Node glossary
ComfyUI Custom Nodes
62,141 custom nodes across 8,268 extensions — their inputs, outputs, and categories.
- Audio Cleaner
- Index TTS 2.5 - Base (多语言/语速)
- Index TTS 2.5 - Cache Control
- Index TTS 2.5 - Emotion Audio
- Index TTS 2.5 - Emotion Text
- Index TTS 2.5 - Emotion Vector
- Index TTS 2.5 - Extract Voice
- Index TTS 2.5 - Load Voice
- Index TTS 2.5 - Save Voice
- Index TTS 2.5 - Voice Base
- Index TTS 2 - Base
- Index TTS 2 - Cache Control
- Index TTS 2 - Emotion Audio
- Index TTS 2 - Emotion Text
- Index TTS 2 - Emotion Vector
- Index TTS 2 Pro (小说多角色)
- Index TTS
- Index TTS Pro
- 小说文本结构化
- Timbre音频加载器
- Zhenzhen API Settings (Legacy)
- zhenzhen-bernini-r-edit-image-fal
- zhenzhen-bernini-r-video-fal
- zhenzhen-boogu-image-fal
- zhenzhen-bria-fibo-edit-fal
- zhenzhen-bria-genfill-v2-fal
- zhenzhen-bria-video-background-removal-v3-fal
- Zhenzhen ChatGPT Api
- Concurrent Submit | zhenzhen-bernini-r-edit-image-fal
- Concurrent Submit | zhenzhen-bernini-r-video-fal
- Concurrent Submit | zhenzhen-boogu-image-fal
- Concurrent Submit | zhenzhen-bria-fibo-edit-fal
- Concurrent Submit | zhenzhen-bria-genfill-v2-fal
- Concurrent Submit | zhenzhen-bria-video-background-removal-v3-fal
- Concurrent Submit | Zhenzhen ChatGPT Api
- Concurrent Submit | zhenzhen-cosmos-3-super-fal
- Concurrent Submit | zhenzhen-creatify-aurora-fal
- Concurrent Submit | Zhenzhen Doubao Seedance 2.0
- Concurrent Submit | Zhenzhen Doubao Seededit3.0
- Concurrent Submit | Zhenzhen Doubao Seedream4.5
- Concurrent Submit | Zhenzhen Doubao Seedream4.0
- Concurrent Submit | Zhenzhen Doubao Seedream3.0
- Concurrent Submit | zhenzhen-FlashVSR-video-upscale-lowprice
- Concurrent Submit | Zhenzhen_Flux_2_Flex
- Concurrent Submit | zhenzhen_Flux_2_Max
- Concurrent Submit | Zhenzhen_Flux_2_Pro
- Concurrent Submit | zhenzhen-flux-3-video-lowprice
- Concurrent Submit | Zhenzhen_Flux_Kontext_bfl
- Concurrent Submit | Zhenzhen_Flux_Kontext_Edit
- Concurrent Submit | Zhenzhen_Flux_Kontext
- Add To Playlist (mtb)
- Animation Builder (mtb)
- Any To String (mtb)
- Apply Text Template (mtb)
- Apply Vit Matte (mtb)
- Audio Cut (mtb)
- Audio Duration (mtb)
- Audio Isolate Speaker (mtb)
- Audio Resample (mtb)
- Audio Sequence (mtb)
- Audio Stack (mtb)
- Audio To Text (mtb)
- Auto Pan Equilateral (mtb)
- Batch2d Transform (mtb)
- Batch Float Assemble (mtb)
- Batch Float Fill (mtb)
- Batch Float Fit (mtb)
- Batch Float Math (mtb)
- Batch Float (mtb)
- Batch Float Normalize (mtb)
- Batch From Folder (mtb)
- Batch Make (mtb)
- Batch Merge (mtb)
- Batch Sequence (mtb)
- Batch Sequence Plus (mtb)
- Batch Shake (mtb)
- Batch Shape (mtb)
- Batch Time Wrap (mtb)
- BBox Force Dimensions (mtb)
- Bbox From Mask (mtb)
- BeatImpactAnalysisNode
- Beat-Aligned Scene Durations
- 🎨 Color Match To Reference
- 🎞️ Fast Film Grain
- 🌀 Fast Laplacian Sharpen
- 📏 Fast Sobel Sharpen
- 🎯 Fast Unsharp Sharpen
- H3 VAE Decode Fast (Batched Tiles)
- Image From Folder (Index)
- Image From Folder (Index For Remake Mode)
- 🎞️ Match Grain To Reference
- SRTLyricsMerger
- VRGDG_ArchiveLlmBatchFolders
- ✂️ VRGDG Audio Crop
- VRGDG_AudioCropTime
- VRGDG_AudioDelayByIndex
- VRGDG_BoxIT
- VRGDG Build Video Output Path (General)
- VRGDG Build Video Output Path (General_SRT)
- 🎧 VRGDG_CalculateSetsFromAudio
- VRGDG_CalculateSetsFromAudio_Queue
- VRGDG ChatGPT Images Browser
- VRGDG_CleanAudio
- VRGDG Clear Memory Button
- 🌀 VRGDG_CombinevideosV2
- 🎬 VRGDG Combine Videos V3
- VRGDG_CombinevideosV5
- 🎞️ VRGDG_ConditionalLoadVideos
- VRGDG_CreateFinalVideo
- VRGDG_CreateFinalVideo_SRT
- LayerMask: BBox Join(Advance)
- LayerMask: Ben Ultra(Advance)
- LayerMask: BiRefNetUltra(Advance)
- LayerMask: BiRefNet Ultra V2(Advance)
- LayerMask: Draw BBox Mask(Advance)
- LayerMask: Draw BBox Mask V2(Advance)
- LayerMask: EVF-SAM Ultra(Advance)
- LayerMask: Florence2 Ultra(Advance)
- LayerMask: Human Parts Ultra(Advance)
- LayerMask: Load Ben Model(Advance)
- LayerMask: Load BiRefNet Model(Advance)
- LayerMask: Load BiRefNet Model V2(Advance)
- LayerMask: Load Florence2 Model(Advance)
- LayerMask: Load SAM2 Model(Advance)
- LayerMask: Load SegmentAnything Models(Advance)
- LayerMask: MaskByDifferent(Advance)
- LayerMask: Mediapipe Facial Segment(Advance)
- LayerMask: Object Detector Florence2(Advance)
- LayerMask: Object Detector Gemini(Advance)
- LayerMask: Object Detector Gemini V2(Advance)
- LayerMask: Object Detector Mask(Advance)
- LayerMask: Object Detector YOLO8(Advance)
- LayerMask: Object Detector YOLO World(Obsolete)
- LayerMask: PersonMaskUltra(Advance)
- LayerMask: PersonMaskUltra V2(Advance)
- LayerMask: SAM2 Ultra(Advance)
- LayerMask: SAM2 Ultra V2(Advance)
- LayerMask: SAM2 Video Ultra(Advance)
- LayerMask: SegmentAnythingUltra(Advance)
- LayerMask: SegmentAnythingUltra V2(Advance)
- MiniMax H3 Easy
- MiniMax H3 Easy Aspect Ratio
- MiniMax H3 Easy Context Segments
- MiniMax H3 Easy 3D Latent Upscale (Built-in)
- MiniMax H3 Easy Loader
- MiniMax H3 Easy Media Bridge
- MiniMax H3 Easy Media Loader
- MiniMax H3 Easy Media Splitter
- MiniMax H3 Easy Model Adapter
- MiniMax H3 Easy Output
- MiniMax H3 Easy Sample
- MiniMax H3 Easy Second Pass Conditioning
- MiniMax H3 Easy Segment Collect
- MiniMax H3 Easy Segment Decode
- MiniMax H3 Easy Segment Refine
- MiniMax H3 Easy Segment Sample
- MiniMax H3 Easy Sample Setup
- MiniMax H3 Easy Segment Step
- MiniMax H3 Easy Selected Video Context
- MiniMax H3 Easy SelfLift
- (Down)Load CLIPModel
- (Down)Load CLIPVisionModel
- (Down)Load DynamiCrafter CNModel
- (Down)Load DynamiCrafterModel
- DynamiCrafter BatchInterpolation
- DynamiCrafter CNLoader
- DynamiCrafter ControlnetApply
- DynamiCrafterI2V
- DynamiCrafter LoadInitNoise
- DynamiCrafter ModelLoader
- ToonCrafter Decode
- ToonCrafter Interpolation
- Apply Mask to Image
- Apply Reference Images
- Regions Attention Mask
- Background Region
- Apply ControlNet (tooling-nodes)
- Load ControlNet (tooling-nodes)
- Define Region
- Extract Image Tile
- Extract Mask Tile
- Generate Tile Mask
- Krita Canvas
- Krita Image Layer
- Krita Mask Layer
- Krita Output
- Krita Selection
- Send Text
- Krita Style
- Krita Style & Prompt
- List Region Masks
- Load Image (Base64)
- Load Image from Cache
- Load Mask (Base64)
- Merge Image Tile
- NSFW Filter
- Parameter
- Reference Image
- Save Image to Cache
- Send Image (WebSocket)
- Create Tile Layout
- Translate Text
- Spectrum Apply MiniMax H3
- Spectrum H3 Objective Media Capture Reset
- Spectrum H3 Objective Media Stage (One-Shot / Full Media)
- Spectrum H3 Objective Quality Compare (One-Shot / Full Media)
- Spectrum H3 Objective Media Capture (Sequential - Bounded)
- Spectrum H3 Objective Quality Compare (Staged One-Shot / Full Media)
- FL Animated Shape Patterns
- FL Anime Line Extractor
- FL API Base64 Image Loader
- FL API Image Saver
- FL Apply Mask
- FL Ascii
- FL Audio Beat Prompt Envelope
- FL Audio Beat Prompt Schedule
- FL Audio Beat Visualizer
- FL Audio BPM Analyzer
- FL Audio Crop
- FL Audio Drum Detector
- FL Audio Envelope Prompt
- FL Audio Envelope Visualizer
- FL Audio Frame Calculator
- FL Audio Music Video Sequencer
- FL Audio Reactive Brightness
- FL Audio Reactive Edge Glow
- FL Audio Reactive Envelope
- FL Audio Reactive Saturation
- FL Audio Reactive Scale
- FL Audio Reactive Speed
- FL Audio Segment Extractor
- FL Audio Separation
- FL Audio Shot Iterator
- FL Batch Align
- FL Black Frame Reject
- FL Bulk PDF Loader
- FL BulletHell Game
- FL Caption Saver V2
- CXH_DownloadAndLoadFlorence2Model
- CXH_Florence2Run
- CXH_HG_Model_Load
- CXH_IC_Lora_Florence2Run
- CXH_Ic_lora_Joy_batch
- CXH_IC_lora_reversal
- CXH_Min2_6_classifiy
- CXH_Min2_6_prompt_Run
- CXH_MinCP3_4B_Chat
- CXH_MinCP3_4B_Load
- CXH_SmolVlm_Load
- CXH_SmolVlm_Run
- Joy_caption
- Joy_caption_alpha_batch
- Joy_caption_alpha_batch_Dirs
- Joy_caption_alpha_load
- Joy_caption_alpha_prompt
- Joy_caption_alpha_run
- Joy_caption_load
- advanced xyPlot
- advPlot combo
- advPlot images
- advPlot merge
- advPlot range
- advPlot string
- textConcat
- tinyConditioning
- debugInput
- float
- hiresfixScale
- imageOutput
- imageRemBG
- int
- tinyKSampler
- multiModelMerge
- pipe > basic_pipe
- pipe > detailer_pipe
- pipeEDIT
- pipeEncodeConcat
- pipeIN (Legacy)
- pipeKSampler v1 (Legacy)
- pipeKSamplerAdvanced v1 (Legacy)
- pipeKSamplerAdvanced
- pipeKSamplerSDXL v1 (Legacy)
- pipeKSamplerSDXL
- pipeKSampler
- pipeLoader v1 (Legacy)
- pipeLoaderSDXL v1 (Legacy)
- pipeLoaderSDXL
- advanced xyPlot
- advPlot combo
- advPlot images
- advPlot merge
- advPlot range
- advPlot string
- textConcat
- tinyConditioning
- debugInput
- float
- hiresfixScale
- imageOutput
- imageRemBG
- int
- tinyKSampler
- multiModelMerge
- pipe > basic_pipe
- pipe > detailer_pipe
- pipeEDIT
- pipeEncodeConcat
- pipeIN (Legacy)
- pipeKSampler v1 (Legacy)
- pipeKSamplerAdvanced v1 (Legacy)
- pipeKSamplerAdvanced
- pipeKSamplerSDXL v1 (Legacy)
- pipeKSamplerSDXL
- pipeKSampler
- pipeLoader v1 (Legacy)
- pipeLoaderSDXL v1 (Legacy)
- pipeLoaderSDXL
- FLUX.2 Klein Color Anchor
- FLUX.2 Klein Detail Controller
- FLUX.2 Klein Enhancer
- Flux2Klein KSampler Experimental
- FLUX.2 Klein Mask Ref Controller
- Multi ReferenceLatent
- FLUX.2 Klein Ref Latent Controller
- FLUX.2 Klein Ref Latent Weight
- FLUX.2 Klein Sectioned Encoder
- FLUX.2 Klein Text Enhancer
- FLUX.2 Klein Text/Ref Balance
- FLUX.2 Klein Identity Feature Transfer
- FLUX.2 Klein Identity Feature Transfer Advanced
- Identity Feature Transfer Final
- FLUX.2 Klein Identity Feature Transfer V3
- FLUX.2 Klein Identity Guidance
- AudioLDM2
- Chat Musician
- Creative Art Prompt Generator
- Florence-2 Multitask Vision
- Hosted VLM API (Secure)
- JoyTag
- JSON to Text
- Structured Keyword Extraction
- Kosmos-2
- [Legacy] Modern VLM Compatibility
- LLaVA Vision Projector Loader
- LLaVA Loader
- LLaVA (Managed Cache, Advanced)
- LLaVA (Managed Cache)
- Structured Prompt Generator
- LLaVA Sampler (Advanced)
- LLaVA Sampler
- LLM Loader (GGUF)
- LLM (Managed Cache, Advanced)
- LLM (Managed Cache)
- LLM Prompt Generator
- LLM Sampler
- MC-LLaVA
- MiniCPM-V 2.6 (GGUF)
- MiniMax Music
- Modern VLM (Qwen / SmolVLM2 / LFM / InternVL / Granite / Gemma)
- Molmo Vision-Language Model
- MoonDream (Moondream 2)
- Moondream 2
- Moondream 3 / 3.1 Caption
- MinusZone - ApplyCUDAGenerator
- MinusZone - ApplySDXLSamplingSettings
- MinusZone - ChatGLM3TextEncode
- MinusZone - ChatGLM3TextEncodeAdvanceV2
- MinusZone - ChatGLM3Embeds2Conditioning
- MinusZone - ChatGLM3Loader
- MinusZone - ChatGLM3TextEncodeV2
- IPAdapterAdvanced(kolors) - Legacy
- IPAdapterFaceID(kolors) - Legacy
- IPAdapterInsightFaceLoader(kolors) - Legacy
- IPAdapterModelLoader(kolors) - Legacy
- MinusZone - KolorsCheckpointLoaderSimple
- MinusZone - KolorsCLIPVisionLoader - Legacy
- MinusZone - KolorsControlNetLoader
- MinusZone - KolorsControlNetPatch
- MinusZone - Kolors UNET Loader
- MinusZone - KolorsUNETLoaderV2
- (Down)Load SAM3 Model
- SAM3 BBox Collector
- SAM3 Combine Boxes
- SAM3 Combine Points
- SAM3 Create Box
- SAM3 Create Point
- SAM3 Text Segmentation
- SAM3 Interactive Collector
- SAM3 Multiprompt Segmentation
- SAM3 Multi-Region Collector
- SAM3 Point Collector
- SAM3 Propagate
- SAM3 Point Segmentation
- SAM3 Video Output
- SAM3 Video Segmentation