Custom nodes (7817) sorted by GitHub Stars

• **MAGI-1** - 1: Autoregressive Video Generation at Scale
• **WAS Node Suite**
• **Comfy-WaveSpeed**
• **ComfyUI-ComfyUI-Hunyuan3DWrapper** - 2, additional installation steps needed, please check the github repository
• **refiners**
• **ComfyUI-Gemini** - pro & Gemini-pro-vision in ComfyUI.
• **AnimateDiff** - webui-animatediff.
• **FitDiT[official - fidelity virtual try-on using Diffusion Transformers (DiT).
• **ComfyUI_Qwen2-VL-Instruct** - VL-Instruct](https://github.com/QwenLM/Qwen2-VL) by [a/ComfyUI](https://github.com/comfyanonymous/ComfyUI), which includes, but is not limited to, support for text-based queries, video queries, single-image queries, and multi-image queries to generate captions or responses.
• **ComfyUI-MMAudio**
• **TRELLIS2** - env` to attempt a one click isolated install. Will download and use pixi package manager. ComfyUI nodes for TRELLIS.2 - Microsoft's image-to-3D generation model. Generate high-quality 3D meshes with PBR materials from a single image. Models autodownload from HuggingFace.
• **ComfyUI-WanAnimatePreprocess**
• **OmniVoice TTS** - speaker, voice design, text-to-speech
• **Rebalance Pack**
• **PixelOE** - Oriented Pixelization based on Contrast-Aware Outline Expansion.
• **BenjiAI**
• **UniRig** - env` to attempt a one click isolated install. Will download and use pixi package manager. Automatic skeleton extraction for ComfyUI using UniRig (SIGGRAPH 2025)
• **Licon MSR** - frame MP4 reference videos from multiple subject images and a background image, designed for LTX 2.3 MSR (Multiple-Subject-Reference) LoRA workflows.
• **Comfyui_Comfly**
• **ComfyUI-BiRefNet**
• **ComfyUI-SDPose-OOD**
• **ComfyUI HY Motion1** - Motion 1.0 for text-to-3D human motion generation.
• **MotionCapture** - 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-INT8-Fast** - 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-Qwen3-TTS** - TTS, supporting 1.7B and 0.6B models, Custom Voice, Voice Design, Voice Cloning and Fine-Tuning.
• **ComfyUI-Easy-IndexTTS2** - shot text-to-speech synthesis system.
• **WeiLin-ComfyUI-prompt-all-in-one** - ComfyUI-Prompt-all-in-one Write prompt words like WebUI
• **ComfyUI-QwenTTS** - TTS. It provides CustomVoice, VoiceDesign, and VoiceClone workflows with strict ComfyUI compatibility and practical controls for quality, speed, and stability.
• **Echo-Memory** - Memory: controlled memory study on Wan 2.1 1.3B (Context, Compression, Spatial, State-Space).
• **10S Nodes** - pass quality, and STG guidance nodes for the LTX2 video diffusion model
• **ComfyUI-Qwen-Image-Integrated-KSampler** - Github: https://github.com/luguoli - intelligent multimodal sampler, support Z-Image, optimizes official offset issues, image scaling, multiple reference images, automatic VRAM/RAM management, batch generation, automatic saving, sound notification
• **radiance** - bit color space collection of nodes for ComfyUI.
• **FreeFuse**
• **ComfyUI-Logic**
• **Comfy Pilot**
• **ComfyUI-Unique3D**
• **ComfyUI-ZML-Image** - w/ZZZ_ZML_English_Patch
• **ComfyUI-Model-Manager**
• **ComfyUI-Qwen3-ASR** - ASR, supporting speech-to-text transcription with 1.7B and 0.6B models, 52 languages/dialects, and optional timestamp alignment.
• **SAM3DObjects** - env` to attempt a one click isolated install. Will download and use pixi package manager. ComfyUI wrapper for SAM3DObjects: extract 3D meshes/gaussians from pictures
• **Comfyui UltraShape1** - Image-guided 3D mesh refinement
• **comfuinoda-Navyblue** - to-use node. However, I have observed that LyingSigmaSampler does not control the noise mask smoothly enough, or in other words, it cannot control it more precisely. LyingSigmaSampler has a great advantage, of course, other nodes are also great. They can be applied to most models, including SD3.5, and they work well, which is a challenge for users because they have to deal with different noise masks. Therefore, I have added smoothing processing to LyingSigmaSampler in the hope of helping more people.
• **ComfyUI-Panorama-Stickers**
• **ComfyUI-ComfyUI-VideoNoiseWarp** - Research/Go-with-the-Flow
• **NKD VFX Tools** - direct generation with light, camera, depth, 3D placement and perspective. Relight, lens blur, lens distortion, 3D/splat preview, fSpy camera solve, perspective unwarp
• **ComfyUI-FL-Qwen3TTS** - High-quality text-to-speech with voice cloning, voice design, and custom voices
• **Workflow Models Downloader** - powered advanced search, metadata caching, and automatic URL restoration.
• **ComfyUI-Catcat**
• **ComfyUI SCAIL2 Multi Cond** - reference and scheduled SCAIL-2 workflow helpers for ComfyUI.
• **FL AceStep Training** - LoRA Training nodes for ACE-Step 1.5 in ComfyUI
• **ComfyUI_Local_Media_Manager**
• **LiTo Image-to-3D** - env` to attempt a one click isolated install. Will download and use pixi package manager. ComfyUI wrapper for LiTo: single-image to 3D Gaussian Splat generation
• **FSampler - Fast Diffusion Sampling via Epsilon Extrapolation** - free, sampler-agnostic acceleration layer for diffusion sampling that reduces model calls by predicting each step's epsilon (noise) from recent real calls. Provides fixed history modes (h2/h3/h4) and adaptive mode for 40-60%+ speedup.
• **ComfyUI-GLM4** - to-prompt capabilities. Features include advanced text chat (video prompt expansion) and GLM-4V powered image description.
• **ComfyUI_MagicQuill** - 4 like large language and visual assistant.
• **ComfyStream**
• **ComfyUI-SecNodes_Ultra_Fast**
• **SDVN_Comfy_node** - Image
• **Anima Artist Mixer** - artist mixing for Anima through cross-attention or post-adapter embedding projection.
• **ComfyUI FL-MCP** - compatible agents to your local ComfyUI setup.
• **大炮-Qwen3VL** - Qwen3VL ComfyUI 自定义节点集合，集成了阿里云 Qwen 团队开发的 Qwen3-VL 多模态大语言模型系列。
• **Qwen-2.5 in ComfyUI** - 2.5 in ComfyUI
• **ComfyUI-Qwen3-TTS** - TTS voice cloning and multi-character dubbing. Features script-driven unlimited multi-character dubbing, emotion-aware speech-to-speech (ASR) technology, and efficient speech asset management capabilities.
• **ComfyUI-HunyuanVideo-Foley**
• **OpenPose Editor (DocKr)** - completion, pause/edit workflow support, and UI fixes.
• **houdini-comfyui-bridge**
• **ComfyUI GaussianViewer**
• **ComfyUI-Index-TTS2** - Index-TTS2 is a custom node plugin for ComfyUI that packages the core functionality of IndexTTS2 (long-form, multi-speaker, multi-dialect podcast voice generation) into a visual workflow
• **ComfyUI-OCIO** - style OpenColorIO color nodes for ComfyUI. Read a still/sequence/video, grade in ACES, decode a generative model's latent without the 0..1 clamp, write EXR/TIFF/PNG/JPEG or ProRes/DNxHR/h264/hevc - fully color-managed, on ComfyUI's native VIDEO wire, and encode ACEScct for LTX-2.5's native HDR path. Thirteen nodes: Read, Write, Player, ColorSpace, LogConvert, Exposure, Display, CDLTransform, FileTransform, LookTransform, Clip Repair, VAE Decode, VAE Encode.
• **MiniMax H3 FirstBlockCache**
• **ComfyUI-TrixLoader** - style Camera Raw, Advanced AI Mask Editor (SAM 2.1/3, GroundingDINO, RMBG), and Crop-Pad-Outpaint (CPO) Editor for ComfyUI.
• **comfyui-purgevram**
• **ComfyUI-Muye-nodes**
• **ComfyUI-Video-Stabilizer**
• **ComfyUI_SenseNova_U1** - U1: Unifying Multimodal Understanding and Generation with NEO-Unify Architecture
• **ComfyUI-Florence-2** - 2-large-ft](https://huggingface.co/microsoft/Florence-2-large-ft)
• **Wan-SVI2Pro-FLF**
• **WhiteRabbit**
• **ComfyUI_ChatterBox_SRT_Voice** - Audio-Suite). This legacy v3.x version is maintained for compatibility only. For new projects, use TTS Audio Suite v4.0.0+ which provides a unified multi-engine TTS platform with ChatterBox, F5-TTS, Higgs Audio, and RVC support.
• **DJZ-Nodes**
• **Anima Prompt T8**
• **UniVidX Intrinsic & Alpha Decomposition**
• **Segment-Queue-Runner** - task parallel queue.
• **HY-World 2.0 — WorldMirror 3D** - World 2.0 ComfyUI nodes — WorldMirror V1 & V2 3D reconstruction
• **python-interpreter-node**
• **comfyui-gpt-image2-prompt-T8**
• **Cable Management for ComfyUI** - chained links, PCB-style routing, ribbon cables, and proper right-to-left wrapping support.
• **ComfyUI-DanbooruSearcher**
• **Comfy Inpainting Works** - Net inpainting and/or outpainting with batch size - Alimama or Flux Fill'. Works with Kontext now! By installing this 'node' you can always keep them up to date by updating on the manager. This is not a new custom node. You will still need to install all other custom nodes used on the workflows. You will also find my 'Flux LoRA Block Weights Preset Tester' here.
• **ComfyUI Storyboard** - to-use Storyboard extension for ComfyUI.
• **Comfyui_Prompt_Edit**
• **Group Assistant**
• **ComfyUI-Sentinel** - user registration, IP filtering, and user-specific input/output directories.
• **comfyui_bmad_nodes**
• **Diffusion_pipe_in_ComfyUI**
• **ComfyUI Easy RAG**
• **ComfyUI_Seed-VC** - VC: Very quickly convert `speech` or `singing` into another person's voice, without changing the content rhythm
• **ComfyUI-clip-interrogator** - interrogator
• **ComfyUI-Sapiens2**
• **Polotno Canvas Editor**
• **Kiko Prompt Builder** - style prompts with camera settings, lighting, composition, and color palettes. Compatible with FLUX (Black Forest Labs), z-image, and other JSON-prompt models.
• **Flux FaceIR** - face and whole-image restoration.
• **ComfyUI_BaiduTranslate**
• **ComfyUI-VideoMaMa**
• **ComfyUi-TextEncodeEditAdvanced**
• **ComfyUI Quantization Toolkit** - precision loading, LoRA handling, and low-VRAM runtime controls.
• **ComfyUI_Pixel_Snapping** - based image alignment, intelligent mask cropping and restoration for ComfyUI
• **Custom Node Kit**
• **ComfyUI_Prompt-All-In-One**
• **ComfyUI_IPAdapter_plus_V2**
• **QuantOps** - wise FP8)
• **ComfyUI-CustomNodePacks** - versioning) + MaskEditControl (pinpoint mask editing with SAM 2.1 / SAM 3, per-axis erode/expand, point editor, bbox tools, video mask propagation).
• **Decor8 AI Virtual Staging** - as-you go subscription plan or credits bundle. Reach out to decor8@immex.tech if you have any questions or need test credits.
• **Anima Sampler** - style rectified-flow sampler nodes for Anima models in ComfyUI.
• **ComfyUI NAG Extended**
• **Hunyuan3D-Part** - env` to attempt a one click isolated install. Will download and use pixi package manager. Hunyuan3D-Part nodes for ComfyUI: 3D part segmentation with P3-SAM and high-fidelity part generation with X-Part diffusion.
• **ComfyUI-RelayAPI**
• **diffus3/ComfyUI-extensions**
• **ComfyUi-ImageGalleryLoader**
• **llama-cpp-dapao**
• **Shinsplat** - over iterator. Custom LoRA Loader to extract and view meta-data and trigger phrases. Green Box is a node that can be chained to inject prompt fragments, iterating through a list. Python is a node that allows complete control, manipulation and creation of data, write your Python code inside this node. Multiple input/output ports referenced by name.
• **comfyUI_DaVinciResolve**
• **ComfyUI_LLM_Banana**
• **ComfyUI CreativeCode**
• **ComfyUI-Hangover-Moondream**
• **ComfyUI Ideogram Helper**
• **Pond Nodes**
• **ComfyUI-CustomNodes-Template** - CustomNodes-Template](https://github.com/jhj0517/ComfyUI-CustomNodes-Template).
• **FlowDenoise** - compensated temporal video denoising for ComfyUI. Optical flow-based (MEMFOF/RAFT) temporal averaging with independent chroma/luma denoising control.
• **BitsAndBytes NF4 Loaders** - foundation/bitsandbytes">BitsAndBytes</a> NF4 quantized models
• **ComfyUI Notebook** - style custom node for executing Python code within ComfyUI workflows. Features syntax highlighting, shared variables between cells, and pre-loaded libraries (numpy, torch, PIL, matplotlib).
• **ComfyUI WebUI Prompt Bridge**
• **comfyui-ayang_node**
• **ComfyUI-Hangover-Nodes** - 2 Interrogator, Save Image w/o Metadata, Image Scale Bounding Box. An implementation of Microsoft [a/kosmos-2](https://huggingface.co/microsoft/kosmos-2-patch14-224) image to text transformer.
• **Cozy Dynamic**
• **HyMotion** - Motion 1.0 for text-to-3D human motion generation with custom character support:UE5, MIXAMO, DAZ(G3,G9).
• **ComfyUI NVIDIA RTX VSR Pro** - compatible NVIDIA RTX Video Super Resolution Pro node for ComfyUI with exact 16K hybrid processing and channel-corruption detection.
• **sd-samplers**
• **ComfyUI_OmniGen_Nodes**
• **ComfyUI-AudioX** - MAF video-to-audio generation
• **ComfyUI-FunAudioBreezyVoice**
• **ComfyUI-TP-OmnimatteZero**
• **Preset Download Manager**
• **danbot-comfy-node**
• **Feedback Sampler** - style zoom animations through iterative feedback loop with pan, rotate, LAB color coherence, anti-blur sharpening, and ControlNet sequence support
• **ComfyUI_ASR**
• **comfyui-cyclist**
• **OpenCV** - level standalone functions of OpenCV Python cv2 auto-generated from the type definitions
• **ShowMe**
• **ComfyUI-FL-VoxCPM** - Text-to-speech with voice cloning, voice design, V2 support, and LoRA training
• **ComfyUI-LTX2.5-MSR** - reference image conditioning nodes for LTX-2.5 in ComfyUI, using MSR slot embeddings and negative temporal offsets.
• **Enhancement Utils** - time resource monitor (CPU/RAM/GPU/VRAM/temp), node execution profiler with per-node timing badges, graph auto-layout (Quick/Dagre/ELK), node navigation with Follow Execution, Play Sound, System Notification, and an image loader with recursive subfolder scanning, custom-folder loading, and metadata extraction. A modern, well-organized alternative to ComfyUI-Custom-Scripts and Crystools.
• **Comfyui-bitdance**
• **FLOAT Optimized**
• **CLIPSeg**
• **Krea 2 AnyPaint** - mask inpainting and outpainting
• **Comfyui-mini-nodes** - precision color matching (MKL, Wavelet, HM), latent size adjustment, and metadata-aware image saving.
• **KSampler Multi-Choice** - click your favourite and only that image gets rendered. Exact continuation, no wasted steps, works with any model.
• **ComfyUI_LTX2_SM** - 2 is the first DiT-based audio-video foundation model that contains all core capabilities of modern video generation in one modelsynchronized audio and video
• **ComfyUI-Agnes-AI** - based AI generation platform. Generate images, create videos, enhance prompts, and analyze visuals — all without a local GPU. Zero extra Python dependencies.
• **MiniMax References Manager** - to-Video, with a dedicated object/character replacement mode.
• **SDXLResolutionPresets**
• **ntdviet/comfyui-ext**
• **ASTERR** - off environment, as it could have potential security risks.]
• **ComfyUI-SC-PhotoDoodle**
• **Prompt Gallery**
• **ComfyUI_VoxCPM_SM** - Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning锛寉ou can use this node,easy infer and easy train
• **ComfyUI-SAM3D-BodyMod** - drive SAM3D Body MHR pose data in ComfyUI.
• **SDXL_sizing**
• **graphNavigator**
• **AudioSuiteAdvanced**
• **Sa2VA-DP**
• **ComfyUI_RH_Pixal3D** - to-3D generation and GLB export.
• **ComfyUI-Sapiens2-Easy**
• **Texture_Projection**
• **ComfyUI-Deforum**
• **ComfyUI_XISER_Nodes** - layer canvas editing, multimodal LLM intelligent processing (supporting mainstream models like DeepSeek, Qwen, Kimi, Wan), professional-grade image processing toolchains, video generation orchestration systems (supporting Wansiang series reference-based video, image-to-video, and keyframe-to-video generation), and visual data tools, providing end-to-end support for AI image and video generation workflows from creative conception to fine editing. With advanced PSD import, BiRefNet intelligent matting, real-time layer transformations, unified configuration-based video generation orchestration, and secure API key management, it significantly enhances creative efficiency and output quality. Additionally, it offers workflow customization features like node color management and label nodes to improve visual organization and personalization of complex workflows.
• **Diffusion_pipe_in_ComfyUI_Win** - Pipe In ComfyUI Custom Node is a powerful extension plugin that provides complete Diffusion model training and fine-tuning capabilities for ComfyUI. This project allows users to configure and launch training for various advanced AI models within ComfyUI's graphical interface, supporting both LoRA and full fine-tuning, covering the most popular image generation and video generation models available today.You can train Qwen lora with 16g Vram
• **ComfyUI-FitDit**
• **CADabra** - env` to attempt a one click isolated install. Will download and use pixi package manager. CAD file processing nodes for ComfyUI with interactive 3D OCC CAD viewer. Load STEP, IGES, BREP files and generate meshes using OCC, GMSH.
• **ComfyUI-Segmentation-Agent**
• **comfyui-copilot**
• **MiniMax H3 Direct**
• **ComfyUI-AuraSR** - ai/AuraSR model.
• **Vewd** - captures all generated media into a grid for easy viewing, sorting, and comparing.
• **Latent Tools**
• **G-Workflows** - normalized 800x450, set/capture/drag-drop) and details List view with sortable columns including Tags. Tags: dedicated sidebar pane with live counts, chip-input editor with autocomplete, drag-and-drop assign, drag-and-drop reorder, custom/A-Z/Z-A sort, global rename/delete, per-workflow Copy/Paste/Clear. Search with focused (current view) default and a Global toggle to scan every root. Stackable Name/Date sort on cards. Favorites and per-workflow descriptions, full file/folder CRUD with multi-select (Ctrl/Shift range) and mandatory delete confirmation, and a Save button that recognizes the workflow you already have open. UI extension only — adds no graph nodes.
• **Image loader with subfolders**
• **H3 Studio** - Commons image/audio search built in. Continue a clip with real continuity: the previous render's tail frames AND audio are pinned at the new head, so motion and the actual waveform carry through the join — with an auto mode that chains clips hands-free. Finished clips land on a reel you can trim, crossfade, level, score with a soundtrack lane plus three fx lanes, and export as one video. Also includes v2v restyling, soft denoise zones (differential diffusion with per-frame masks), regional prompting and a temporal LoRA blend.
• **🌊 FlowState Creator Suite**
• **ComfyUI-LoraBlockWeight** - block LoRA weighting for DiT models (FLUX.1, Qwen-Image, SD3.5 Large): scan every transformer block, sweep strengths, and render labeled comparison grids.
• **Akatz-Loop-Nodes**
• **ComfyUI MiniMax H3 Flow Director** - long videos block-by-block with automated keyframe flow chaining and low, constant VRAM usage.
• **ComfyUI_kkTranslator_nodes**
• **Comfyui-PixNodes**
• **SDXLCustomAspectRatio** - friendly aspect ratios.
• **Felsir-image-tools**
• **🗂️ Prompt Manager**
• **ComfyUI-SenseNova-U1** - U1 custom nodes for ComfyUI (API + local inference).
• **Muse Minimax Director (Seed Hunt)** - based director node for MiniMax H3 — visual CUT/segment editor, multi-character reference images, reference video + reference audio (with per-clip audio pairing for lipsync/voice reference), First/Last Frame mode, automatic chunking with a hybrid hard-lock continuation option, and a Seed Hunt toggle that scouts 4 candidate seeds in one run for use with Muse Minimax Refine's second-pass upscale.