ComfyUI Custom Extensions

Custom nodes for ComfyUI that help iterate over and save image/caption datasets, useful for preparing training data for fine-tuning diffusion models.

ComfyUI custom nodes for Chutes.ai video generation API

Fixes ComfyUI's case-sensitive dropdown sorting so all combo widgets sort A→Z, case-insensitively.

Cyberpunk/Spy-craft steganography nodes for ComfyUI. Hide secret text messages inside AI-generated images using LSB (Least Significant Bit) steganography. Features encryption with optional password key. Nodes: StegoEncode (hide text), StegoDecode (reveal text).

Load numbered videos from a folder for batch workflows. Supports skip-missing mode for sequences with gaps.

A raw, flexible wrapper node for running local Llama binaries directly within ComfyUI with full control over flags and support for experimental models.

Unified loader nodes with folder organization support for checkpoints, LoRA, VAE, and diffusion models

AsyncDiff node for ComfyUI

[a/Distrifuser](https://github.com/mit-han-lab/distrifuser) sampler node for ComfyUI

ComfyUI custom node for generating and controlling random seeds across multiple generations. (Description by CC)

ComfyUI custom node: Load & Resize Image with Mask and Filename output

A custom ComfyUI node that receives a text prompt, removes or replaces sentences based on user-defined trigger words, and passes the filtered text to the next node.

A custom ComfyUI node that batch-processes files from an input folder, removes every sentence containing the word "Watermark", and saves cleaned files to an output folder. Supports dry run and case-sensitive modes. (Description by CC)

Build a ComfyUI "self-improving" workflow where each render is evaluated by a local vision LLM, which then edits the prompt/parameters and triggers another run.

face detection nodes for comfyui

Nodes:SingleImageDataUrlLoader

ComfyUI custom node that generates pose images from DWPose/OpenPose keypoint data, allowing creation of pose visualizations with selectively filtered body parts. (Description by CC)

Custom ComfyUI node providing comment stripping functionality for prompts with multiple marker styles. (Description by CC)

Custom nodes for ComfyUI that send images and videos directly to Telegram chats.

ComfyUI Frontend Vue Basic is custom node that demonstrate how to use vue as frontend framework along with primevue and vue-i18n, cooperating with ComfyUI API. Needs ComfyUI Frontend 1.25.0 or later.

Automated workflow tool for scheduling and publishing AI artwork directly to DeviantArt with full mature content controls.

SnJake Baikal-Swin-Anime x2 is a custom ComfyUI node for upscaling anime/illustration images with a dedicated restoration model.

ComfyUI custom nodes for InfiniDepth — arbitrary-resolution monocular depth estimation.

Generic YOLO-Pose keypoint detector: IMAGE -> keypoints JSON (also to /history).

Multiple named boolean toggle switches in a single node, each with an independent BOOLEAN output. Adjustable toggle count (1-20) and labels; batch-apply to other nodes by name filter (widgets/bypass/mute).

ComfyUI custom node for flexible image loading with file picker and random folder selection. Features instant preview, auto mode switching, and browser-based file selection.

NODES: Mobile SAM Model Loader, Mobile SAM Detector, Mobile SAM Predictor

ComfyUI custom node for Kie Nano Banana 2 image generation with optional reference images.

A ComfyUI custom node for saving images in various formats

A powerful ComfyUI custom node for saving images with flexible custom metadata fields embedded in PNG files.

Custom ComfyUI nodes for the INDG toolset including flexible image batching, path utilities, and memory cleanup.

Generate and edit images using Google Gemini models in ComfyUI with ComfyUI Cloud API authentication.

Anima loader nodes for ComfyUI. AnimaAdapterLoader auto-detects LoRA, HydraLoRA multi-head with live σ-conditional and FeRA-style FEI-conditional routing, ChimeraHydra dual-pool routing (per-Linear content router + network-level FreqRouter on FEI+σ), and LoReFT residual-stream edits. AnimaFeraLoader handles FeRA (Yin et al., arXiv:2511.17979) — both the author-faithful networks.methods.fera format and the plan2 stacked_experts_global_fei format with global router on the latent's spectral energy + independent stacked experts per Linear. AnimaSoftTokensLoader handles SoftREPA-parameterization soft tokens (Lee et al., arXiv:2503.08250) — per-layer × per-timestep-bucket learned tokens spliced into the crossattn embedding inside the first n_layers DiT blocks. Three single-purpose nodes; chain via the MODEL socket.

Nodes: Ultimate Concat (Mobile), Send Notification (Mobile), Settings Launcher (Mobile), Settings Launcher Outputs (Mobile)

Ported from ComfyUI-IF_Gemini to support Gemini 3.0 API calls. Please NOTE: Open Router Functionality has been removed.

Custom ComfyUI node: switch between two inputs from an optional boolean condition, with graceful handling when inputs are missing.

Virtual Set and Get nodes for ComfyUI: name a value on a Set node and read it from a Get node without long wires.

Node for scheduling conditioning strength while preserving non-floating tensors such as token ids.

A node for ComfyUI that provides a convenient way of resizing or cropping an image for diffusion tasks.

A simple node for ComfyUI that rotates or resizes the input latent to common orientations.

Lazy indexed switches with a default route for ComfyUI.

Adds windowed, curved shift control for Flow Matching samplers (SD3-style / flow schedules). It is a drop-in replacement for Comfy's included ModelSamplingSD3 node.

A node for ComfyUI that picks from `input_a` and `input_b` based on the given `chance`.

Lightweight repository containing an independent CCIP inference module for anime character feature extraction, pairwise difference calculation, and clustering. (Description by CC)

A minimal ComfyUI custom node plugin to load and run a CCIP adapter.

Pick a megapixel budget and aspect ratio; get the closest usable resolution.

Nodes to enable easy selection of image/video sizes (width/height) and int/string selectors

Custom nodes for ComfyUI that enable video generation using ByteDance's Seedance model via [a/Fal.ai](https://fal.ai/).

This custom node saves metadata when I explore images. It creates a sidecare json file beside the image file.

This custom node builds a new LoRA or patch file relative to a finetuned model, computing weight differences and writing results as standard LoRA or exact diff patch files.

Custom nodes for ComfyUI that combine LoRA loading with prompt text injection and a boolean enable/disable switch.

This custom node ports the sd_forge_multidiffusion model wrapper into ComfyUI.

Adds a StableYogi Prompt node that outputs a ready-made prompt string. Wire it into CLIP Text Encode and every queue pulls a fresh prompt.

ComfyUI integration for LlamaCPP Python with logging support. (Description by CC)

Simple test bridge from ComfyUI to OpenAI image generation and editing.

Logic control node with 5 universal input ports that checks connections in reverse priority order and outputs the index of the first valid active input, with support for muted nodes and any data type.

Mega-ASR's comfyui version implementation

Clean pure-torch Deforum-style nodes for ComfyUI animation loops: an exact-Deforum depth-aware 3D camera warp (pixel-identical to transform_image_3d), LAB/EMA color-coherence nodes that stop feedback-loop color drift, a vanilla-semantics cadence node, and an optical-flow estimator.

Custom ComfyUI Nodes for verifing needed files/models are present per workflow, can download if missing.

Utility nodes for ComfyUI workflows. (Description by CC)

Export images from Photoshop directly into ComfyUI running on RunPod — no cloud uploads, just local files synced over SSH.

Add vertical and horizontal video grid support

Custom nodes for ComfyUI including LLM Chat (Claude, Gemini, GPT), WaveSpeed AI image and video generation, VertexAI integration, and workflow utilities.

Real-time memory monitor for ComfyUI on Apple Silicon (MPS / unified memory) — unified RAM, MPS driver/active, MLX Metal, swap, and per-run peaks. The Mac analogue of ComfyUI-MemoryVisualization.

Custom Nodes for Creative Engineering in ComfyUI at Studio Deep (Freelance Generative AI Engineer)

Control which groups execute based on iteration ranges - a simplified alternative to complex conditional branching workflows.

A small ComfyUI custom node for building strong image prompts from separate, structured fields.

A ComfyUI custom node that loads character definition YAML files and lets you compose prompts via per-category dropdowns with live rescan support.

Custom node for ComfyUI to load the Orpheus TTS base model and prepare it for LoRA injection + speech generation.

ComfyUI custom node that loads UNET diffusion models and extracts the model name as a string output.

A custom ComfyUI node that uploads generated images directly to Google Cloud Storage and notifies your Supabase database — with zero Supabase Egress cost.

A ComfyUI custom node for generating images with Z-Image through Hugging Face Diffusers with configurable model selection and generation parameters.

A collection of custom nodes for ComfyUI

NODES:Reflatent

A custom node suite for ComfyUI that provides accelerated video generation using [a/FastVideo](https://github.com/hao-ai-labs/FastVideo). See the blog post about FastVideo V1 to learn more.

Vates brand high-performance sampling pipeline with Rust components, offering precision σ scheduling, memory optimization, and noise alignment for efficient multi-batch image generation. (Description by CC)

Utilities for working with camera animations inside ComfyUI. The repository currently provides a node for loading camera motion from ASCII FBX files and a corresponding command line helper for debugging.

Unofficial ComfyUI environment using web scraping methods to enable Meta AI integration for text-to-image and image-to-video generation. (Description by CC)

Custom node that provides loop (for-loop) functionality in ComfyUI.

ComfyUI custom node to save prompt and intermediate outputs

A tiny ComfyUI custom node that detects whether a face is in profile using SEGS eye detections.

ComfyUI custom node set for batch comic-page generation from a JSON script

A dedicated ComfyUI custom node designed to streamline the process of converting transparent images (RGBA) into masks and high-quality mask previews.

TK View and Light: A ComfyUI node for 3D camera and lighting control

A custom ComfyUI node that allows interaction with Mistral AI language and vision models directly inside a ComfyUI workflow.

A minimal, opinionated ComfyUI custom node that emits portrait (0°) and/or landscape (90°) latent variants in a single run.

A lightweight browser extension + custom ComfyUI node that creates a seamless Web → ComfyUI pipeline for sending images directly from the browser into your workflows.

This is a custom node for ComfyUI. The PromptGenerationConfig node allows users to configure settings such as image dimensions, step count, and CFGScale through prompts during image generation. The PromptEdit node enables users to add text from the prompt to the negative prompt (or vice versa) and replace parts of the prompt using regular expressions.

Batch sampling utility node for ComfyUI. (Description by CC)

A comprehensive set of ComfyUI custom nodes for interacting with RunPod's serverless API, including both public endpoints (Flux, Qwen, Seedream, WAN, SORA, etc.) and custom serverless workers.

Advanced ComfyUI node pack: seam-locked pose tiled upscaling and cap-based temporal stitch inpainting for WAN VACE.

A rotoscoping tool for ComfyUI that allows you to create animated masks using polygon curves with keyframe interpolation.

FaceCLIP nodes for ComfyUI providing joint embeddings from aligned face images plus text prompts, and identity-preserving image synthesis using fine-tuned SDXL UNet. (Description by CC)

Simple collect all batch output, then convert to a string list, like ECMAScript Promise.all

Resize and pad with color selection for ComfyUI

A simple ComfyUI custom node for string interpolation.

A collection of custom nodes for ComfyUI that streamline common workflows. — All-in-one model loaders: checkpoint, LoRA, CLIP, VAE — GGUF quantized model support: FLUX, FLUX2, SDXL, SD3.5 — Workflow settings nodes for FLUX, SDXL, and SD3.5 — Latent factory with aspect ratio, megapixel, and automatic model format detection — Context nodes for passing pipeline state between nodes — CLIP text encoders for FLUX, SDXL, and SD3.5 — KSampler variants with guided sampling and step-by-step latent preview — VAE encoders and decoders: tiled and context-based — Image tools: load, resize, upscale, preview, save, ControlNet reference — Post-production: brightness, contrast, LUT color grading, film grain, upscaler

Custom nodes for ComfyUI with advanced image scaling, latent manipulation, and Flux sampling

ComfyUI extension with several convenience nodes.