ComfyUI Custom Extensions
Browse 9,446 ComfyUI extensions and 73,215 custom nodes.
IndexTTS2 精确停顿控制([pause:N])ComfyUI 节点:停顿延长/缩短/插入,平均偏差 13ms,支持批量生成与试听验收。Precise pause control for IndexTTS2 — TTS ComfyUI nodes with waveform-domain pause editing, ±13ms accuracy.
Resolve the conflict issue between the original plugin and the new comfy environment, adapt Nunchaku and kontext, support Chinese and custom fonts, and quickly measure the best parameters after model fine-tuning without the need for complicated node connections.
ComfyUI prompt word template management plug-in. Instead of adding any nodes to the canvas, a "Prompt Word Assistant" button is provided in the operation bar to open a full-screen modal box to manage the prompt word template with variables. After filling in the variables, copy the merged results with one click.
Qwen-TTS nodes for ComfyUI
Smart, unified model loaders for ComfyUI that support both standard .safetensors and quantized .gguf formats — no switching nodes required. Includes flexible UNET and CLIP loaders that work across models like SDXL, SD3, Flux, and more.
A node layout helper extension for ComfyUI. Assists in arranging and aligning nodes on the canvas without modifying workflow files — all operations are frontend-only.
Interactive trajectory exploration for text2img generation. Intermediate results preview, branch selection, variation controls.
Provides a series of utility nodes designed for interacting with MinIO, including functionalities such as uploading and downloading files and folders, as well as creating buckets if they do not already exist.
SASolver for Comfyui. Adapted from [a/comfyanonymous/ComfyUI#4454](https://github.com/comfyanonymous/ComfyUI/pull/4454) and [a/https://github.com/Koishi-Star/Euler-Smea-Dyn-Sampler](https://github.com/Koishi-Star/Euler-Smea-Dyn-Sampler)
An image compare view node designed for precise comparison, featuring customisable background colour, with transparent/alpha images/transparency supported.
A simple node to save your history in html file. I saves the WorkFlow with all it's input values so you can duplicate it later.
Nodes that are very useful for iterative workflows
A small node suite for ComfyUI
Advanced multi-dimensional prompt variation system for ComfyUI with 240 pre-defined modifiers and 19 custom nodes. (Description by CC)
A collection of nodes for ComfyUI. ex:A node for batch managing int, float, and string parameters with presets
Transceiver is a python library that swiftly exchanges fundamental data structures, specifically numpy arrays, between processes, optimizing AI inference tasks that utilize ComfyUI.
A simple sidebar tweak to force fixe the ComfyUI menu to the top of the screen. Reaaally quick and dirty. May break with some ComfyUI setup.
Reusable tagged image and audio reference library for MiniMax H3 workflows in ComfyUI
General audio nodes. Mix, Bass/Treble, Concatenate, Pitch, Add/remove silence, Speed
This is a standalone node pack that provides powerful color correction methods for ComfyUI, extracted from the ComfyUI-DLoRAL project. It allows you to transfer the color profile from a source image or video to a target image or video. This is ideal for restoring the original color to AI-processed videos (like upscaling or frame interpolation) or for creative color grading.
125+ production-ready V3 custom nodes for ComfyUI covering file ops, S3 cloud storage, image/video/audio processing, model management (HuggingFace/Civitai/S3), OpenAI & Runpod integration, and workflow utilities.
Harronode is a custom node designed to build prompts easily for use with the Harrlogos SDXL LoRA. This Node simplifies the process of crafting prompts and makes all built in activation terms available at your fingertips.
A ComfyUI custom node that resizes images while maintaining aspect ratio.
ZenKit — a UX framework for ComfyUI: panels, a theme token system and a cross-plugin event bus, exposed as window.ZenKit, with a Media Viewer, Asset Browser and Timer built in.
A compact, real-time histogram analysis node for ComfyUI — with easy-to-use interactive UI, smooth rendering, and accurate pixel sampling. Built for compositing-style workflows and color diagnostics.
ComfyUI custom node: LoRA stack with auto trigger-word extraction, plus an Anima cross-generation remap node (28/40/52 layers)
ComfyUI node pack for encrypting and hiding text or images. Security: AES-256-GCM (authenticated) with scrypt key derivation. Steganography: LSB (PNG/TIFF) and DCT/JPEG (more robust to recompression).
Take full control of ComfyUI with a suite of advanced nodes built around the PyCode Max engine
A lightweight ComfyUI custom-node package for managing Model-Only LoRA stacks and combining LoRA trigger text with prompts.
Adds a menu button that switches between old and new style ComfyUI menus.
ComfyUI extension to add a settings button to the sidebar
ComfyUI wrapper nodes for OmniVoice multilingual zero-shot TTS.
Generate Orpheus TTS audio via LM Studio
Nodes:Batch Image Blend by Mask, Batch Enlarged Overlay, Batch Image Overlay, Remove Black Pixels to Transparent, Canny Shrink and Recenter, ...
Automatically organize ComfyUI image and video outputs by subject using local Ollama classification, with metadata preservation and full-library Auto-Sort recovery.
Remote workflow executor node - Execute workflows on remote ComfyUI servers. Supports image/text/audio/video input and output.
FRED's enhanced custom nodes for ComfyUI
Multi-channel image handling for ComfyUI. Work with images that have arbitrary number of channels (segmentation masks, feature maps, spectral bands, etc.).
PainterImageFromBatch is an enhanced ComfyUI custom node for extracting contiguous frames from image batches.
ComfyUI node for saving, previewing, and passing images downstream while supporting mask editing and intermediate node execution. (Description by CC)
Automatically scales your input video to specified dimensions and encodes it into latent space for sampling.
A ComfyUI custom node for DreamOmni2 GGUF multimodal models — powered directly by llama-cpp-python.
A ComfyUI custom node for generating synchronized audio for videos using the HunyuanVideo-Foley model.
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.
A minimal dynamic prompting + mirrored wildcards node for ComfyUI.
A simple custom node that embeds the full ComfyUI-Lora-Manager web interface directly into your ComfyUI workflow graph. This eliminates the need to have a separate browser tab open for managing your LoRAs and recipes.
Embeds the ComfyUI-Lora-Manager web interface directly into your ComfyUI workflow graph, eliminating the need for a separate browser tab.
Nodes: TTS WebUI Kokoro, TTS WebUI Chatterbox, TTS WebUI StyleTTS2, TTS WebUI Kitten TTS, TTS WebUI F5-TTS, TTS WebUI Preset Add API key to environment variable 'TTS_WEBUI_OPENAI_API_KEY' Alternatively you can write your API key to file 'tts_api_key.txt' You can also use and/or override the above by entering your API key in the 'api_key' field of each node.
ComfyUI prompt, pipe and media tools redesigned from Eclipse with compact panels and a focus on canvas performance in classic canvas and Nodes 2.0.
ComfyUI_FlipStreamViewer is a tool that provides a customizable viewer interface for flipping images with frame interpolation.
ComfyUI Workflow to run audioldm-l-full pipeline [a/https://huggingface.co/cvssp/audioldm-l-full](https://huggingface.co/cvssp/audioldm-l-full)
quick Comfy Node to convert input waveform audio to MP3
A modular system that adds randomness to prompt generation
A ComfyUI custom node that filters LTX-2 LoRAs to strip out audio-weight interference, ensuring clean, high-fidelity sound while maintaining visual fine-tuning.
MiniMax H3 for ComfyUI: a 14 s 1088x1920 video with audio in 99.8 s on an RTX 4070 12GB (speed mode). The audio is generated first and locked, which also reduces the metallic voice of fast settings.
This project provides a set of custom timer nodes for ComfyUI. These nodes allow you to measure and append runtime information to strings or other data during your workflow.
ComfyUI custom node for experimental Anima/Cosmos flow-slider LoRA training.
Shuffle nodes after queue execution.
This node is load PNG image sequentially with metadata.
This node is load png image sequentially with metadata. Only supported for PNG format that has been created by ComfyUI.[w/renamed from comfyui-load-image-39. You need to remove previous one and reinstall to this.]
Shuffle nodes after queue added.
A custom node for ComfyUI that integrates with [a/Hedra](https://www.hedra.com/)'s Character-3 API to generate talking avatar videos from images and audio.
A powerful ComfyUI custom node for combining video clips with synchronized audio, background music, and advanced audio controls.
Custom node for ComfyUI that makes parts of the image transparent (face, background...)
Custom nodes for modifying, saving and loading of various conditionings.
Node for usage of Gemini API
A simple and intuitive prompt management tool for ComfyUI.
A Beginner-friendly Node Suite for prompt refinement in ComfyUI, including custom nodes for weighting, splitting, combining, catalogues, and the PromptRefiner for a simple prompt interface. For more info, join me on https://www.twitch.tv/sirwillance. Be one of the first 50 followers to get a FREE upgrade to the Standard Tier!
A small arcade shooter that runs inside the ComfyUI canvas where players survive swarms of API nodes.
Docked lofi radio player for ComfyUI.
Local GGUF LLM/VLM nodes for ComfyUI (llama.cpp): prompt generation, image captioning and VRAM management, with automatic GPU setup for llama-cpp-python and a prompt library for Krea2/FLUX2 images and MiniMax H3 video.
Queue progress monitor accessory for ComfyUI that displays rendering progress, processing speed, history, and KSampler preview in a single node. (Description by CC)
ComfyUI custom nodes for working with [a/Ollama](https://github.com/ollama/ollama). NOTE:Assumes that an Ollama server is running at http://127.0.0.1:11434 and accessible by the ComfyUI backend.
Fast, GPU-batched RIFE frame interpolation for ComfyUI with working bidirectional ensemble in fp16/32. Self-contained, weights bundled, no extra dependencies.
MooER is an LLM-based Speech Recognition and Translation Model from Moore Threads.You can use MooER when install ComfyUI_MooER node
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
SolarRenderer: Few-Step Generative Reference Rendering
A ComfyUI custom node for cropping videos using FFmpeg with pixel-precise control.
Preview images of LoRA files and edit their associated JSON files.
Distilled 1-step ResShift super-resolution (×4 or ×2) as a pixel-space IMAGE to IMAGE node. A ResShift student distilled from a 15-step teacher upsamples any RGB image in one stochastic step (scale dropdown). Self-contained vendored ResShift net (no xformers needed on any GPU); student + vq-f4 VQGAN auto-download on first use.
KSampler-compatible Anima EasyControl image conditioning for ComfyUI.
This is node replaces the init_image conditioning for the [a/Stable Video Diffusion](https://github.com/Stability-AI/generative-models) image to video model with text embeds, together with a conditioning frame. The conditioning frame is a set of latents.
Automatically removes an item from the job queue after the job is finished. No custom nodes are required.
Through this node, you can more easily test the impact of different blocks in flux_lora on the final result.
Motion-aware denoising cache and batched VAE decoder for MiniMax H3 in ComfyUI
Standalone ComfyUI custom node for generating clean sphere-based relighting reference images with in-node orbit gizmo.
A node designed specifically for image editing models—supporting tiled refinement, editing, and upscaling—compatible with FLUX.3/FLUX.2 klein, Qwen-Image 2.1 / Edit 2509 / 2511, Krea 2+lora and Moss +lora, while ensuring cross-tile consistency.
NODES:Google Translate
ComfyUI V3 nodes for official dots.tts checkpoints by T8star-Aix
Local FLUX 3 PUP prompt enhancement with Q4_K_M GGUF, reference images and layout support. Windows/NVIDIA; separate model and runtime downloads are required.
ComfyUI Diffusers wrapper nodes to run SANA models on low vram devices. Works on 2GB VRAM 12GB RAM laptop.
Nodes to generate audio for video using [https://github.com/hkchengrex/MMAudio](https://github.com/hkchengrex/MMAudio), with Audio Adjustment (Pitch Adjustment) and bug fixes.
ComfyUI custom node for rendering seam-free turntables and multiple views from Trellis meshes using native PyTorch rendering.
ComfyUI nodes for running Lightricks LTX-2.3 video generation natively on Apple Silicon via MLX (ltx-2-mlx), including text-to-video, image-to-video, and audio-to-video.
Pauses your workflow and opens a popup window to manually pick which generated images pass through to the rest of the graph.
Smooth and stabilise OpenPose in ComfyUI: removes pose jitter, hand flicker and dropped keypoints before ControlNet.
A collection of utility nodes designed to enhance your ComfyUI workflow with smart image loading, Krita integration, widget extraction, and more.
A custom ComfyUI node using Together AI's Vision models for free image descriptions, image generation, and image-to-image transformation. Features include customizable prompts, advanced parameters, and robust error handling.