ComfyUI Custom Extensions
Browse 8,530 ComfyUI extensions and 65,510 custom nodes.
Setting Up a Web Interface Using ComfyUI. NOTE:When installed, you can access it via http://127.0.0.1:8188/comfygen.
This custom node provides the capability to manipulate multiple string inputs.
MiniMax H3 video and audio generation nodes for ComfyUI
IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech
ComfyUI nodes for FLUX.2 Klein conditioning: region-aware text enhancement, sectioned prompt encoding, and corrected reference-latent mixing with multi-reference support.
for use jimeng ai in comfyui
Add title, comment and memo functions to nodes, which support custom styles and automatic word wrapping, compatible with Nodes 2.0.
A simple ComfyUI plugin that Its purpose and function is to replicate some of the editing effects of capcut,jianying and pr.
card-per-image folder viewer with editable prompts and per-image output sockets.
ComfyUI custom node - all-in-one Ultimate Sampler V6.5. Loads whole checkpoint or split stack (diffusion + dual CLIP + VAE), supports Flux/SD3/Wan/Qwen-Image/Krea2/Z-Image/LTXV and more, with LoRA list and fp8/nvfp4 weight precision.
NODES:Advanced Lying Sigma Sampler, Save Image To target Path
ComfyUI nodes for HiDream-I1 model.
ComfyUI-HunyuanPortrait is now available in ComfyUI, HunyuanPortrait is a diffusion-based condition control method that employs implicit representations for highly controllable and lifelike portrait animation.
Make Matrix-Game avialbe in ComfyUI.
ComfyUI nodes for UNO model.
A ComfyUI custom node that patches the attention mechanism to use Flash Attention 2 on AMD, similar to how Patch Sage Attention KJ works in KJNodes.
Smart context window model patches for SCAIL-2 long video workflows in ComfyUI.
This is a ComfyUI node package that integrates with VIDU API, supporting features such as text-to-video, image-to-video, character-to-video generation, and video super-resolution.
A comprehensive queue management system for ComfyUI workflows
a custom node for [a/EzAudio](https://github.com/haidog-yaqub/EzAudio)
TeleStyle custom nodes for ComfyUI video style transfer and official Qwen image style transfer.
Custom nodes to run microsoft/Phi models.
A ComfyUI custom node that enhances image and video generation prompts using LM Studio's local OpenAI-compatible API.
Ultralytics workflow and editor tools for ComfyUI with enhanced preview and UI integration.
Custom ComfyUI nodes for StoryMem - Multi-shot long video storytelling with memory-conditioned video diffusion models.
ComfyUI custom nodes for Cosmos reference latent conditioning.
All-in-one face styling node for ComfyUI: curated style presets with auto-fill prompts, FaceDetailer parameters, and a dynamic searchable LoRA stack. Outputs CONDITIONING + modified MODEL ready for FaceDetailer / KSampler.
Custom FP8 compute kernels for Apple Silicon (MPS)
ComfyUI Nodes for HPSv2, Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
Custom ComfyUI node for using Qwen-Image-Layered as a conversion tool to transform layer numbers into latent space length parameters. (Description by CC)
Add text to image in ComfyUI
DiffRhythm2 歌曲生成。
OuteTTS - Unified Text-To-Speech. A node for ComfyUI
Professional OpenColorIO / ACES color-management nodes for ComfyUI. Mirrors Nuke's OCIO node set with ACES 2.0, 1.3, and 1.2 support, EXR sequence loading, animated preview, and video export (MP4, WebP, GIF).
Quickly create empty latents in common resolutions and aspect ratios for SD 1.5, SDXL, Flux, Chroma, and HiDream. Choose from curated presets or generate by axis and aspect ratio. Appears in the 'latent' node group.
Custom node for ComfyUI that allows you to analyze songs using NVIDIA's Music Flamingo.
This is a ComfyUI implementation of the timestep shift technique used in [a/NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training.](https://arxiv.org/abs/2412.02030) For more details, visit the official [a/NitroFusion GitHub repository](https://github.com/ChenDarYen/NitroFusion).
Some mathematical calculation nodes，freedom And omnipotent, string calculation nodes, can customize the number of parameters and calculation formulas（expression）. The calculation content can also be displayed in places such as the label title of Comfy Node，String to Image Title Label
A ComfyUI scheduler that finds the shift value required to align high/low sampling steps with a target sigma boundary.
A modern ComfyUI custom node package that provides essential UI controls for image generation workflows. These nodes allow you to centralize commonly shared parameters (scheduler, sampler, dimensions, seeds) and link them to multiple nodes in your workflow, eliminating redundancy while maintaining JSON metadata compatibility.
This Comfyui node creates an anaglyph image from a color and depth map input. It achieves high speeds suitable for video to anaglyph conversion by using CUDA GPU acceleration.
It works the same as human-parser-comfyui-node but is implemented in pure Python so that it doesn't require a runtime build for InPlaceABNSync.
One-node NegPiP prompting for Z-Image, SD1, SDXL, and Anima in ComfyUI.
A collection of custom nodes for ComfyUI.
A collection of custom nodes for ComfyUI.
A professional ComfyUI custom node for browsing and loading LoRA files with folder tree navigation, multi-slot support, and instant preview.
Distributed image generation for ComfyUI with Thinkbox Deadline integration (master/worker via render farm)
A Simple App U See. A simple alternative User Interface for Image and Video Generation using ComfyUI as backend.
Standalone version of ComfyUI's PreviewImage and SaveImage nodes, extracted as an independent custom node for easy reuse and customization.
A collection of ComfyUI custom nodes for interacting with various cloud services. These nodes are designed to work with any ComfyUI instance, including cloud-hosted environments (such as MimicPC) where users may have limited system access.
650+ visual styles for ComfyUI, every one with a rendered preview you can browse before you commit. Each ships a written description, a keyword list and a matching negative prompt. Plus 1000+ artists with descriptors that work even when your model does not know the name, and previewed modifiers for lighting, colour, era, period dress, finish and mood. Offline, zero dependencies.
Mask and control-frame generation nodes for WanVideo/VACE workflows — supports 11 generation modes, source trimming, and merge-back with optical flow blending.
Takes the difference in between the positive and negative conditioning at the attention. NOTE: Will not work with Flux
editing activations in wanvideo
It is a simple HunyuanVideo block swap node for ComfyUI native nodes.
ComfyUI-native nodes to run First Order Motion Model for Image Animation and its non-diffusion-based successors. [a/https://github.com/AliaksandrSiarohin/first-order-model](https://github.com/AliaksandrSiarohin/first-order-model)
A collection of ComfyUI nodes. Including: WFEN, RealViFormer, ProPIH
PromptSync video tools, MiniMax H3 media references, prompt utilities, and video comparison nodes for ComfyUI.
A ComfyUI custom node connecting to local OpenAI-compatible LLM servers (LM Studio or vLLM) that transforms ideas into optimized prompts for various image and video generators.
Basic Dynamic Prompts functionality with a Rich Text texbox for coloring.
ComfyUI extension to scan local Civitai models and check for newer versions.
A modern re-implementation of the classic [a/cg-image-picker](https://github.com/chrisgoringe/cg-image-picker) ComfyUI nodes. Keep the workflow-pausing image selection experience while shedding the legacy compatibility shims.
Generate images with your ChatGPT subscription - no API key: your Codex CLI login runs gpt-image-2 inside ComfyUI, billed to your ChatGPT plan. Plus 212 fal.ai nodes, one per model, each with a live price badge, a spending cap, reuse of identical paid runs and free result recovery: all Flux (1, 2, Kontext, Flux 3 video), all MiniMax (Hailuo, H3, Speech, Music), all ElevenLabs, all Nano Banana, Seedance 2.5, Kling, Topaz, Qwen, Sync lipsync, SAM 3.1 video segmentation and VEED Fabric - one command adds any new fal model. Also: shared image settings, run-N-of-M shot selection, auto-numbered run folders, caption sidecars, reusable system prompts, and video, TTS and caption utilities. Keywords: ChatGPT, Codex, gpt-image-2, fal, Flux, MiniMax, Hailuo, ElevenLabs, Nano Banana, Seedance, Kling, lipsync, image to video, text to speech.
Nodes:Image Gradient,Mask Gradient
Tag completion with a1111-sd-webui-tagcomplete style wildcard sub-selection, supporting CSV files and multiple wildcard sources. Features smart parsing, text overflow handling, and full compatibility with existing wildcard files. v2.0.0 with major wildcard workflow improvements.
HuggingFace model downloader for ComfyUI — search, download, and organize AI models directly within your workflow with integrated Civitai repository access and batch download support.
Experimental Normalized Attention Guidance node for Anima Preview 3 in ComfyUI.
This custom node for ComfyUI allows you to test combinations of samplers and schedulers. It generates a batch of generated images(latents), as well as RGB images, each one annotated with the specific combination used, performance timing, and several image quality metrics (Laplacian Variance, Gradient Mean, FFT-based sharpness) for our internal usage, but kept as they could may be useful for others to.
ComfyUI nodes for FeyNobg (feyninc/FeyNobg), a BiRefNet-based background removal model. Vendors its own Swin-Transformer backbone so it never upgrades ComfyUI's pinned transformers/torch versions. Supports HuggingFace and ModelScope download sources.
A ComfyUI custom node that automatically selects appropriate video resolution dimensions based on generation mode, aspect ratio, and quality settings. Designed to work seamlessly with video generation models and KJNodes image resize nodes.
A model cached-loader custom node for ComfyUI.
Excel spreadsheet-driven ComfyUI nodes that let you load models, values, and workflows based on saved rows in Excel. Great for organizing and switching between CLIPs, VAEs, LoRAs, and more.
Nodes:SaveImgAdv, CLIPTextEncodeWithStats. Collection of tools supporting txt2img generation in ComfyUI and other tasks.
Archive and organize your generated images into date-structured folders, and compress PNG images to JPEG/WebP with full workflow metadata preservation, saving 85-95% disk space.
The unofficial implementation of ZIM in ComfyUI
Standalone ComfyUI node to grab the last N frames from a directory as a single batch with optional frame stride, designed for video continuation workflows and temporal consistency improvement.
ComfyUI custom nodes for VibeVoice ASR (Automatic Speech Recognition) with support for auto-labeling music/lyrics and high accuracy transcription.
text_append_node, vramdebugplus, tensordebugplus, animation_schedule_output
Diffusers custom_node
Custom_nodes for model in ComfyUI
Batch samplers, schedulers, cfg, shift and steps tester custom node, automatic looping functionality for RES4LYF custom nodes
Load Anima Base and Anima 2.9B LoRAs on the inherited layers of Anima 3.8B.
Nodes:CLIP Text Encode (Batch), String Input, Batch String
NODES:HF ModelLoader, Show Images, Text2Image Inference, Decode Latent, Show CrossAttn Map, Show SelfAttn Map
ComfyUI nodes for RGB-X: Image decomposition and generation using intrinsic channels (albedo, normal, roughness, metallic, irradiance)
Adaptive sigma scheduling custom node for ComfyUI. Dynamically adjusts step sizes during sampling based on how the denoising direction changes.
This node is to fill image for outpainting(inpainting) Fill image using cv2 methods(cv2_ns, cv2_telea and edge_pad)
Nodes for loading and saving images with metadata in ComfyUI.
Pixstri is a custom plugin for ComfyUI designed to generate comic pages. It provides a hierarchical node system that allows you to create comic layouts with rows and frames, making it easy to design and preview comic pages within your ComfyUI workflows.
Block Swap (RAM Offload) node for native ComfyUI MODEL - run DiT models larger than VRAM by streaming transformer blocks from system RAM.
Restoring the ComfyUI frontend pre-vue update queue functionality, drag&drop support, quicksave, and more in a clean design that respects your screen area.
A collection of ComfyUI custom nodes that allow to use most Diffusers pipelines and components in Comfy(Txt2Img, Img2Img, Inpainting, LoRAS, B-LoRAS, ControlNet...)
Makki's self custom nodes for ComfyUI.
The Face Cropper Node (MarwanFaceCropping) is a custom image processing node designed for ComfyUI. It takes an input image and crops it to a 2:3 aspect ratio, ensuring that most of the subject remains in the frame while maintaining the correct proportions.
Why make this node? Because I only need simple text related operations and don't want to install anything extra.
MTCLIPEncode: An extension for ComfyUI's CLIPTextEncode node, offering multilingual translation (using MarianMT) and prompt enhancement (using Ollama). Seamlessly translate your native language prompts into English and further optimize them for generating your desired images with Stable Diffusion. Supports Krita AI Diffusion.
Translates Audio Music to MIDI
Custom ComfyUI nodes used in Maxed Out workflows (SDXL, Flux, etc.)
An enhanced extension for ComfyUI that records, visualizes, and extracts the actual execution path of a workflow.
Nodes: InpaintMediapipe. This node provides a simple interface to inpaint.