniMax H3 video/audio generation for ComfyUI with unified clip planning, continuity, lip-sync, and adaptive low-VRAM execution.
ComfyUI nodes for SCAIL input processing
This extension contains 6 nodes for ComfyUI that allows for more control and flexibility over the noise.
An extension for ComfyUI that allows hot reloading. Once installed, you can preview changes in real-time while developing custom nodes or installing plugins without restarting ComfyUI.
Long-form MiniMax H3 video generation for ComfyUI with AV latent continuation, reference conditioning, chunked sampling, and resume support.
Nodes: load Image with metadata, get config data, load image from base64 string, Load Loras From Prompt, Generate Latent Noise, Combine Two Latents Into Batch, General Purpose Controlnet Unit, ControlNet Script, Content Mask Latent, Auto-Photoshop-SD Seed, Expand and Blur the Mask
HeyGem AI avatar.
Precise resolution and aspect ratio control for ComfyUI
ComfyUI implemtation for NAG
NO8D custom nodes for LoRA stacking, prompt generation, image loading, generation and masking, style selection, image comparison and composition, and dataset saving in ComfyUI.
The project integrates the Retrieval Augmented Generation (RAG) tool [a/Llama-Index](https://www.llamaindex.ai/), [a/Microsoft's AutoGen](https://microsoft.github.io/autogen/), and [a/LlaVA-Next](https://github.com/LLaVA-VL/LLaVA-NeXT) with ComfyUI's adaptable node interface, enhancing the functionality and user experience of the platform.
A set of useful nodes for convenient use of ComfyUI, including: Seed randomization before the generation process starts, with saving of the last used values and the ability to automatically interrupt the current generation; A function to pause the generation process; Slider nodes for convenient control of input parameters; An alternative version of the standard Reroute node.
This project converts raster images into SVG format using the [a/VTracer](https://github.com/visioncortex/vtracer) library. It's a handy tool for designers and developers who need to work with vector graphics programmatically.
A ComfyUI custom node suite for Qwen3-TTS, supporting 1.7B and 0.6B models, Custom Voice, Voice Design, Voice Cloning and Fine-Tuning.
A multimodal MiniMax H3 prompt-writing extension for ComfyUI with local and API providers.
A ComfyUI plugin based on HY-Motion 1.0 for text-to-3D human motion generation.
Bilateral Reference Network achieves SOTA result in multi Salient Object Segmentation dataset, this repo pack BiRefNet as ComfyUI nodes, and make this SOTA model easier use for everyone.
This node speeds up Flux2, Chroma, Z-Image in ComfyUI by using INT8 quantization, delivering ~2x faster inference on my 3090, but it should work on any NVIDIA GPU with enough INT8 TOPS.
This node speeds up Flux2, Chroma, Z-Image Turbo, Qwen Image in ComfyUI by using INT8 quantization on RTX 20 and 30 series cards, delivering 1.5~2x faster inference in tests with an RTX3090.
ComfyUI custom nodes for Fish Audio S2-Pro TTS | voice clone, multi-speaker, and text-to-speech
ComfyUI Version of '[a/Visual Style Prompting with Swapping Self-Attention](https://github.com/naver-ai/Visual-Style-Prompting)'
A suite of tools for prompt management. Combining nodes helps the user sequence strings for prompts, also creating logical groupings if necessary. Individual nodes can be chained together in any order.
An implementation of the RAG LlamaIndex with Agents from AutoGen
This is a ComfyUI plugin that makes it easier to call and run workflows from RunningHub in your local ComfyUI setup.
Implementation of the [a/StyleAligned](https://style-aligned-gen.github.io/) paper for ComfyUI. This node allows you to apply a consistent style to all images in a batch; by default it will use the first image in the batch as the style reference, forcing all other images to be consistent with it.
A ComfyUI node set and frontend extension for interactive 360 panorama workflows.
Redux StyleModelApply adds more controls
ComfyUI custom node implementation of OmniGen
A timeline for MiniMax H3 video: generate a clip, then extend it, prepend to it or bridge between clips seamlessly from their saved latents. The Timeline node is a mini video editor to arrange, cut and preview them, make seamless loops, and upscale the whole sequence in one pass. Companion to comfyui-obvpm.
ComfyUI MuseTalk
StyleModelApply adds more controls
a comfyui custom node for [a/hallo](https://github.com/fudan-generative-vision/hallo)
Official ComfyUI Support - InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
A powerful node alignment and color management plugin for ComfyUI, designed to enhance your workflow efficiency
Image and matte filtering nodes for ComfyUI `image/filters/*`
a comfyui custom node for [a/CosyVoice](https://github.com/FunAudioLLM/CosyVoice)
Allor is a plugin for ComfyUI with an emphasis on transparency and performance.
Node for generating almost seamless textures, based on similar setting from A1111.
Sync with version of BiRefNet. NODES:AutoDownloadBiRefNetModel, LoadRembgByBiRefNetModel, RembgByBiRefNet.
ComfyUI nodes to edit videos using Genmo Mochi
Perturbed-Attention Guidance (PAG), Smoothed Energy Guidance (SEG), Sliding Window Guidance (SWG), PLADIS, Normalized Attention Guidance (NAG), Token Perturbation Guidance (TPG) for ComfyUI and SD reForge.
PhotoMaker for ComfyUI
ComfyUI reference implementation for [a/PhotoMaker](https://github.com/TencentARC/PhotoMaker) models. NOTE: PhotoMaker V2 is supported.
Custom nodes use topazvideoai in comfyui.
Easy prompting for generation of endless random art pieces and photographs!
Fixed AttentionCouple, NegPip(negative weights in prompts) for SDXL and FLUX, more CFG++ and SMEA DY samplers, etc.
A ComfyUI custom node package for segment anything 3
Offering a series of utility nodes designed to simplify workflows and enhance efficiency
Transcribe audio and add subtitles to videos using Whisper in ComfyUI
A ComfyUI custom node for zero-shot text-to-speech synthesis system.
gguf node for comfyui
This is a plugin for displaying documentation for each comfyui node.
DiffuEraser is a diffusion model for video Inpainting, you can use it in ComfyUI
Text to speech with F5-TTS
This is a custom node that lets you take advantage of Latent Diffusion Super Resolution (LDSR) models inside ComfyUI.
Nodes:NNLatentUpscale, A custom ComfyUI node designed for rapid latent upscaling using a compact neural network, eliminating the need for VAE-based decoding and encoding.
Nodes: StableAudioSampler. Wraps the new Stable Audio Open Model in the sampler that dropped Jun 5th. See Github for Features
official implementation of [zehong-ma/MagCache](https://github.com/zehong-ma/MagCache) for ComfyUI
ComfyUI-Minimax-H3-Promptor custom node for ComfyUI provides automation suite for generating MiniMax H3 prompts.
This project provides an unofficial ComfyUI implementation of [a/FLOAT](https://github.com/deepbrainai-research/float) for Generative Motion Latent Flow Matching for Audio-driven Talking Portrait
The aim of these custom nodes is to get an easy access to the tags used to trigger a lora / lycoris. Extract the tags from civitai or from the safetensors metadatas when available.
A ComfyUI custom node package for streamlined media loading and video pipeline assembly. Provides intuitive nodes that simplify media resource loading with user-friendly parameters, making it easier to build and configure video processing workflows.
Krea2 Turbo Enhancement Nodes
We provide ComfyUI-ResAdapter node to help users to use [a/ResAdapter](https://github.com/bytedance/res-adapter) in ComfyUI.
Native-style ComfyUI nodes for Krea2 Control LoRA inference. The plugin keeps ComfyUI's built-in Krea2 inference path intact, uses the expanded input projection from the LoRA checkpoint during sampling, and injects a VAE-encoded control latent.
Include nodes for sam + bpy operation, that allows workflow creations for generative 2d character rig.
This is an implementation of [a/MiniCPM-V-2_6-int4](https://github.com/OpenBMB/MiniCPM-V) by [a/ComfyUI](https://github.com/comfyanonymous/ComfyUI), including support for text-based queries, video queries, single-image queries, and multi-image queries to generate captions or responses.
This is an implementation of [MiniCPM-V-4_5](https://github.com/OpenBMB/MiniCPM-V) by [ComfyUI](https://github.com/comfyanonymous/ComfyUI), including support for text-based queries, video queries, single-image queries, and multi-image queries to generate captions or responses.
Video masking tools for ComfyUI: jitter-free subject-tracked crop and uncrop with feathered mask-confined pasting, video mask cleanup, and pixel-to-latent mask reduction aligned to causal video VAE frame grouping.
A collection of utility nodes for advanced image editing in ComfyUI, supporting multiple AI models including Qwen, Qwen-Image 2.1, Flux2Klein, Flux3Klein and Krea2.
Upscale long, high-resolution MiniMax H3 video on a VRAM-limited GPU in a single node.
This project adapts the SAM2 to incorporate functionalities from [a/comfyui_segment_anything](https://github.com/storyicon/comfyui_segment_anything). Many thanks to continue-revolution for their foundational work.
Implementation of [a/faceswap](https://github.com/nosiu/InstantID-faceswap/tree/main) based on [a/InstantID](https://github.com/InstantID/InstantID) for ComfyUI.
请安装新版ComfyUI-Global-Translation,感谢支持!
A comprehensive, smart and compatible multi-language translation solution for the ComfyUI interface. Frontend and backend cooperate to translate nodes, menus, the settings panel, ComfyUI Manager and workflow templates in real time, while staying fully compatible with ComfyUI's official native translation instead of overriding it. The target language automatically follows ComfyUI's official locale setting (Settings → Extensions → Comfy.Locale), so nothing is forced on users who keep the official language; 15 language packs are bundled, including the RTL languages Arabic, Persian and Hebrew. Translation can be switched on/off live without restarting ComfyUI, and a built-in manager lets you disable translation for individual plugins.
Implementation of DepthCrafter nodes for ComfyUI, create consistent depth maps for your videos.
This project is an unofficial ComfyUI implementation of [a/InvSR](https://github.com/zsyOAOA/InvSR) (Arbitrary-steps Image Super-resolution via Diffusion Inversion)
A clean, efficient ComfyUI custom node pack for Qwen3-TTS. It provides CustomVoice, VoiceDesign, and VoiceClone workflows with strict ComfyUI compatibility and practical controls for quality, speed, and stability.
A collection of post processing nodes for ComfyUI, which enable a variety of visually striking image effects.
HDR, ACES and 32-bit float VFX nodes for ComfyUI: learned SDR to HDR, HDR VAE encode and decode, OCIO colour management, EXR I/O, a pro Viewer, and Nuke / Resolve handoff.
Mel-Band RoFormer for Music Source Separation
This custom node implements a Latent Consistency Model sampler in ComfyUI. (LCM)
ComfyUI custom nodes for inpainting/outpainting using the new latent consistency model (LCM)
a comfyui custom node for [a/GPT-SoVITS](https://github.com/RVC-Boss/GPT-SoVITS)! you can voice cloning and tts in comfyui now [w/NOTE:make sure ffmpeg is worked in your commandline]
ComfyUI custom nodes for inpainting/outpainting using the new latent consistency model (LCM)
A port of the openpose-editor extension for stable-diffusion-webui. NOTE: Requires [a/this ComfyUI patch](https://github.com/comfyanonymous/ComfyUI/pull/711) to work correctly
WeiLin-ComfyUI-Prompt-all-in-one Write prompt words like WebUI
A danbooru gallery for ComfyUI
ComfyUI wrapper nodes for [a/Latent Bridge Matching (LBM)](https://github.com/gojasper/LBM)
Running ONNX/TRT version of the MiniMax-H3 VAE in ComfyUI, which can increase speed by up to 1.7x
MatlowAI's MiniMax-H3 nodes: Dials (training-free steering sliders, rack, time curves), Contact-Sheet diffusion, and Motion Lab (test-time de-roping of fast motion via oracle-guided v2v time-smear)
ACE-Step: A Step Towards Music Generation Foundation Model