云端节点目录

在云端运行你喜爱的 ComfyUI 自定义节点

在 Comfy Cloud 托管 GPU 上即开即用，预装数百个社区节点——细节修复、ControlNet 预处理、动画工具与日常便利组件，应有尽有。

云端节点目录

查找自定义节点包

ComfyUI-KJNodes

Various quality of life -nodes for ComfyUI, mostly just visual stuff to improve usability.

查看仓库•187 个节点

包含节点

_for_testing

Differential Diffusion Advanced

advanced/guidance

Skip Layer Guidance WanVideo

conditioning/controlnet

Set Shakker Labs Union ControlNet Type

image

Image Pad For Outpaint Masked
Image Pad For Outpaint Target Size
Image Prep For ICLora

KJNodes/audio

ImageTransformByNormalizedAmplitude
NormalizedAmplitudeToFloatList
NormalizedAmplitudeToMask
OffsetMaskByNormalizedAmplitude
Sound Reactive

KJNodes/constants

BOOL Constant
Float Constant
INT Constant
String Constant
String Constant Multiline

KJNodes/controlnet

Custom ControlNet Weights Flux From List

KJNodes/deprecated

Create Audio Mask
Create Fade Mask
Patch Model Patcher Order
TorchCompileCosmosModel
TorchCompileLTXModel
TorchCompileModelFluxAdvanced
TorchCompileModelHyVideo
TorchCompileModelQwenImage
TorchCompileModelWanVideo
WanVideo Tea Cache (native)

KJNodes/experimental

CFG Zero Star/Init
CheckpointPerturbWeights
Fast Preview
Flux Block Lora Select
GLIGENTextBoxApplyBatchCoords
Interpolate Coords
Latent Inpaint TTM
Model Patch Torch Settings
NABLA Attention KJ
Patch Flash Attention KJ
Patch Sage Attention KJ
PiD Color Bias Correction
Plot Coordinates
Points Editor
Scheduled CFG Guidance
Stable Zero123 Batch Schedule
Style Model Apply Advanced
SV3D Batch Schedule

KJNodes/hunyuanvideo

Apply RifleXRoPE HunuyanVideo
Hunyuan Video Block Lora Select
HunyuanVideo Encode Keyframes To Cond
Leapfusion Hunyuan I2V Patcher

KJNodes/image

Color Match
Create Gradient From Coords
Create Shape Image On Path
Cross Fade Images
Cross Fade Images Multi
Cut And Drag On Path
Get Image or Mask Range From Batch
Get Image Size & Count
Get Images From Batch Indexed
Get Latent Size & Count
Gradient To Float
Image Add Multi
Image Batch Extend With Overlap
Image Batch Filter
Image Batch Join With Transition
Image Batch Multi
Image Concatenate From Batch
Image Crop By Mask
Image Crop By Mask And Resize
Image Crop By Mask Batch
Image Grab PIL
Image Grid Composite 2x2
Image Grid Composite 3x3
Image Grid To Batch
Image Normalize -1 to 1
Image Tensor List
Image Uncrop By Mask
Image Upscale With Model Batched
ImageBatchRepeatInterleaving
ImagePad KJ
ImagePass
Insert Image Batch By Indexes
Insert Images To Batch Indexed
Load & Resize Image
Merge Image Channels
Pad Image Batch Interleaved
Preview Animation
Remap Image Range
Replace Images In Batch
Resize Image (deprecated)
Resize Image v2
Reverse Image Batch
Save Image With Alpha
Screencap mss
Shuffle Image Batch
Split Image Channels
Transition Images In Batch
Transition Images Multi

KJNodes/InstanceDiffusion

AppendInstanceDiffusionTracking
CreateInstanceDiffusionTracking
DrawInstanceDiffusionTracking

KJNodes/latents

Empty Latent Image Custom Presets
Empty Latent Image Presets
Get Latent Range From Batch
Get Latents From Batch Indexed
Insert Latent To Index

KJNodes/lora

DiT Block Lora Loader

KJNodes/ltxv

LTX2 Block Lora Select
LTXV Enhance A Video KJ

KJNodes/masking

(Down)load CLIPSeg
Batch CLIPSeg
Batch Crop From Mask
Batch Crop From Mask Advanced
Batch Uncrop
Batch Uncrop Advanced
Bbox To Int
Bbox Visualize
Blockify Mask
Color To Mask
Consolidate Masks
Draw Mask On Image
FilterZeroMasksAndCorrespondingImages
Get Mask Size & Count
Grow Mask With Blur
Mask Batch Multi
Offset Mask
Remap Mask Range
Resize Mask
Round Mask
Separate Masks
Split Bboxes

KJNodes/masking/conditioning

Conditioning Multi Combine
ConditioningSetMaskAndCombine
ConditioningSetMaskAndCombine3
ConditioningSetMaskAndCombine4
ConditioningSetMaskAndCombine5

KJNodes/masking/generate

Create Fade Mask Advanced
Create Fluid Mask
Create Gradient Mask
Create Magic Mask
Create Shape Mask
Create Shape Mask On Path
Create Text On Path
Create Voronoi Mask
Float To Mask

KJNodes/memory

Model Memory Usage Factor Override
Model Memory Use Report Patch
VRAM Debug

KJNodes/misc

CondPassThrough
Dummy Out
Lazy Switch KJ
ModelPass
Scale Batch Prompt Schedule
Sleep
String to Float List
Timer Node KJ

KJNodes/model_loaders

CheckpointLoaderKJ
Diffusion Model Loader KJ
Diffusion Model Selector

KJNodes/noise

Custom Sigmas
Flip Sigmas Adjusted
Float To Sigmas
Generate Noise
Inject Noise To Latent
Sigmas To Float

KJNodes/text

Add Label
Append Strings To List
Create Text Mask
Join String Multi
Join Strings
Something To String
Superprompt
Widget To String

KJNodes/torchcompile

TorchCompileControlNet
TorchCompileModelAdvanced
TorchCompileModelFluxAdvancedV2
TorchCompileModelWanVideoV2
TorchCompileVAE

KJNodes/vae

VAE Decode Loop KJ
VAELoader KJ

KJNodes/wan

Apply RifleXRoPE WanVideo
Wan21 Block Lora Select
WanVideo Enhance A Video (native)
WanVideoNAG

KJNodes/weights

Mask Or Image To Weight
Spline Editor
Weight Schedule Convert
Weight Schedule Extend

ComfyUI-VideoHelperSuite

Nodes related to video workflows

查看仓库•32 个节点

包含节点

Video Helper Suite 🎥🅥🅗🅢

Load Video (Upload) 🎥🅥🅗🅢
Load Video FFmpeg (Upload) 🎥🅥🅗🅢
Prune Outputs 🎥🅥🅗🅢
Select Latest 🎥🅥🅗🅢
Unbatch 🎥🅥🅗🅢
Video Combine 🎥🅥🅗🅢
Video Info (Loaded) 🎥🅥🅗🅢
Video Info (Source) 🎥🅥🅗🅢
Video Info 🎥🅥🅗🅢

Video Helper Suite 🎥🅥🅗🅢/audio

Audio to legacy VHS_AUDIO🎥🅥🅗🅢
Legacy VHS_AUDIO to Audio🎥🅥🅗🅢
Load Audio (Upload)🎥🅥🅗🅢

Video Helper Suite 🎥🅥🅗🅢/batched nodes

VAE Decode Batched 🎥🅥🅗🅢
VAE Encode Batched 🎥🅥🅗🅢

Video Helper Suite 🎥🅥🅗🅢/image

Get Image Count 🎥🅥🅗🅢
Merge Images 🎥🅥🅗🅢
Repeat Images 🎥🅥🅗🅢
Select Every Nth Image 🎥🅥🅗🅢
Select Images 🎥🅥🅗🅢
Split Images 🎥🅥🅗🅢

Video Helper Suite 🎥🅥🅗🅢/latent

Get Latent Count 🎥🅥🅗🅢
Merge Latents 🎥🅥🅗🅢
Repeat Latents 🎥🅥🅗🅢
Select Every Nth Latent 🎥🅥🅗🅢
Select Latents 🎥🅥🅗🅢
Split Latents 🎥🅥🅗🅢

Video Helper Suite 🎥🅥🅗🅢/mask

Get Mask Count 🎥🅥🅗🅢
Merge Masks 🎥🅥🅗🅢
Repeat Masks 🎥🅥🅗🅢
Select Every Nth Mask 🎥🅥🅗🅢
Select Masks 🎥🅥🅗🅢
Split Masks 🎥🅥🅗🅢

ComfyUI Impact Pack

This node pack offers various detector nodes and detailer nodes that allow you to configure a workflow that automatically enhances facial details. And provide iterative upscaler.

查看仓库•185 个节点

包含节点

ImpactPack

ONNXDetectorProvider
SAMLoader (Impact)

ImpactPack/__for_testing

Make Tile SEGS

ImpactPack/Debug

ImpactDummyInput
ImpactLogger

ImpactPack/Detailer

CoreMLDetailerHookProvider
CustomSamplerDetailerHookProvider
DenoiseSchedulerDetailerHookProvider
Detailer (SEGS)
Detailer (SEGS) with auto retry
Detailer (SEGS/pipe)
Detailer For Video (SEGS/pipe)
DetailerDebug (SEGS)
DetailerDebug (SEGS/pipe)
MaskDetailer (pipe)
NoiseInjectionDetailerHookProvider
SEGSDetailer
SEGSDetailer For Video (SEGS/pipe)
SEGSPaste
UnsamplerDetailerHookProvider
VariationNoiseDetailerHookProvider

ImpactPack/Detector

BBOX Detector (combined)
BBOX Detector (SEGS)
ONNX Detector (SEGS/legacy) - use BBOXDetector
SAM2 Video Detector (SEGS)
SAMDetector (combined)
SAMDetector (segmented)
SEGM Detector (combined)
SEGM Detector (SEGS)
Simple Detector (SEGS)
Simple Detector (SEGS/pipe)
Simple Detector for Video (SEGS)

ImpactPack/HuggingFace

HF Transformers Classifier Provider
SEGS Classify

ImpactPack/Logic

Control Bridge
ImpactBoolean
ImpactCompare
ImpactConditionalBranch
ImpactConditionalBranchSelMode
ImpactConditionalStopIteration
ImpactConvertDataType
ImpactFloat
ImpactIfNone
ImpactInt
ImpactLogicalOperators
ImpactNeg
ImpactValueSender
SEGS isn't Empty

ImpactPack/Logic/_for_test

ImpactImageInfo
ImpactLatentInfo
ImpactMinMax
Remote Boolean (on prompt)
Remote Int (on prompt)
Set Mute State
Sleep

ImpactPack/Operation

Flatten Mask Batch
Image List to Image Batch
Mask Batch to Mask List
Mask List to Mask Batch
MASK to SEGS
MASK to SEGS for Video
MediaPipe FaceMesh to SEGS
Pixelwise(MASK - MASK)
Pixelwise(MASK & MASK)
Pixelwise(MASK + MASK)
Pixelwise(SEGS - SEGS)
Pixelwise(SEGS & MASK)
Pixelwise(SEGS & MASKS ForEach)
Pixelwise(SEGS & SEGS)
SEGS to MASK (combined)
ToBinaryMask

ImpactPack/Pipe

Any PIPE -> BasicPipe
BasicPipe -> DetailerPipe
BasicPipe -> DetailerPipe (SDXL)
DetailerPipe -> BasicPipe
Edit BasicPipe
Edit DetailerPipe
Edit DetailerPipe (SDXL)
FromBasicPipe
FromBasicPipe_v2
FromDetailer (SDXL/pipe)
FromDetailerPipe
FromDetailerPipe_v2
ToBasicPipe
ToDetailerPipe
ToDetailerPipeSDXL

ImpactPack/Prompt

ImpactWildcardEncode
ImpactWildcardProcessor

ImpactPack/Regional

CombineRegionalPrompts
RegionalPrompt
RegionalSampler
RegionalSamplerAdvanced

ImpactPack/Sampler

KSamplerAdvancedProvider
KSamplerProvider
TiledKSamplerProvider
TwoAdvancedSamplersForMask
TwoSamplersForMask

ImpactPack/sampling

GITSScheduler Func Provider
KSampler (Advanced/pipe)
KSampler (pipe)
Negative Cond Placeholder

ImpactPack/Simple

FaceDetailer
FaceDetailer (pipe)

ImpactPack/Upscale

CfgScheduleHookProvider
DenoiseScheduleHookProvider
DetailerHookCombine
Iterative Upscale (Image)
Iterative Upscale (Latent/on Pixel Space)
Latent Scale (on Pixel Space)
NoiseInjectionHookProvider
PixelKSampleHookCombine
PixelKSampleUpscalerProvider
PixelKSampleUpscalerProviderPipe
PixelTiledKSampleUpscalerProvider
PixelTiledKSampleUpscalerProviderPipe
StepsScheduleHookProvider
TwoSamplersForMask Upscaler Provider
TwoSamplersForMask Upscaler Provider (pipe)
UnsamplerHookProvider
Upscaler (SEGS)
Upscaler (SEGS/pipe)

ImpactPack/Util

Assemble (SEGS)
BlackPatchRetryHookProvider
CLIPSegDetectorProvider
Combine Conditionings
Concat Conditionings
ControlNetApply (SEGS)
ControlNetApply (SEGS) - DEPRECATED
Count Elts in SEGS
Decompose (SEGS)
Dilate Mask
Dilate Mask (SEG_ELT)
Dilate Mask (SEGS)
Edit SEG_ELT
EmptySegs
Execution Order Controller
From SEG_ELT
From SEG_ELT bbox
From SEG_ELT crop_region
Gaussian Blur Mask
Gaussian Blur Mask (SEGS)
Image Batch to Image List
Impact Scheduler Adapter
ImpactControlNetClearSEGS
Inversed Switch (Any)
IPAdapterApply (SEGS)
LamaRemoverDetailerHookProvider
LatentSender
List Bridge
Make Image Batch
Make Image List
Make List (Any)
Make Mask Batch
Make Mask List
PreviewDetailerHookProvider
Reencode Latent
Reencode Latent (pipe)
Remove Image from SEGS
Remove Noise Mask
ScaleBy BBOX (SEG_ELT)
SEGS Assign (label)
SEGS Concat
SEGS Filter (intersection)
SEGS Filter (label)
SEGS Filter (non max suppression)
SEGS Filter (ordered)
SEGS Filter (range)
SEGS Merge
SEGS to Mask Batch
SEGS to Mask List
SEGSLabelFilterDetailerHookProvider
SEGSOrderedFilterDetailerHookProvider
SEGSPreview
SEGSPreview (CNET Image)
SEGSRangeFilterDetailerHookProvider
SEGSToImageList
Select Nth Item (Any list)
Set Default Image for SEGS
String List to String
String Selector
Switch (Any)
Switch (images, mask)
Switch (latent/legacy)
Switch (SEGS/legacy)
Wildcard Prompt from String

ComfyUI_essentials

Essential nodes that are weirdly missing from ComfyUI core. With few exceptions they are new features and not commodities.

查看仓库•60 个节点

包含节点

essentials/conditioning

🔧 Cond Combine Multiple
🔧 SD3 Negative Conditioning
🔧 SDXL CLIPTextEncode

essentials/image analysis

🔧 Image Enhance Difference

essentials/image batch

🔧 Image Expand Batch
🔧 Image From Batch
🔧 Image List To Batch
🔧 Images Batch Multiple

essentials/image manipulation

🔧 Image Composite
🔧 Image Composite From Mask Batch
🔧 Image Crop
🔧 Image Flip
🔧 Image Random Transform
🔧 Image Remove Background
🔧 Image Resize
🔧 Image Seam Carving
🔧 Image Tile
🔧 Image Untile
🔧 InSPyReNet TransparentBG
🔧 RemBG Session

essentials/image processing

🔧 Image Apply LUT
🔧 Image Color Match
🔧 Image Color Match Adobe
🔧 Image Contrast Adaptive Sharpening
🔧 Image Desaturate
🔧 Image Histogram Match
🔧 Image Posterize
🔧 Pixelize

essentials/image utils

🔧 Get Image Size
🔧 Image Remove Alpha
🔧 Image To Device
🔧 Noise From Image

essentials/mask

🔧 Mask Blur
🔧 Mask Bounding Box
🔧 Mask Fix
🔧 Mask Flip
🔧 Mask From Color
🔧 Mask From List
🔧 Mask From RGB/CMY/BW
🔧 Mask From Segmentation
🔧 Mask Smooth
🔧 Transition Mask

essentials/mask batch

🔧 Mask Batch
🔧 Mask Expand Batch
🔧 Mask From Batch

essentials/sampling

🔧 Flux Sampler Parameters
🔧 Inject Latent Noise
🔧 KSampler Stochastic Variations
🔧 KSampler Variations with Noise Injection
🔧 Plot Sampler Parameters

essentials/segmentation

🔧 Apply CLIPSeg
🔧 Load CLIPSeg Models

essentials/text

🔧 Draw Text

essentials/utilities

🔧 Batch Count
🔧 Console Debug
🔧 Debug Tensor Shape
🔧 Model Compile
🔧 Remove Latent Mask
🔧 SDXL Empty Latent Size Picker
🔧 Simple Math

comfyui_controlnet_aux

Plug-and-play ComfyUI node sets for making ControlNet hint images

查看仓库•64 个节点

包含节点

ControlNet Preprocessors

AIO Aux Preprocessor
ControlNetAuxSimpleAddText
Enchance And Resize Hint Images
Execute All ControlNet Preprocessors
Generation Resolution From Image
Generation Resolution From Latent
Pixel Perfect Resolution
Preprocessor Selector

ControlNet Preprocessors/Faces and Poses Estimators

AnimalPose Estimator (AP10K)
DensePose Estimator
DWPose Estimator
MediaPipe Face Mesh
OpenPose Pose

ControlNet Preprocessors/Line Extractors

Anime Lineart
AnyLine Lineart
Binary Lines
Canny Edge
Diffusion Edge (batch size ↑ => speed ↑, VRAM ↑)
Fake Scribble Lines (aka scribble_hed)
HED Soft-Edge Lines
M-LSD Lines
Manga Lineart (aka lineart_anime_denoise)
PiDiNet Soft-Edge Lines
PyraCanny
Realistic Lineart
Scribble Lines
Scribble PiDiNet Lines
Scribble XDoG Lines
Standard Lineart
TEEDPreprocessor

ControlNet Preprocessors/Normal and Depth Estimators

BAE Normal Map
Depth Anything
Depth Anything V2 - Relative
DSINE Normal Map
LeReS Depth Map (enable boost for leres++)
MeshGraphormer Hand Refiner
MeshGraphormer Hand Refiner With External Detector
Metric3D Depth Map
Metric3D Normal Map
MiDaS Depth Map
MiDaS Normal Map
Zoe Depth Anything
Zoe Depth Map

ControlNet Preprocessors/Optical Flow

Mask Optical Flow (DragNUWA)
Unimatch Optical Flow

ControlNet Preprocessors/others

Inpaint Preprocessor
SAM Segmentor

ControlNet Preprocessors/Pose Keypoint Postprocess

Colorize Facial Parts from PoseKPS
Render Pose JSON (Animal)
Render Pose JSON (Human)
Save Pose Keypoints
Upper Body Tracking From PoseKps (InstanceDiffusion)

ControlNet Preprocessors/Recolor

Image Intensity
Image Luminance

ControlNet Preprocessors/Semantic Segmentation

Anime Face Segmentor
OneFormer ADE20K Segmentor
OneFormer COCO Segmentor
Semantic Segmentor (legacy, alias for UniFormer)
UniFormer Segmentor

ControlNet Preprocessors/T2IAdapter-only

Color Pallete
Content Shuffle

ControlNet Preprocessors/tile

Tile
TTPlanet Tile GuidedFilter
TTPlanet Tile Simple

ComfyUI Impact Subpack

This node pack provides nodes that complement the Impact Pack, such as the UltralyticsDetectorProvider.

查看仓库•1 个节点

包含节点

ImpactPack

UltralyticsDetectorProvider

ComfyUI_LayerStyle

A set of nodes for ComfyUI it generate image like Adobe Photoshop's Layer Style. the Drop Shadow is first completed node, and follow-up work is in progress.

查看仓库•161 个节点

包含节点

😺dzNodes/LayerColor

LayerColor: AutoAdjust
LayerColor: AutoAdjust V2
LayerColor: AutoBrightness
LayerColor: Brightness & Contrast
LayerColor: Brightness Contrast V2
LayerColor: Color of Shadow & Highlight
LayerColor: ColorAdapter
LayerColor: ColorBalance
LayerColor: Colorof Shadow Highlight V2
LayerColor: ColorTemperature
LayerColor: Exposure
LayerColor: Gamma
LayerColor: HSV
LayerColor: LAB
LayerColor: Levels
LayerColor: LUT Apply
LayerColor: Negative
LayerColor: RGB
LayerColor: YUV
LayerUtility: Color Name
LayerUtility: Name To Color

😺dzNodes/LayerFilter

LayerFilter: Add Grain
LayerFilter: ChannelShake
LayerFilter: ColorMap
LayerFilter: Distort Displace
LayerFilter: Film
LayerFilter: Film V2
LayerFilter: Gaussian Blur V2
LayerFilter: GaussianBlur
LayerFilter: HalfTone
LayerFilter: HDR Effects
LayerFilter: MotionBlur
LayerFilter: Sharp & Soft
LayerFilter: SkinBeauty
LayerFilter: SoftLight
LayerFilter: WaterColor

😺dzNodes/LayerMask

LayerMask: BlendIf Mask
LayerMask: CreateGradientMask
LayerMask: DrawRoundedRectangle
LayerMask: Image To Mask
LayerMask: Load Segformer Model
LayerMask: Mask Box Detect
LayerMask: Mask Box Extend
LayerMask: Mask by Color
LayerMask: Mask Grain
LayerMask: MaskEdgeShrink
LayerMask: MaskEdgeUltraDetail
LayerMask: MaskEdgeUltraDetail V2
LayerMask: MaskEdgeUltraDetail V3
LayerMask: MaskGradient
LayerMask: MaskGrow
LayerMask: MaskInvert
LayerMask: MaskMotionBlur
LayerMask: MaskStroke
LayerMask: PixelSpread
LayerMask: Segformer B2 Clothes Ultra
LayerMask: Segformer Clothes Pipeline
LayerMask: Segformer Clothes Setting
LayerMask: Segformer Fashion Pipeline
LayerMask: Segformer Fashion Setting
LayerMask: Segformer Ultra V2
LayerMask: Segformer Ultra V3
LayerMask: Shadow & Highlight Mask
LayerMask: Shadow Highlight Mask V2

😺dzNodes/LayerStyle

LayerStyle: ColorOverlay
LayerStyle: ColorOverlay V2
LayerStyle: DropShadow
LayerStyle: DropShadow V2
LayerStyle: DropShadow V3
LayerStyle: Gradient Map
LayerStyle: GradientOverlay
LayerStyle: GradientOverlay V2
LayerStyle: InnerGlow
LayerStyle: InnerGlow V2
LayerStyle: InnerShadow
LayerStyle: InnerShadow V2
LayerStyle: OuterGlow
LayerStyle: OuterGlow V2
LayerStyle: Stroke
LayerStyle: Stroke V2

😺dzNodes/LayerUtility

LayerUtility: Check Mask
LayerUtility: Check Mask V2
LayerUtility: ColorImage
LayerUtility: ColorImage V2
LayerUtility: ColorPicker
LayerUtility: CropBoxResolve
LayerUtility: CropByMask
LayerUtility: CropByMask V2
LayerUtility: CropByMask V3
LayerUtility: ExtendCanvas
LayerUtility: ExtendCanvas V2
LayerUtility: Flux Kontext Image Scale
LayerUtility: Get Main Colors
LayerUtility: Get Main Colors V2
LayerUtility: GetImageSize
LayerUtility: GradientImage
LayerUtility: GradientImage V2
LayerUtility: H/L Frequency Detail Restore
LayerUtility: IC Mask
LayerUtility: IC Mask Crop Back
LayerUtility: Image Composite Handle Mask
LayerUtility: Image Mask Scale As
LayerUtility: Image Mask Scale As V2
LayerUtility: Image Reel
LayerUtility: Image Reel Composit
LayerUtility: ImageBlend
LayerUtility: ImageBlend V2
LayerUtility: ImageBlendAdvance
LayerUtility: ImageBlendAdvance V2
LayerUtility: ImageBlendAdvance V3
LayerUtility: ImageChannelMerge
LayerUtility: ImageChannelSplit
LayerUtility: ImageCombineAlpha
LayerUtility: ImageHub
LayerUtility: ImageOpacity
LayerUtility: ImageRemoveAlpha
LayerUtility: ImageScaleByAspectRatio
LayerUtility: ImageScaleByAspectRatio V2
LayerUtility: ImageScaleRestore
LayerUtility: ImageScaleRestore V2
LayerUtility: ImageShift
LayerUtility: LayerImageTransform
LayerUtility: LayerMaskTransform
LayerUtility: Load VQA Model
LayerUtility: Nano Banana Image Scale
LayerUtility: Pad Image Batch to 8n+1
LayerUtility: Restore Pad Image Batch
LayerUtility: RestoreCropBox
LayerUtility: RoundedRectangle
LayerUtility: SimpleTextImage
LayerUtility: TextImage
LayerUtility: TextImage V2
LayerUtility: VQA Prompt

😺dzNodes/LayerUtility/Data

LayerUtility: Any Rerouter
LayerUtility: Boolean
LayerUtility: Boolean Operator
LayerUtility: Boolean Operator V2
LayerUtility: Choice Text Preset
LayerUtility: Float
LayerUtility: Gray Value
LayerUtility: HSV Value
LayerUtility: If
LayerUtility: Image Batch To List(Multi)
LayerUtility: Image List To Batch(Multi)
LayerUtility: Integer
LayerUtility: Number Calculator
LayerUtility: Number Calculator V2
LayerUtility: PrintInfo
LayerUtility: Random Generator
LayerUtility: Random Generator V2
LayerUtility: RGB Value
LayerUtility: Seed
LayerUtility: String
LayerUtility: String Condition
LayerUtility: Switch Case
LayerUtility: Text Preseter
LayerUtility: TextBox
LayerUtility: TextJoin
LayerUtility: TextJoinV2
LayerUtility: XY to Percent

😺dzNodes/LayerUtility/SystemIO

LayerUtility: Batch Selector

ComfyUI-WanVideoWrapper

ComfyUI wrapper nodes for WanVideo

查看仓库•140 个节点

包含节点

ControlNet Preprocessors/Pose Keypoint Postprocess

Face Mask From Pose Keypoints

KJNodes/masking

Draw Gaussian Noise On Image

LivePortrait

Landmarks to Image

WanVideoWrapper

(Down)load Wav2Vec Model
Create CFG Schedule Float List
Create Schedule Float List
Draw ArcFace Landmarks
Draw NLF Poses
Dummy Comfy Wan Model Object
Extract Start Frames For Continuations
FantasyPortrait Face Detector
FantasyPortrait Model Loader
FantasyTalking Model Loader
FantasyTalking Wav2Vec Embeds
HuMo Embeds
Load Lynx Resampler
Load NLF Model
Load VQVAE
Lynx Encode Face IP
Lynx InsightFace Crop
Mocha Embeds
MTV Crafter Encode Poses
Multi/InfiniteTalk Model Loader
Multi/InfiniteTalk Wav2vec2 Embeds
MultiTalk Silent Embeds
NLF Predict
Normalize Audio Loudness
Qwen Loader
ReCamMaster Pose Visualizer
TextImageEncodeQwenVL
Wan Video Prompt Extender
Wan Video Prompt Extender Select
WanMove Native
WanVideo Add Bindweave Embeds
WanVideo Add Control Embeds
WanVideo Add Dual Control Embeds
WanVideo Add Extra Latent
WanVideo Add Fantasy Portrait
WanVideo Add FlashVSR Input
WanVideo Add LucyEdit Latents
WanVideo Add Lynx Embeds
WanVideo Add OneToAll Extend Embeds
WanVideo Add OneToAll Pose Embeds
WanVideo Add OneToAll Reference Embeds
WanVideo Add Pusa Noise
WanVideo Add S2V Embeds
WanVideo Add SCAIL Pose Embeds
WanVideo Add SCAIL Reference Embeds
WanVideo Add StandIn Latent
WanVideo Add SteadyDancer Embeds
WanVideo Add StoryMem Latents
WanVideo Add TTMLatents
WanVideo Add WanMove Tracks
WanVideo Animate Embeds
WanVideo Apply NAG
WanVideo ATI Comfy
WanVideo ATI Tracks
WanVideo ATI Tracks Visualize
WanVideo Block List
WanVideo CLIP Text Encoder Loader
WanVideo ClipVision Encode
WanVideo Combine Embeds
WanVideo Context Options
WanVideo Control Embeds
WanVideo Controlnet Apply
WanVideo Controlnet Loader
WanVideo Decode
WanVideo Diffusion Forcing Sampler
WanVideo Draw WanMove Tracks
WanVideo EasyCache
WanVideo Empty Embeds
WanVideo Encode
WanVideo Encode Latent Batch
WanVideo Enhance-A-Video
WanVideo Experimental Args
WanVideo Extra Model Select
WanVideo FlashVSR Decoder Loader
WanVideo Free Init Args
WanVideo FunCamera Embeds
WanVideo Image Resize To Closest
WanVideo ImageClip Encode (Deprecated)
WanVideo ImageToVideo Encode
WanVideo Latent ReScale
WanVideo Long I2V Multi/InfiniteTalk
WanVideo Long SkyReelsV3 A2V
WanVideo Loop Args
WanVideo Lora Block Edit
WanVideo Lora Select
WanVideo Lora Select Multi
WanVideo MagCache
WanVideo MiniMax Remover Embeds
WanVideo Model Loader
WanVideo MTV Crafter Motion
WanVideo Pass Images From Samples
WanVideo Phantom Embeds
WanVideo Preview Embeds
WanVideo RealisDance Latents
WanVideo ReCamMaster Camera Embed
WanVideo ReCamMaster Default Camera
WanVideo ReCamMaster Generate Orbit Camera
WanVideo RoPE Function
WanVideo Sampler
WanVideo Sampler From Settings
WanVideo Sampler Settings
WanVideo Sampler v2
WanVideo Scheduler
WanVideo Scheduler v2
WanVideo Set Attention Mode Override
WanVideo Set LoRAs
WanVideo Set Radial Attention
WanVideo Sigma To Step
WanVideo SLG
WanVideo SVIPro Embeds
WanVideo T5 Text Encoder Loader
WanVideo TeaCache
WanVideo TextEmbed Bridge
WanVideo TextEncode
WanVideo TextEncode Cached
WanVideo TextEncodeSingle
WanVideo Tiny VAE Loader
WanVideo Torch Compile Settings
WanVideo UltraVico Settings
WanVideo Uni3C Controlnet Loader
WanVideo Uni3C Embeds
WanVideo UniAnimate DWPose Detector
WanVideo UniAnimate Pose Input
WanVideo UniLumos Embeds
WanVideo VACE Encode
WanVideo VACE Module Select
WanVideo VACE Start To End Frame
WanVideo VAE Loader
WanVideoSampler v2 Extra Args
Wav2vec2 Model Loader
Whisper Model Loader

WanVideoWrapper/Ovi

Ovi MMAudio VAE Loader
WanVideo Add MMAudio To Latents
WanVideo Decode Ovi Audio
WanVideo Empty MMAudio Latents
WanVideo Encode Ovi Audio
WanVideo Ovi CFG

ComfyUI-Frame-Interpolation

A custom node suite for Video Frame Interpolation in ComfyUI

查看仓库•11 个节点

包含节点

ComfyUI-Frame-Interpolation

VFI FloatToInt

ComfyUI-Frame-Interpolation/others

KSampler Gradually Adding More Denoise (efficient)

ComfyUI-Frame-Interpolation/VFI

ATM VFI (only supports 2x multiplier)
CAIN VFI
FILM VFI
FLAVR VFI
IFRNet VFI
IFUnet VFI
Make Interpolation State List
MOMO VFI (only supports 2x multiplier)
RIFE VFI (recommend rife47 and rife49)

ComfyUI_UltimateSDUpscale

ComfyUI nodes for the Ultimate Stable Diffusion Upscale script by Coyote-A.

查看仓库•3 个节点

包含节点

image/upscaling

Ultimate SD Upscale
Ultimate SD Upscale (Custom Sample)
Ultimate SD Upscale (No Upscale)

ComfyUI-Florence2

Nodes to use Florence2 VLM for image vision tasks: object detection, captioning, segmentation and ocr

查看仓库•3 个节点

包含节点

Florence2

DownloadAndLoadFlorence2Lora
DownloadAndLoadFlorence2Model
Florence2Run

ComfyUI reference implementation for the IPAdapter models. The IPAdapter are very powerful models for image conditioning. The style and composition of a reference can be easily transferred to the generation. Think of it as a 1-image lora.

查看仓库•29 个节点

包含节点

ipadapter

IPAdapter
IPAdapter Advanced
IPAdapter Batch (Adv.)
IPAdapter Unified Loader

ipadapter/dev

IPAdapter Mad Scientist

ipadapter/embeds

IPAdapter Combine Embeds
IPAdapter Embeds
IPAdapter Embeds Batch
IPAdapter Encoder
IPAdapter Load Embeds

ipadapter/faceid

IPAdapter FaceID
IPAdapter FaceID Batch
IPAdapter Unified Loader FaceID

ipadapter/loaders

IPAdapter InsightFace Loader
IPAdapter Model Loader
IPAdapter Unified Loader Community

ipadapter/params

IPAdapter Combine Params
IPAdapter from Params
IPAdapter Regional Conditioning

ipadapter/style_composition

IPAdapter Style & Composition Batch SDXL
IPAdapter Style & Composition SDXL

ipadapter/tiled

IPAdapter Tiled
IPAdapter Tiled Batch

ipadapter/utils

IPAdapter Combine Weights
IPAdapter Noise
Prep Image For ClipVision

ipadapter/weights

IPAdapter Weights
IPAdapter Weights From Strategy
Prompt Schedule From Weights Strategy

WAS Node Suite v3

WAS-NS reborn; Tools for image processing, filters, masking, text, logic, numbers, latents, files, 3D scenes, animation, and Llama-Index in ComfyUI: language models, documents, retrieval, chat, memory and agents as nodes.

查看仓库•183 个节点

包含节点

WAS Suite/Animation

Create Morph Image

WAS Suite/Conditioning

CLIPTextEncode (NSP)

WAS Suite/Debug

Samples Passthrough (Stat System)
Text to Console

WAS Suite/Image

Image Batch
Image Blank
Image Blend
Image Blend by Mask
Image Blending Mode
Images to Linear
Images to RGB

WAS Suite/Image/Adjustment

Image Levels Adjustment
Image Rotate Hue
Image Shadows and Highlights

WAS Suite/Image/AI

Image Rembg (Remove Background)

WAS Suite/Image/Analyze

Image Analyze
Image Color Palette
Image to Seed

WAS Suite/Image/Bound

Bounded Image Blend
Bounded Image Blend with Mask
Bounded Image Crop
Bounded Image Crop with Mask
Image Bounds
Inset Image Bounds

WAS Suite/Image/Filter

Image Bloom Filter
Image Canny Filter
Image Chromatic Aberration
Image Dragan Photography Filter
Image Edge Detection Filter
Image fDOF Filter
Image Film Grain
Image Filter Adjustments
Image Gradient Map
Image High Pass Filter
Image Lucy Sharpen
Image Median Filter
Image Monitor Effects Filter
Image Nova Filter
Image SSAO (Ambient Occlusion)
Image SSDO (Direct Occlusion)
Image Style Filter

WAS Suite/Image/Generate

Image Generate Gradient

WAS Suite/Image/Generate/Noise

Image Perlin Noise
Image Perlin Power Fractal
Image Power Noise
Image to Noise
Image Voronoi Noise Filter

WAS Suite/Image/Masking

Convert Masks to Images
Image to Latent Mask
Mask Arbitrary Region
Mask Batch
Mask Batch to Mask
Mask Ceiling Region
Mask Crop Dominant Region
Mask Crop Minority Region
Mask Crop Region
Mask Dilate Region
Mask Dominant Region
Mask Erode Region
Mask Fill Holes
Mask Floor Region
Mask Gaussian Region
Mask Invert
Mask Minority Region
Mask Paste Region
Mask Rect Area
Mask Rect Area (Advanced)
Mask Smooth Region
Mask Threshold Region
Masks Add
Masks Combine Batch
Masks Combine Regions
Masks Subtract
SAM Image Mask
SAM Parameters
SAM Parameters Combine

WAS Suite/Image/Process

Create Grid Image from Batch
Image Crop Face
Image Crop Location
Image Crop Square Location
Image Mix RGB Channels
Image Paste Crop
Image Paste Crop by Location
Image Paste Face
Image Pixelate
Image Remove Background (Alpha)
Image Remove Color
Image Seamless Texture
Image Select Channel
Image Select Color
Image Threshold
Image Tiled

WAS Suite/Image/Transform

Image Displacement Warp
Image Flip
Image Padding
Image Resize
Image Rotate
Image Stitch
Image Transpose

WAS Suite/Integer

Integer place counter

WAS Suite/Latent

Blend Latents
Latent Batch

WAS Suite/Latent/Generate

Latent Noise Injection

WAS Suite/Latent/Transform

Latent Upscale by Factor (WAS)
Tensor Batch to Image

WAS Suite/Loaders

Load Lora
Lora Loader
unCLIP Checkpoint Loader

WAS Suite/Loaders/Advanced

Diffusers Model Loader

WAS Suite/Logic

Boolean To Text
CLIP Input Switch
CLIP Vision Input Switch
Conditioning Input Switch
Control Net Model Input Switch
Image Aspect Ratio
Image Input Switch
Latent Input Switch
Logic Boolean
Logic Boolean Primitive
Logic Comparison AND
Logic Comparison OR
Logic Comparison XOR
Logic NOT
Lora Input Switch
Model Input Switch
Number Input Condition
Number Input Switch
Text Contains
Text Input Switch
Upscale Model Switch
VAE Input Switch

WAS Suite/Number

Constant Number
Number Counter
Number PI
Random Number
Seed

WAS Suite/Number/Functions

Number Multiple Of

WAS Suite/Number/Operations

Image Size to Number
Latent Size to Number
Number Operation
Number to Float
Number to Int
Number to Seed
Number to String
Number to Text

WAS Suite/Sampling

KSampler (WAS)
KSampler Cycle

WAS Suite/Text

Prompt Multiple Styles Selector
Prompt Styles Selector
Text Concatenate
Text Dictionary Convert
Text Dictionary Get
Text Dictionary Keys
Text Dictionary New
Text Dictionary To Text
Text Dictionary Update
Text List
Text List Concatenate
Text List to Text
Text Multiline
Text Multiline (Code Compatible)
Text Random Line
Text String

WAS Suite/Text/Operations

String to Text
Text Shuffle
Text Sort
Text String Truncate
Text to Conditioning
Text to Number
Text to String

WAS Suite/Text/Parse

Text Parse A1111 Embeddings
Text Parse Noodle Soup Prompts

WAS Suite/Text/Search

Text Compare
Text Find
Text Find and Replace
Text Find and Replace by Dictionary
Text Find and Replace Input

WAS Suite/Text/Tokens

Text Add Token by Input
Text Add Tokens
Text Parse Tokens

WAS Suite/Utilities

Bus Node
Hex to HSL
HSL to Hex

ComfyUI-RMBG

A sophisticated ComfyUI custom node engineered for advanced image and video background removal and precise segmentation of objects, faces, clothing, and fashion elements. This tool leverages a diverse array of models, including RMBG-2.0, VRMBG-3.0, FeyNoBg, Finegrain Box Segmenter, INSPYRENET, BEN, BEN2, BiRefNet, SDMatte, SAM, SAM2, SAM3, Florence-2, and YOLO, while also incorporating an interactive Canvas studio, real-time background replacement, and instant VRAM unloading.

查看仓库•35 个节点

包含节点

🧪AILab/🎭Inpaint

Reference Latent Mask (RMBG) 🖼️🎭

🧪AILab/🖼️IMAGE

Crop To Object (RMBG) 🖼️🎭
IC LoRA Concat (RMBG) 🖼️🎭
Image and Mask to List (RMBG)
Image Combiner (RMBG) 🖼️
Image Crop (RMBG) 🖼️
Image Preview (RMBG) 🖼️
Image Resize (RMBG) 🖼️🎭
Image Stitch (RMBG) 🖼️
Image to List (RMBG)
Image/Mask Converter (RMBG) 🖼️🎭
Image/Mask Preview (RMBG) 🖼️🎭
Mask Combiner (RMBG) 🎭
Mask Enhancer (RMBG) 🎭
Mask Extractor (RMBG) 🎭
Mask Overlay (RMBG) 🖼️🎭
Mask Preview (RMBG) 🎭
Side By Side Compare (RMBG) 🖼️🖼️
Unbatch Images (RMBG) 🖼️

🧪AILab/🦠MASK

Mask to List (RMBG)

🧪AILab/🧽RMBG

Accessories Segment (RMBG)
BiRefNet (RMBG)
Body Segment (RMBG)
Clothes Segment (RMBG)
Color to Mask (RMBG) 🎭
Face Segment (RMBG)
Fashion Segment (RMBG)
Florence2 (RMBG)
Florence2 Box Coordinates (RMBG)
Lama Remover (RMBG)
Remove Background (RMBG)
SAM2 Segmentation (RMBG)
SAM3 Segmentation (RMBG)
SDMatte Matting (RMBG)

🧪AILab/🛠️UTIL/🔄IO

Color Input (RMBG) 🎨

ComfyUI-Inpaint-CropAndStitch

The '✂️ Inpaint Crop' and '✂️ Inpaint Stitch' nodes enable inpainting only on masked area very easily: crop the image around the masked area with the Crop node, then use any standard workflow for sampling, then connect the sampled image to the Stitch node, which will put it back in place in the original image. These nodes enable faster sampling of smaller areas and take care of downsampling and upsampling to fit specific model and resource needs.

查看仓库•6 个节点

包含节点

inpaint

(OLD 💀 use Crop instead) Extend Image for Outpainting
(OLD 💀 use Crop instead) Resize Image Before Inpainting
(OLD 💀, use the new ✂️ Inpaint Crop node)
(OLD 💀, use the new ✂️ Inpaint Stitch node)
✂️ Inpaint Crop (Improved)
✂️ Inpaint Stitch (Improved)

ComfyUI-Advanced-ControlNet

Nodes for scheduling ControlNet strength across timesteps and batched latents, as well as applying custom weights and attention masks.

查看仓库•42 个节点

包含节点

—

Apply Advanced ControlNet 🛂🅐🅒🅝
Apply Advanced ControlNet(1) 🛂🅐🅒🅝
ControlNet Custom Weights 🛂🅐🅒🅝
ControlNet Soft Weights 🛂🅐🅒🅝
Load Advanced ControlNet Model (diff) 🛂🅐🅒🅝
Load Advanced ControlNet Model 🛂🅐🅒🅝
Scaled Soft Weights 🛂🅐🅒🅝
T2IAdapter Custom Weights 🛂🅐🅒🅝
T2IAdapter Soft Weights 🛂🅐🅒🅝

Adv-ControlNet 🛂🅐🅒🅝

Apply Advanced ControlNet 🛂🅐🅒🅝
Apply Advanced ControlNet(1) 🛂🅐🅒🅝
Load Advanced ControlNet Model (diff) 🛂🅐🅒🅝
Load Advanced ControlNet Model 🛂🅐🅒🅝

Adv-ControlNet 🛂🅐🅒🅝/ControlNet++

ControlNet++ Input 🛂🅐🅒🅝
Load ControlNet++ Model (Multi) 🛂🅐🅒🅝
Load ControlNet++ Model (Single) 🛂🅐🅒🅝

Adv-ControlNet 🛂🅐🅒🅝/CtrLoRA

Load CtrLoRA Model 🛂🅐🅒🅝

Adv-ControlNet 🛂🅐🅒🅝/keyframes

Latent Keyframe 🛂🅐🅒🅝
Latent Keyframe From List 🛂🅐🅒🅝
Latent Keyframe Group 🛂🅐🅒🅝
Latent Keyframe Interp. 🛂🅐🅒🅝
Timestep Keyframe 🛂🅐🅒🅝
Timestep Keyframe From List 🛂🅐🅒🅝
Timestep Keyframe Interp. 🛂🅐🅒🅝

Adv-ControlNet 🛂🅐🅒🅝/Reference

Reference ControlNet (Finetune) 🛂🅐🅒🅝
Reference ControlNet 🛂🅐🅒🅝

Adv-ControlNet 🛂🅐🅒🅝/Reference/preprocess

Reference Preproccessor 🛂🅐🅒🅝

Adv-ControlNet 🛂🅐🅒🅝/SparseCtrl

Load SparseCtrl Model 🛂🅐🅒🅝
SparseCtrl Index Method 🛂🅐🅒🅝
SparseCtrl Spread Method 🛂🅐🅒🅝

Adv-ControlNet 🛂🅐🅒🅝/SparseCtrl/experimental

🧪Load Merged SparseCtrl Model 🛂🅐🅒🅝

Adv-ControlNet 🛂🅐🅒🅝/SparseCtrl/extras

SparseCtrl Weight Extras 🛂🅐🅒🅝

Adv-ControlNet 🛂🅐🅒🅝/SparseCtrl/preprocess

RGB SparseCtrl 🛂🅐🅒🅝

Adv-ControlNet 🛂🅐🅒🅝/weights

Default Weights 🛂🅐🅒🅝
Scaled Soft Masked Weights 🛂🅐🅒🅝
Scaled Soft Weights 🛂🅐🅒🅝

Adv-ControlNet 🛂🅐🅒🅝/weights/ControlNet

ControlNet Custom Weights [Flux] 🛂🅐🅒🅝
ControlNet Custom Weights [SD1.5] 🛂🅐🅒🅝
ControlNet Soft Weights [SD1.5] 🛂🅐🅒🅝

Adv-ControlNet 🛂🅐🅒🅝/weights/extras

Middle Weight Extras 🛂🅐🅒🅝

Adv-ControlNet 🛂🅐🅒🅝/weights/T2IAdapter

T2IAdapter Custom Weights 🛂🅐🅒🅝
T2IAdapter Soft Weights 🛂🅐🅒🅝

ControlAltAI_Nodes

Quality of Life Nodes from ControlAltAI. Flux Resolution Calculator, Flux Sampler, Flux Union ControlNet Apply, Noise Plus Blend, Boolean Logic, and Flux Region Nodes.

查看仓库•17 个节点

包含节点

ControlAltAI Nodes/Flux

Flux Resolution Calc
Flux Sampler
Flux Union ControlNet Apply

ControlAltAI Nodes/Flux Region

Flux Attention Cleanup
Region Mask Generator

ControlAltAI Nodes/HiDream

HiDream Resolution

ControlAltAI Nodes/Image

Get Image Size Ratio
Noise Plus Blend
Perturbation Texture

ControlAltAI Nodes/Logic

Boolean Basic
Boolean Reverse
Choose Upscale Model
Integer Settings
Integer Settings Advanced
Switch (Three Way)
Switch (Two Way)

ControlAltAI Nodes/Utility

Text Bridge

ComfyUI-AnimateDiff-Evolved

Improved AnimateDiff integration for ComfyUI.

查看仓库•144 个节点

包含节点

—

🚫[DEPR] Motion Model Settings (Adv. Attn) 🎭🅐🅓①
🚫[DEPR] Motion Model Settings (Advanced) 🎭🅐🅓①
🚫[DEPR] Motion Model Settings (Simple) 🎭🅐🅓①
🚫[DEPR] Motion Model Settings 🎭🅐🅓①
🚫AnimateDiff Combine [DEPRECATED, Use Video Combine (VHS) Instead!] 🎭🅐🅓
🚫AnimateDiff Loader (Advanced) [DEPRECATED] 🎭🅐🅓
🚫AnimateDiff Loader [DEPRECATED] 🎭🅐🅓
Context Options◆Looped Uniform 🎭🅐🅓

Animate Diff 🎭🅐🅓

AnimateDiff Keyframe 🎭🅐🅓
Load AnimateDiff LoRA 🎭🅐🅓
Sample Settings 🎭🅐🅓

Animate Diff 🎭🅐🅓/① Gen1 nodes ①

AnimateDiff Loader [Legacy] 🎭🅐🅓①
AnimateDiff Loader 🎭🅐🅓①

Animate Diff 🎭🅐🅓/② Gen2 nodes ②

Apply AnimateDiff Model (Adv.) 🎭🅐🅓②
Apply AnimateDiff Model 🎭🅐🅓②
Load AnimateDiff Model 🎭🅐🅓②
Use Evolved Sampling 🎭🅐🅓②

Animate Diff 🎭🅐🅓/② Gen2 nodes ②/AnimateLCM-I2V

Apply AnimateLCM-I2V Model 🎭🅐🅓②
Load AnimateLCM-I2V Model 🎭🅐🅓②
Scale Ref Image and VAE Encode 🎭🅐🅓②

Animate Diff 🎭🅐🅓/② Gen2 nodes ②/AnimateLCM-I2V/🧪experimental

🧪Inject I2V into AnimateDiff Model 🎭🅐🅓②

Animate Diff 🎭🅐🅓/② Gen2 nodes ②/CameraCtrl

AnimateDiff+CameraCtrl Keyframe 🎭🅐🅓
Apply AnimateDiff+CameraCtrl Model 🎭🅐🅓②
Load AnimateDiff+CameraCtrl Model 🎭🅐🅓②

Animate Diff 🎭🅐🅓/② Gen2 nodes ②/CameraCtrl/poses

Create CameraCtrl Poses (Adv.) 🎭🅐🅓②
Create CameraCtrl Poses (Combo) 🎭🅐🅓②
Create CameraCtrl Poses 🎭🅐🅓②
Load CameraCtrl Poses (File) 🎭🅐🅓②
Manual Append CameraCtrl Poses 🎭🅐🅓②
Replace Camera Parameters 🎭🅐🅓②
Replace Orig. Pose Aspect Ratio 🎭🅐🅓②

Animate Diff 🎭🅐🅓/② Gen2 nodes ②/PIA

AnimateDiff-PIA Keyframe 🎭🅐🅓
Apply AnimateDiff-PIA Model 🎭🅐🅓②
PIA Input [Multival] 🎭🅐🅓②
PIA Input [Paper Presets] 🎭🅐🅓②

Animate Diff 🎭🅐🅓/② Gen2 nodes ②/PIA/🧪experimental

🧪Inject PIA into AnimateDiff Model 🎭🅐🅓②

Animate Diff 🎭🅐🅓/ad settings

AnimateDiff Settings 🎭🅐🅓

Animate Diff 🎭🅐🅓/ad settings/pe adjust

Adjust PE [Full Stretch] 🎭🅐🅓
Adjust PE [Manual] 🎭🅐🅓
Adjust PE [Sweetspot] 🎭🅐🅓

Animate Diff 🎭🅐🅓/ad settings/weight adjust

Adjust Weight [All◆Add] 🎭🅐🅓
Adjust Weight [All◆Mult] 🎭🅐🅓
Adjust Weight [Indiv-Attn◆Add] 🎭🅐🅓
Adjust Weight [Indiv-Attn◆Mult] 🎭🅐🅓
Adjust Weight [Indiv◆Add] 🎭🅐🅓
Adjust Weight [Indiv◆Mult] 🎭🅐🅓

Animate Diff 🎭🅐🅓/conditioning

Manual Combine Conds 🎭🅐🅓
Set CLIP LoRA Hook 🎭🅐🅓
Set LoRA Hook Keyframes 🎭🅐🅓
Set Props and Combine Conds 🎭🅐🅓
Set Props on Conds 🎭🅐🅓
Set Unmasked Conds 🎭🅐🅓
Timesteps Conditioning 🎭🅐🅓

Animate Diff 🎭🅐🅓/conditioning/combine lora hooks

Combine LoRA Hooks [2] 🎭🅐🅓
Combine LoRA Hooks [4] 🎭🅐🅓
Combine LoRA Hooks [8] 🎭🅐🅓

Animate Diff 🎭🅐🅓/conditioning/register lora hooks

Animate Diff 🎭🅐🅓/conditioning/schedule lora hooks

LoRA Hook Keyframe 🎭🅐🅓
LoRA Hook Keyframes From List 🎭🅐🅓
LoRA Hook Keyframes Interp. 🎭🅐🅓

Animate Diff 🎭🅐🅓/conditioning/single cond ops

Manual Combine Cond 🎭🅐🅓
Set Model LoRA Hook 🎭🅐🅓
Set Props and Combine Cond 🎭🅐🅓
Set Props on Cond 🎭🅐🅓
Set Unmasked Cond 🎭🅐🅓

Animate Diff 🎭🅐🅓/context opts

Context Options◆Batched [Non-AD] 🎭🅐🅓
Context Options◆Looped Uniform 🎭🅐🅓
Context Options◆Standard Static 🎭🅐🅓
Context Options◆Standard Uniform 🎭🅐🅓
Context Options◆Views Only [VRAM⇈] 🎭🅐🅓

Animate Diff 🎭🅐🅓/context opts/context extras

Context Extras◆ContextRef 🎭🅐🅓
Context Extras◆NaiveReuse 🎭🅐🅓
Set Context Extras 🎭🅐🅓

Animate Diff 🎭🅐🅓/context opts/context extras/contextref

ContextRef Keyframe 🎭🅐🅓
ContextRef Keyframes From List 🎭🅐🅓
ContextRef Keyframes Interp. 🎭🅐🅓
ContextRef Mode◆First 🎭🅐🅓
ContextRef Mode◆Indexes 🎭🅐🅓
ContextRef Mode◆Sliding 🎭🅐🅓
ContextRef Tune◆Attn 🎭🅐🅓
ContextRef Tune◆Attn+Adain 🎭🅐🅓

Animate Diff 🎭🅐🅓/context opts/context extras/naivereuse

NaiveReuse Keyframe 🎭🅐🅓
NaiveReuse Keyframes From List 🎭🅐🅓
NaiveReuse Keyframes Interp. 🎭🅐🅓

Animate Diff 🎭🅐🅓/context opts/view opts

View Options◆Looped Uniform 🎭🅐🅓
View Options◆Standard Static 🎭🅐🅓
View Options◆Standard Uniform 🎭🅐🅓

Animate Diff 🎭🅐🅓/context opts/visualize

Visualize Context Options (K.) 🎭🅐🅓
Visualize Context Options (K.Adv.) 🎭🅐🅓
Visualize Context Options (S.Cus.) 🎭🅐🅓

Animate Diff 🎭🅐🅓/extras

AnimateDiff Unload 🎭🅐🅓
Empty Latent Image (Big Batch) 🎭🅐🅓
Load Checkpoint w/ Noise Select 🎭🅐🅓
PerturbedAttnGuide [Multival] 🎭🅐🅓
RescaleCFG [Multival] 🎭🅐🅓

Animate Diff 🎭🅐🅓/iteration opts

Default Iteration Options 🎭🅐🅓
FreeInit Iteration Options 🎭🅐🅓

Animate Diff 🎭🅐🅓/multival

Multival [Float List] 🎭🅐🅓
Multival [Floats] 🎭🅐🅓
Multival 🎭🅐🅓
Multival Scaled Mask 🎭🅐🅓
Multival to Mask 🎭🅐🅓

Animate Diff 🎭🅐🅓/noise layers

Noise Layer [Add Weighted] 🎭🅐🅓
Noise Layer [Add] 🎭🅐🅓
Noise Layer [Normalized Sum] 🎭🅐🅓
Noise Layer [Replace] 🎭🅐🅓

Animate Diff 🎭🅐🅓/per block

AD Block 🎭🅐🅓
AD Block+ 🎭🅐🅓
AD Per Block 🎭🅐🅓
AD Per Block Floats (SD1.5) 🎭🅐🅓
AD Per Block Floats (SDXL) 🎭🅐🅓
AD Per Block+ (SD1.5) 🎭🅐🅓
AD Per Block+ (SDXL) 🎭🅐🅓
AD Per Block++ (SD1.5) 🎭🅐🅓
AD Per Block++ (SDXL) 🎭🅐🅓

Animate Diff 🎭🅐🅓/sample settings

Ancestral Options 🎭🅐🅓

Animate Diff 🎭🅐🅓/sample settings/cfg extras

CFG Extras◆PAG [Multival] 🎭🅐🅓
CFG Extras◆PAG 🎭🅐🅓
CFG Extras◆RescaleCFG [Multival] 🎭🅐🅓
CFG Extras◆RescaleCFG 🎭🅐🅓

Animate Diff 🎭🅐🅓/sample settings/custom cfg

Custom CFG [Multival] 🎭🅐🅓
Custom CFG 🎭🅐🅓
Custom CFG Keyframe [Multival] 🎭🅐🅓
Custom CFG Keyframe 🎭🅐🅓
Custom CFG Keyframes From List 🎭🅐🅓
Custom CFG Keyframes Interp. 🎭🅐🅓

Animate Diff 🎭🅐🅓/sample settings/image inject

Image Injection 🎭🅐🅓
Image Injection Options 🎭🅐🅓

Animate Diff 🎭🅐🅓/sample settings/sigma schedule

Create Raw Sigma Schedule 🎭🅐🅓
Create Sigma Schedule 🎭🅐🅓
Sigma Schedule Interp. Mean 🎭🅐🅓
Sigma Schedule Split Combine 🎭🅐🅓
Sigma Schedule To Sigmas 🎭🅐🅓
Sigma Schedule Weighted Mean 🎭🅐🅓

Animate Diff 🎭🅐🅓/scheduling

Add Values Replace 🎭🅐🅓
Condition Step Extraction 🎭🅐🅓
Float to Floats 🎭🅐🅓
Prompt Scheduling [Latents] 🎭🅐🅓
Prompt Scheduling 🎭🅐🅓
Value Scheduling [Latents] 🎭🅐🅓
Value Scheduling 🎭🅐🅓

ComfyUI_Fill-Nodes

Fill-Nodes is a versatile collection of custom nodes for ComfyUI that extends functionality across multiple domains. Features include advanced image processing (pixelation, slicing, masking), visual effects generation (glitch, halftone, pixel art), comprehensive file handling (PDF creation/extraction, Google Drive integration), AI model interfaces (GPT, DALL-E, Hugging Face), utility nodes for workflow enhancement, and specialized tools for video processing, captioning, and batch operations. The pack provides both practical workflow solutions and creative tools within a unified node collection.

查看仓库•107 个节点

包含节点

🏵️Fill Nodes/Audio

FL Audio Beat Visualizer
FL Audio BPM Analyzer
FL Audio Crop
FL Audio Drum Detector
FL Audio Envelope Visualizer
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

🏵️Fill Nodes/Captioning

FL CSV Extractor

🏵️Fill Nodes/experiments

FL Batch Align
FL Color Picker
FL Grad Generator
FL Video Recompose

🏵️Fill Nodes/games

FL BulletHell Game
FL Tetris Game

🏵️Fill Nodes/Image

FL Anime Line Extractor
FL Apply Mask
FL Black Frame Reject
FL Image Add Noise
FL Image Add To Batch
FL Image Adjuster
FL Image Aspect Cropper
FL Image Batch
FL Image Batch To Grid
FL Image Batch To Image List
FL Image Blank
FL Image Crop
FL Image List To Image Batch
FL Image Notes
FL Image Overlay
FL Image Selector
FL Image Size
FL Image Slicer
FL Padding Remover
FL Replace Color

🏵️Fill Nodes/Ksamplers

FL KSampler Basic
FL KSampler Plus
FL KSampler Plus V2
FL KSampler Settings
FL KSampler XYZ Plot
FL Sampler String XYZ
FL Scheduler String XYZ

🏵️Fill Nodes/Loaders

FL Upscale Model

🏵️Fill Nodes/PDF

FL Images To PDF
FL PDF Encryptor
FL PDF Image Extractor
FL PDF Merger
FL PDF Text Extractor
FL PDF To Images
FL Text To PDF

🏵️Fill Nodes/Prompting

FL MadLib Generator
FL Prompt Basic
FL Prompt Multi
FL Prompt Selector
FL Prompt Selector Basic

🏵️Fill Nodes/utility

FL Random Shape Generator

🏵️Fill Nodes/Utility

FL Float
FL Float to Int
FL Inpaint Crop
FL Inpaint Stitch
FL Int to Float
FL Math
FL Padding
FL Paste By Mask
FL Paste On Canvas
FL Path Type Checker
FL Random Number
FL SDUltimate Slices
FL Separate Mask Components
FL Switch
FL Switch Big
FL Unload All Models
FL Unload Model
FL Video CropMask

🏵️Fill Nodes/VFX

FL Ascii
FL Dither
FL Glitch
FL Halftone
FL Hexagonal Pattern
FL Image Collage
FL Image Pixelator
FL Pixel Art
FL PixelSort
FL Retro Effect
FL Ripple
FL Text Overlay

🏵️Fill Nodes/Video

FL Video Batch Splitter
FL Video Cadence
FL Video Cadence Compile
FL Video Crossfade
FL Video Trim

🏵️Fill Nodes/WIP

FL Animated Shape Patterns
FL Fractal KSampler
FL Qwen Image Edit with Strength
FL Wan First Frame Last Frame
FL Wan Vace To Video Multi Reference
FL Wan Video Blender
FL Wan Video Blender 3-Way
FL Wan Video Continuation Blender
FL Wan Video Continue

ComfyUI-QwenVL

ComfyUI-QwenVL custom node: Integrates the Qwen-VL series, including Qwen2.5-VL, Qwen3-VL, Qwen3.5-VL, Qwen3.6-VL (MoE), and Qwen3.8-VL, with GGUF support for advanced multimodal AI in text generation, image understanding, and video analysis.

查看仓库•3 个节点

包含节点

🧪AILab/QwenVL

QwenVL
QwenVL (Advanced)
QwenVL Prompt Enhancer

ComfyUI-AdvancedLivePortrait

AdvancedLivePortrait with Facial expression editor

查看仓库•4 个节点

包含节点

AdvancedLivePortrait

Advanced Live Portrait (PHM)
ExpData
Expression Editor (PHM)
PrintExpData:

ComfyUI-segment-anything-2

Nodes to use [a/segment-anything-2](https://github.com/facebookresearch/segment-anything-2) for image or video segmentation.

查看仓库•6 个节点

包含节点

SAM2

(Down)Load SAM2Model
Florence2 Coordinates
Sam2AutoSegmentation
Sam2Segmentation
Sam2VideoSegmentation
Sam2VideoSegmentationAddPoints

ComfyUI-MelBandRoFormer

ComfyUI wrapper nodes for WanVideo

查看仓库•2 个节点

包含节点

Mel-Band RoFormer

Mel-Band RoFormer Model Loader
Mel-Band RoFormer Sampler

ComfyUI-SUPIR

Wrapper nodes to use SUPIR upscaling process in ComfyUI

查看仓库•10 个节点

包含节点

SUPIR

SUPIR Conditioner
SUPIR Decode
SUPIR Encode
SUPIR First Stage (Denoiser)
SUPIR Model Loader (Legacy)
SUPIR Model Loader (v2)
SUPIR Model Loader (v2) (Clip)
SUPIR Sampler
SUPIR Tiles Preview
SUPIR Upscale (Legacy)

audio-separation-nodes-comfyui

Separate audio track into stems (vocals, bass, drums, other). Along with tools to recombine, tempo match, slice/crop audio

查看仓库•7 个节点

包含节点

audio

AudioCombine
AudioCrop
AudioGetTempo
AudioSeparation
AudioSpeedShift
AudioTempoMatch
AudioVideoCombine

ComfyUI-DepthAnythingV2

ComfyUI nodes to use [a/DepthAnythingV2](https://depth-anything-v2.github.io/) NOTE:Models autodownload to ComfyUI/models/depthanything from [a/https://huggingface.co/Kijai/DepthAnythingV2-safetensors/tree/main](https://huggingface.co/Kijai/DepthAnythingV2-safetensors/tree/main)

查看仓库•2 个节点

包含节点

DepthAnythingV2

Depth Anything V2
DownloadAndLoadDepthAnythingV2Model

ComfyUI-Logic

An extension to ComfyUI that introduces logic nodes and conditional rendering capabilities.

查看仓库•4 个节点

包含节点

Logic

Bool
Float
Int
String

ComfyUI-WanAnimatePreprocess

ComfyUI nodes for WanAnimate input processing

查看仓库•4 个节点

包含节点

WanAnimatePreprocess

ONNX Detection Model Loader
Pose and Face Detection
Pose Detection OneToAll Animation
Pose Retarget Prompt Helper

Basic data handling

Basic Python functions for manipulating data that every programmer is used to, lightweight with no additional dependencies. Supported data types: - ComfyUI native: BOOLEAN, FLOAT, INT, STRING, and data lists - Python types as custom data types: DICT, LIST, SET, DATETIME, TIMEDELTA - PyTorch: TENSOR Feature categories: - Boolean logic operations - Type casting/conversion between all supported data types - Comparison operations - Data container manipulation - Flow control (conditionals, branching, execution order) - Mathematical operations - Mathematical formula node in a safe implementation - String manipulation - File system path handling, including STRING, IMAGE and MASK load and save - SET operations - time and date handling - PyTorch Tensor manipulation (arithmetic, slicing, reshaping)

查看仓库•277 个节点

包含节点

Basic/BOOLEAN

and
and (generic)
nand
nor
not
or
or (generic)
xor

Basic/cast

to BOOLEAN
to DICT
to FLOAT
to INT
to LIST
to SET
to STRING

Basic/comparison

!=
<
<=
==
>
>=
compare length
is null
string compare

Basic/Data List

all
any
append
contains
convert to LIST
convert to SET
count
create Data List
create Data List from BOOLEANs
create Data List from FLOATs
create Data List from INTs
create Data List from STRINGs
create Data List of Lists
enumerate
extend
filter
filter select
first
get item
index
insert
last
length
max
min
pop
pop random
range
remove
reverse
set item
shuffle
slice
sort
sum
zip

Basic/DICT

compare
contains key
create DICT
create DICT from BOOLEANs
create DICT from FLOATs
create DICT from INTs
create DICT from STRINGs
create from items (data list)
create from items (LIST)
create from LISTs
exclude keys
filter by keys
from keys
get
get keys values
get multiple
invert
items
keys
length
merge
pop
pop item
pop random
remove
set
setdefault
update
values

Basic/FLOAT

add
create FLOAT
divide
divide (zero safe)
from hex
integer ratio
is integer
multiply
power
round
subtract
to hex

Basic/flow control

continue flow
flow select
force calculation
force execution order
if/elif/.../else
if/else
is connected
switch/case

Basic/INT

add
bit count
bit length
create INT
divide
divide (zero safe)
from bytes
modulus
multiply
power
subtract
to bytes

Basic/LIST

all
any
append
contains
convert to Data List
convert to SET
count
create LIST
create LIST from BOOLEANs
create LIST from FLOATs
create LIST from INTs
create LIST from STRINGs
enumerate
extend
first
get item
index
insert
last
length
max
min
pop
pop random
range
remove
reverse
set item
shuffle
slice
sort
sum

Basic/maths

abs
acos
asin
atan
atan2
ceil
cos
degrees
e (2.71828)
exp
floor
formula
log
log10
max
min
pi (3.14159)
radians
sin
sqrt
tan

Basic/SET

add
all
any
contains
convert to Data List
convert to LIST
create SET
create SET from BOOLEANs
create SET from FLOATs
create SET from INTs
create SET from STRINGs
difference
discard
enumerate
intersection
is disjoint
is subset
is superset
length
pop
pop random
remove
sum
symmetric difference
union

Basic/STRING

capitalize
casefold
center
concat
count
decode
encode
endswith
escape
expandtabs
find
format_map
in (contains)
join (from data list)
join (from LIST)
length
ljust
lower
lstrip
removeprefix
removesuffix
replace
rfind
rjust
rsplit (from data list)
rsplit (from LIST)
rstrip
split (to data list)
split (to LIST)
splitlines (from data list)
splitlines (to LIST)
startswith
strip
swapcase
title
unescape
upper
zfill

Basic/STRING/is

isalnum
isalpha
isascii
isdecimal
isdigit
isidentifier
islower
isnumeric
isprintable
isspace
istitle
isupper

Basic/STRING/regex

find all (data list)
find all (LIST)
search groups (data list)
search groups (LIST)
search named groups
split (data list)
split (LIST)
substitute
test

Basic/tensor

Tensor Binary Op
Tensor Create
Tensor Info
Tensor Join
Tensor Permute
Tensor Reshape
Tensor Slice
Tensor Unary Op

Basic/time

Add Time Delta
Create Time Delta
Extract Time Components
Format Time String
Parse Time String
Subtract Time Delta
Time Difference
Time Now
Time Now (UTC)
Time to Unix Timestamp
Unix Timestamp to Time

LanPaint

Achieve seamless inpainting results without needing a specialized inpainting model.

查看仓库•11 个节点

包含节点

audio

LanPaint MiniMax Audio Decode
LanPaint MiniMax Audio Encode

image

LanPaint Image Decode
LanPaint Image Encode

image/postprocessing

LanPaint Mask Blend

sampling

LanPaint KSampler
LanPaint KSampler (Advanced)

sampling/custom_sampling

LanPaint Sampler Custom
LanPaint Sampler Custom (Advanced)

video

LanPaint AV Decode
LanPaint AV Encode

ComfyUI_LayerStyle_Advance

The nodes detached from ComfyUI Layer Style are mainly those with complex requirements for dependency packages.

查看仓库•46 个节点

包含节点

😺dzNodes/LayerMask

LayerMask: BBox Join(Advance)
LayerMask: Ben Ultra(Advance)
LayerMask: BiRefNet Ultra V2(Advance)
LayerMask: BiRefNetUltra(Advance)
LayerMask: Draw BBox Mask V2(Advance)
LayerMask: Draw BBox Mask(Advance)
LayerMask: EVF-SAM Ultra(Advance)
LayerMask: Load Ben Model(Advance)
LayerMask: Load BiRefNet Model V2(Advance)
LayerMask: Load BiRefNet 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 Mask(Advance)
LayerMask: Object Detector YOLO World(Obsolete)
LayerMask: Object Detector YOLO8(Advance)
LayerMask: PersonMaskUltra V2(Advance)
LayerMask: PersonMaskUltra(Advance)
LayerMask: SAM2 Ultra V2(Advance)
LayerMask: SAM2 Ultra(Advance)
LayerMask: SAM2 Video Ultra(Advance)
LayerMask: SegmentAnythingUltra V2(Advance)
LayerMask: SegmentAnythingUltra V3(Advance)
LayerMask: SegmentAnythingUltra(Advance)
LayerMask: Transparent Background Ultra(Advance)
LayerMask: YoloV8 Detect(Advance)

😺dzNodes/LayerUtility

LayerUtility: Collage(Advance)
LayerUtility: GetColorTone V2(Advance)
LayerUtility: GetColorTone(Advance)
LayerUtility: ImageAutoCrop V2(Advance)
LayerUtility: ImageAutoCrop V3(Advance)
LayerUtility: ImageAutoCrop(Advance)
LayerUtility: LaMa(Advance)
LayerUtility: Load SmolLM2 Model(Advance)
LayerUtility: Load SmolVLM Model(Advance)
LayerUtility: SmolLM2(Advance)
LayerUtility: SmolVLM(Advance)

😺dzNodes/LayerUtility/Prompt

LayerUtility: QWenImage2Prompt(Advance)
LayerUtility: UserPrompt Generator Replace Word(Advance)
LayerUtility: UserPrompt Generator Txt2Img with Reference(Advance)
LayerUtility: UserPrompt Generator Txt2Img(Advance)

😺dzNodes/LayerUtility/SystemIO

LayerUtility: Create QRCode(Advance)
LayerUtility: Decode QRCode(Advance)
LayerUtility: SD3 Negative Conditioning(Advance)

ComfyUI-LivePortraitKJ

Nodes for [a/LivePortrait](https://github.com/KwaiVGI/LivePortrait)

查看仓库•9 个节点

包含节点

LivePortrait

(Down)Load LivePortraitModels
LivePortrait Composite
LivePortrait Cropper
LivePortrait KeypointsToImage
LivePortrait Load FaceAlignmentCropper
LivePortrait Load InsightFaceCropper
LivePortrait Load MediaPipeCropper
LivePortrait Process
LivePortrait Retargeting

ComfyUI-enricos-nodes

pass up to 8 images and visually place, rotate and scale them to build the perfect composition. group move and group rescale. remember their position and scaling value across generations to easy swap images. use the buffer zone to to park an asset you don't want to use or easily reach transformations controls

查看仓库•7 个节点

包含节点

image

💜 Compositor (V3)
💜 Compositor Config (V3)
💜 Compositor Masks Output (V3)
💜 Compositor Tools (V3) Experimental
💜 Compositor Transforms Output (V3)

image/color

💜 Compositor Color Picker
💜 Image Color Sampler

Dynamic Thresholding

Adds nodes for Dynamic Thresholding, CFG scheduling, and related techniques

查看仓库•2 个节点

包含节点

advanced/mcmonkey

DynamicThresholdingFull
DynamicThresholdingSimple

ComfyUI-CogVideoXWrapper

Diffusers wrapper for CogVideoX -models: https://github.com/THUDM/CogVideo

查看仓库•24 个节点

包含节点

CogVideoWrapper

(Down)load CogVideo ControlNet
(Down)load CogVideo GGUF Model
(Down)load CogVideo Model
(Down)load Tora Model
CogVideo Context Options
CogVideo Decode
CogVideo Enhance-A-Video
CogVideo ImageEncode
CogVideo ImageEncode FunInP
CogVideo LoraSelect
CogVideo LoraSelect Comfy
CogVideo Sampler
CogVideo TextEncode
CogVideo TextEncode Combine
CogVideo TransformerEdit
CogVideoControlNet
CogVideoX FasterCache
CogVideoX Model Loader
CogVideoX VAE Loader
CogVideoXFun ResizeToClosestBucket
Tora Encode OpticalFlow
Tora Encode Trajectory

MochiWrapper

CogVideo TorchCompileSettings

PyramidFlowWrapper

CogVideo LatentPreview

ComfyUI-iTools

Whether you're a casual user or a power user, iTools provides the quality-of-life improvements you need to make your ComfyUI experience more efficient and enjoyable.

查看仓库•12 个节点

包含节点

iTools

iTools Add Text Overlay
iTools Checkerboard 🏁
iTools Grid Filler 📲
iTools Instructor 👨🏻‍🏫
iTools KSampler
iTools Line Loader
iTools Load Image 🏕️
iTools Preview Bridge ⛳
iTools Prompt Record 🪶
iTools Regex Editor
iTools Text Preview
iTools Text Replacer

OneButtonPrompt

One Button Prompt has a prompt generation node for beginners who have problems writing a good prompt, or advanced users who want to get inspired. It generates an entire prompt from scratch. It is random, but controlled. You simply load up the script and press generate, and let it surprise you.

查看仓库•5 个节点

包含节点

OneButtonPrompt

Auto Negative Prompt
Create Prompt Variant
One Button Artify
One Button Preset
One Button SuperPrompt

WhatDreamsCost-ComfyUI

LTX Director and a variety of other custom ComfyUI nodes and workflows

查看仓库•2 个节点

包含节点

WhatDreamsCost

Load Audio UI
Speech Length Calculator

ComfyUI-SCAIL-Pose

ComfyUI nodes for SCAIL pose input processing

查看仓库•3 个节点

包含节点

WanAnimatePreprocess

Convert OpenPose Keypoints to DWPose
Pose Detection VitPose to DWPose

WanVideoWrapper

Render NLF Poses

ComfyUI-layerdiffuse

Transparent Image Layer Diffusion using Latent Transparency

查看仓库•6 个节点

包含节点

layer_diffuse

Layer Diffuse Apply
Layer Diffuse Cond Apply
Layer Diffuse Decode
Layer Diffuse Decode (RGBA)
Layer Diffuse Decode (Split)
Layer Diffuse Diff Apply

comfyui_face_parsing

This is a set of custom nodes for ComfyUI. The nodes utilize the [a/face parsing model](https://huggingface.co/jonathandinu/face-parsing) to parse face and provide detailed segmantation. To improve face segmantation accuracy, [a/yolov8 face model](https://huggingface.co/Bingsu/adetailer/) is used to first extract face from an image. There are also auxiliary nodes for image and mask processing. A guided filter is also provided for skin smoothing.

查看仓库•27 个节点

包含节点

face_parsing

BBoxDecompose(FaceParsing)
BBoxDetect(FaceParsing)
BBoxDetectorLoader(FaceParsing)
BBoxListItemSelect(FaceParsing)
BBoxResize(FaceParsing)
ColorAdjust(FaceParsing)
FaceParse(FaceParsing)
FaceParsingModelLoader(FaceParsing)
FaceParsingProcessorLoader(FaceParsing)
FaceParsingResultsParser(FaceParsing)
GuidedFilter(FaceParsing)
ImageCropWithBBox(FaceParsing)
ImageCropWithBBoxList(FaceParsing)
ImageInsertWithBBox(FaceParsing)
ImageListSelect(FaceParsing)
ImagePadWithBBox(FaceParsing)
ImageResizeCalculator(FaceParsing)
ImageResizeWithBBox(FaceParsing)
ImageSize(FaceParsing)
MaskBatchComposite(FaceParsing)
MaskBlackOut(FaceParsing)
MaskBorderDissolve(FaceParsing)
MaskComposite(FaceParsing)
MaskCropWithBBox(FaceParsing)
MaskInsertWithBBox(FaceParsing)
MaskListSelect(FaceParsing)
MaskToBBoxList(FaceParsing)

ComfyUI_Steudio

Divide and Conquer Node Suite: It calculates the optimal upscale resolution and seamlessly divides the image into tiles, ready for individual processing using your preferred workflow. After processing, the tiles are seamlessly merged into a larger image, offering sharper and more detailed visuals.

查看仓库•8 个节点

包含节点

Steudio/Divide and Conquer

Combine Tiles
Divide and Conquer Algorithm
Divide Image and Select Tile

Steudio/Utils

Ratio Calculator
Ratio to Size
Seed Shifter
Sequence Generator
Simple Config

SAM3

Warning, uses experimental package `comfy-env` to attempt a one click isolated install. Will download and use pixi package manager. SAM 3 (Segment Anything Model 3) integration for ComfyUI. Image and video segmentation with text prompts, boxes, and points

查看仓库•14 个节点

包含节点

SAM3

(down)Load SAM3 Model
SAM3 BBox Collector 📦
SAM3 Multi-Region Collector 🎯
SAM3 Multiprompt Segmentation
SAM3 Point Collector
SAM3 Point Segmentation

SAM3/Grounding

SAM3 Text Segmentation

SAM3/prompts

SAM3 Combine Boxes
SAM3 Combine Points
SAM3 Create Box
SAM3 Create Point

SAM3/video

SAM3 Propagate
SAM3 Video Output
SAM3 Video Segmentation

ComfyUI-BFSNodes

Custom ComfyUI nodes for reference-guided video: BFS Sampler (guide-driven IC-LoRAs, auto crop, mask inpainting, temporal chunking), LTX Multiple Controls / Identity Transfer / Edit Anything, Head-Swap and Anime2Real conditioning, MiniMax-H3 latent guides, RoPE layouts and loaders, LoRA Surgery, and Shot Planner / Shot Loop (tabbed panel): split long videos into shots at camera cuts, face-tracked cast, SAM 3 mask per shot with full frame, paste, mask, crop and crop + mask generation modes, optional translucent Colored Mark overlay for manually selected regions, optional Qwen3-VL to suggest settings, describe references ({details}) and the person to replace ({target}), continuity between shots, H3 conditioning with an optional duet and prompt writer, join with the original timing, audio and a side-by-side comparison. H3 Duet: pin a source clip beside the video, training-free.

查看仓库•1 个节点

包含节点

video/composition

Reserved Region Frame Composer

ComfyUI-IC-Light-Native

ComfyUI native implementation of [a/IC-Light](https://github.com/lllyasviel/IC-Light).

查看仓库•3 个节点

包含节点

_for_testing

ICLightAppply

mask/compositing

IC Light Apply Mask Grey

model/latent

VAE Encode ArgMax

ComfyUI-FlashVSR_Ultra_Fast

暂无描述信息。

查看仓库•3 个节点

包含节点

FlashVSR

FlashVSR Init Pipeline
FlashVSR Ultra-Fast
FlashVSR Ultra-Fast (Advanced)

ComfyUI-MimicMotionWrapper

Optimized wrapper nodes for MimicMotion: [a/https://github.com/tencent/MimicMotion](https://github.com/tencent/MimicMotion)

查看仓库•5 个节点

包含节点

MimicMotionWrapper

(Down)Load MimicMotionModel
Diffusers Scheduler
MimicMotion Decode
MimicMotion GetPoses
MimicMotion Sampler

ComfyUI-WanVaceAdvanced

Precise control over Vace frame strengths for reference images, control videos. Also allows Phantom embeddings to be combined with VACE accurately.

查看仓库•15 个节点

包含节点

WanVaceAdvanced

HuMo I2V Patch
StringToFloatListRanged
VaceAdvancedModelPatch
VaceStrengthTester
WanMaskToLatentSpace
WanVacePhantomDualV2
WanVacePhantomExperimentalV2
WanVacePhantomSimple
WanVacePhantomSimpleV2
WanVaceRefsToContextWindows
WanVaceReplace
WanVaceToVideoLatent
WVAOptions
WVAPipeSimple

WanVaceAdvanced/Hooks

VACEAdvancedDetailerHook

ComfyUI-DynamiCrafterWrapper

Wrapper nodes to use Dynami/ToonCrafter image2video and frame interpolation models in ComfyUI

查看仓库•11 个节点

包含节点

DynamiCrafterWrapper

(Down)Load CLIPVisionModel
(Down)Load DynamiCrafter CNModel
(Down)Load DynamiCrafterModel
DynamiCrafter BatchInterpolation
DynamiCrafter CNLoader
DynamiCrafter ControlnetApply
DynamiCrafter LoadInitNoise
DynamiCrafter ModelLoader
DynamiCrafterI2V
ToonCrafter Decode
ToonCrafter Interpolation

Sharp

Warning, uses experimental package `comfy-env` to attempt a one click isolated install. Will download and use pixi package manager. ComfyUI wrapper around Apple's latest SHARP model (ml-sharp). Monocular 3D Gaussian Splatting in under 1 second. Generate 3D Gaussians from a single image using Apple's SHARP model.

查看仓库•3 个节点

包含节点

SHARP

Load Image with EXIF (Focal Length)
Load SHARP Model
SHARP Predict (Image to PLY)

ComfyUI-EditUtils

A collection of utility nodes for advanced image editing in ComfyUI, supporting multiple AI models including Qwen, Qwen-Image 2.1, Flux2Klein, Flux3Klein and Krea2.

查看仓库•17 个节点

包含节点

advanced/conditioning

EditUtils: Adaptive Longest Edge lrzjason
EditUtils: Any2Image lrzjason
EditUtils: Any2Latent lrzjason
EditUtils: Config Json Parser lrzjason
EditUtils: EditTextEncode lrzjason
EditUtils: Flux2Klein Config Preparer lrzjason
EditUtils: Flux2Klein Edit Text Encode lrzjason
EditUtils: Flux2Klein Model Config lrzjason
EditUtils: Flux2Klein Output Extractor lrzjason
EditUtils: List Extractor lrzjason
EditUtils: Model Config lrzjason
EditUtils: Qwen Config Preparer lrzjason
EditUtils: Qwen Edit Output Extractor lrzjason
EditUtils: Qwen Edit Text Encode lrzjason
EditUtils: Qwen Model Config lrzjason

image

EditUtils: Crop With Pad Info lrzjason
EditUtils: Load Image With Filename lrzjason

ComfyUI-KwaiKolorsWrapper

Rudimentary wrapper that runs [a/Kwai-Kolors](https://huggingface.co/Kwai-Kolors/Kolors) text2image pipeline using diffusers.

查看仓库•5 个节点

包含节点

KwaiKolorsWrapper

(Down)load ChatGLM3 Model
(Down)load Kolors Model
Kolors Sampler
Kolors Text Encode
Load ChatGLM3 Model

MW-ComfyUI_AudioTools

A ComfyUI node containing multiple audio processing tools.

查看仓库•29 个节点

包含节点

⚪Lum3on/AudioTools/AI

Speech Denoise (AI)
Speech-to-Text + SRT (Whisper)
Stem Separator (AI)

⚪Lum3on/AudioTools/Analysis

Audio-Reactive Envelope
BPM Detector / Reactive
Loudness Meter (LUFS)

⚪Lum3on/AudioTools/Effects

Delay / Echo
Fade In
Fade Out
Pitch Shift / Time Stretch
Reverb

⚪Lum3on/AudioTools/Processing

Amplify / Gain
De-Esser
De-Hum (50/60Hz)
De-Plosive (Low Cut)
Mix Audio Tracks
Noise Gate
Normalize Audio
Parametric EQ for Voice
Remove Silence
Standardize Audio (Format/Channels)
Trim Audio
Vocal Compressor

⚪Lum3on/AudioTools/Utility

Concatenate Audio
Pad With Silence
Stereo Panner

⚪Lum3on/AudioTools/Visualization

Compare Waveforms
Display Waveform
Show Audio Info

ComfyUI-Prompt-Combinator

'🔢 Prompt Combinator' is a node that generates all possible combinations of prompts from several lists of strings. '🔢 Prompt Combinator Merger' is a node that enables merging the output of two different '🔢 Prompt Combinator' nodes.

查看仓库•3 个节点

包含节点

prompt_combinator

🔢 Pick Random Prompt from Prompt Combinator
🔢 Prompt Combinator
🔢 Prompt Combinator Merger

ComfyUI_Fill-ChatterBox

Voice Clone and TTS model.

查看仓库•5 个节点

包含节点

ChatterBox

FL Chatterbox Dialog TTS
FL Chatterbox Multilingual TTS
FL Chatterbox TTS
FL Chatterbox Turbo TTS
FL Chatterbox VC

FL Path Animator

Interactive path animator with visual editor for creating animated shapes that follow user-drawn paths. WAN ATI compatible for stable video generation.

查看仓库•1 个节点

包含节点

🎨 FL Path Animator

FL Path Animator

Radiance

HDR, ACES and 32-bit float VFX nodes for ComfyUI: learned SDR to HDR, HDR VAE encode and decode, OCIO colour management, EXR I/O, a pro Viewer, and Nuke / Resolve handoff.

查看仓库•70 个节点

包含节点

FXTD Studios/Radiance/Analyze

◎ Radiance False Color
◎ Radiance HDR Histogram
◎ Radiance QC Pro
◎ Radiance Vectorscope
◎ Radiance Waveform

FXTD Studios/Radiance/Color

◎ Radiance ACES 2.0 Output Transform
◎ Radiance Apply Grade Info
◎ Radiance ARRI Wide Gamut 4
◎ Radiance CDL Transform
◎ Radiance Color Matrix
◎ Radiance Color Space Convert
◎ Radiance DaVinci Wide Gamut
◎ Radiance Expand Dynamic Range
◎ Radiance Float32 Color Correct
◎ Radiance GPU Tensor Ops
◎ Radiance Grade
◎ Radiance Grade Apply
◎ Radiance Grade Match
◎ Radiance HDR Exposure Blend
◎ Radiance HDR Shadow/Highlight Recovery
◎ Radiance HDR Tone Map
◎ Radiance Highlight Synthesis
◎ Radiance Image To Float32
◎ Radiance Log Curve Decode
◎ Radiance Log Curve Encode
◎ Radiance LUT Blend
◎ Radiance OCIO Color Transform
◎ Radiance OCIO Display/View
◎ Radiance White Balance
◎ Radiance Workflow Presets

FXTD Studios/Radiance/Data

◎ Radiance Depth Map
◎ Radiance DNA Reader
◎ Radiance DNA Validator
◎ Radiance DNA Writer

FXTD Studios/Radiance/Draw

◎ Radiance Blend Composite
◎ Radiance Metadata Overlay

FXTD Studios/Radiance/Filter

◎ Radiance 32-bit Denoise
◎ Radiance Compression Artifacts
◎ Radiance Depth of Field
◎ Radiance Film Grain
◎ Radiance Motion Blur
◎ Radiance Rolling Shutter

FXTD Studios/Radiance/Generate

◎ Radiance Cinematic Encoder
◎ Radiance Control
◎ Radiance LoRA Stack
◎ Radiance Manager
◎ Radiance Sampler Pro
◎ Radiance Unified Loader
◎ Radiance VAE Decode
◎ Radiance VAE Encode

FXTD Studios/Radiance/Image

◎ Radiance AI Upscale
◎ Radiance Bit Depth Convert
◎ Radiance Downscale 32-bit
◎ Radiance HDR 360 Generate
◎ Radiance Pro Upscale
◎ Radiance Resolution
◎ Radiance Upscale By Size

FXTD Studios/Radiance/IO

◎ Radiance Write

FXTD Studios/Radiance/Layout

◎ Radiance Debug Probe
◎ Radiance Gate
◎ Radiance Mux
◎ Radiance Note
◎ Radiance Reroute
◎ Radiance Reroute+
◎ Radiance Workspace

FXTD Studios/Radiance/Masking

◎ Radiance Load Image

FXTD Studios/Radiance/Utilities

◎ Radiance Show Text

FXTD Studios/Radiance/Video

◎ Radiance Flicker Analyze
◎ Radiance Temporal Smooth

FXTD Studios/Radiance/Views

◎ Radiance Viewer

ComfyQR

QR generation within ComfyUI. Contains nodes suitable for workflows from generating basic QR images to techniques with advanced QR masking.

查看仓库•4 个节点

包含节点

ComfyQR

Mask QR Errors
QR Code
QR Code (Conformed to Image Size)
QR Code (Split)

Licon MSR

A ComfyUI custom node for creating fixed-frame MP4 reference videos from multiple subject images and a background image, designed for LTX 2.3 MSR (Multiple-Subject-Reference) LoRA workflows.

查看仓库•1 个节点

包含节点

Licon/MSR

Licon MSR

ComfyUI-Qwen-TTS

Qwen-TTS nodes for ComfyUI

查看仓库•6 个节点

包含节点

Qwen3-TTS

🎨 Qwen3-TTS VoiceDesign
🎭 Qwen3-TTS VoiceClone
🎭 Qwen3-TTS VoiceClonePrompt
🎵 Qwen3-TTS CustomVoice
💬 Qwen3-TTS DialogueInference
📇 Qwen3-TTS RoleBank

ComfyUI-LTXVideo

Custom nodes for LTX-Video support in ComfyUI

查看仓库•66 个节点

包含节点

conditioning/video_models

🅛🅣🅧 LTXV Add Guide Advanced
🅛🅣🅧 LTXV Add Guide Advanced Attention
🅛🅣🅧 LTXV Img To Video Advanced
🅛🅣🅧 LTXV Img To Video Condition Only

fluxtapoz

LTX Prepare Attn Injection

latent

🅛🅣🅧 LTXV Spatio Temporal Tiled VAE Decode
🅛🅣🅧 LTXV Tiled VAE Decode

latent/video

🅛🅣🅧 LTXV Add Latents
🅛🅣🅧 LTXV Dilate Latent
🅛🅣🅧 LTXV Select Latents
🅛🅣🅧 LTXV Set Video Latent Noise Masks

Lightricks/audio

🅛🅣🅧 LTXV Audio Only Empty Video Latent
🅛🅣🅧 LTXV Audio Only Model

Lightricks/HDR

🅛🅣🅧 LTXV Save HLG
🅛🅣🅧 LTXVHDR Decode Postprocess
🅛🅣🅧 LTXVSDR To HDR Working Space
🅛🅣🅧 LTXVVAE Force Float32

Lightricks/latent

🅛🅣🅧 Linear transition with overlap
🅛🅣🅧 LTXV Linear Overlap Latent Transition

Lightricks/latents

🅛🅣🅧 LTXV Adain Latent
🅛🅣🅧 LTXV Per Step Adain Patcher
🅛🅣🅧 LTXV Per Step Stat Norm Patcher
🅛🅣🅧 LTXV Stat Norm Latent

lightricks/LTXV

🅛🅣🅧 APG Guider
🅛🅣🅧 Dynamic Conditioning
🅛🅣🅧 Gemma 3 Model Loader
🅛🅣🅧 Gemma 3 Prompt Enhancer
🅛🅣🅧 Guider Parameters
🅛🅣🅧 LTXQ8Patch
🅛🅣🅧 LTXV Apply STG
🅛🅣🅧 LTXV Patcher VAE
🅛🅣🅧 LTXV Prompt Enhancer
🅛🅣🅧 LTXVQ8Lora Model Loader
🅛🅣🅧 Multimodal Guider
🅛🅣🅧 Set VAE Decoder Noise
🅛🅣🅧 STG Advanced Presets
🅛🅣🅧 STG Guider
🅛🅣🅧 STG Guider Advanced
🅛🅣🅧 STG Guider Node

Lightricks/mask_operations

🅛🅣🅧 LTXV Preprocess Masks

ltxtricks

LTX Attention Bank
LTX Attn Block Override
LTX Feta Enhance
LTX Flow Edit CFG Guider
LTX Flow Edit Sampler
LTX Forward Model Pred
LTX Reverse Model Pred
LTX Rf-Inv Forward Sampler
LTX Rf-Inv Reverse Sampler
Modify LTX Model

ltxtricks/attn

LTX Apply Perturbed Attention
LTX Attention Override

LTXV/loaders

🅛🅣🅧 Low VRAM Audio VAE Loader
🅛🅣🅧 Low VRAM Checkpoint Loader

ltxvideo

🅛🅣🅧 Get Tiling Sizes

math/conversion

🅛🅣🅧 Float To Int

prompt

🅛🅣🅧 LTXV Multi Prompt Provider
🅛🅣🅧 Multi Prompt Provider

sampling

🅛🅣🅧 LTXV Base Sampler
🅛🅣🅧 LTXV Extend Sampler
🅛🅣🅧 LTXV In Context Sampler
🅛🅣🅧 LTXV Looping Sampler
🅛🅣🅧 LTXV Tiled Sampler
🅛🅣🅧 Tiled Fusion Sampler

utility

🅛🅣🅧 Image to CPU
🅛🅣🅧 LTXV Set Audio Video Mask By Time

comfyui-PlyPreview

Gaussian Splat PLY loader + preview nodes for ComfyUI. Forked from GeometryPack and repackaged to avoid upstream overwrites. Includes front-end viewer (gsplat.js) bundled locally.

查看仓库•2 个节点

包含节点

PlyPreview

Process Gaussian PLY Enhance

PlyPreview/visualization

Preview Gaussian Enhance

Workflow Prettier

Auto-arrange workflow nodes with 4 layout algorithms, group-aware positioning, alignment tools, and undo

查看仓库•1 个节点

包含节点

utils

Workflow Prettifier

Feedback Sampler

Create Deforum-style zoom animations through iterative feedback loop with pan, rotate, LAB color coherence, anti-blur sharpening, and ControlNet sequence support

查看仓库•1 个节点

包含节点

sampling/custom

Feedback Sampler

hellorob

Makes ComfyUI more sweet

查看仓库•6 个节点

包含节点

nodesweet-hellorob

Audio Reactive Transform
Audio Weights Remap
BBox Detector (Batch Chunked)
BBox Detector (Batch ForEach)
BBox Detector (Batch)
Multiline String Repeater

Vewd

A media viewer node for ComfyUI. Auto-captures all generated media into a grid for easy viewing, sorting, and comparing.

查看仓库•1 个节点

包含节点

image

Vewd

Systms Face Composite

Composites refined face images back onto original video frames using bounding box coordinates with support for replace, alpha blend, and feather blending modes.

查看仓库•1 个节点

包含节点

WanAnimatePreprocess

Face Composite

TimeSlice Nodes

Temporal slit-scan / time-displacement effects for ComfyUI — angled, animated and dual-source slicing on a shared engine.

查看仓库•3 个节点

包含节点

Systms/effects

TimeSlice Dual
TimeSlice Effect
TimeSlice Wave

Comfyui UltraShape1

ComfyUI custom nodes for UltraShape - Image-guided 3D mesh refinement

查看仓库•6 个节点

包含节点

UltraShape

UltraShape Convert To GLB/OBJ
UltraShape Output To Trimesh
UltraShape Refine

UltraShape/Loaders

UltraShape Load Coarse Mesh
UltraShape Load Coarse Mesh From Trimesh
UltraShape Load Model

ComfyUI INOUT

Schema-first input/output parameter nodes for ComfyUI workflows.

查看仓库•8 个节点

包含节点

inout/schema

Schema Audio Parameter
Schema Boolean Parameter
Schema Enum Parameter
Schema Float Parameter
Schema Image Parameter
Schema Integer Parameter
Schema String Parameter
Schema Video Parameter

ComfyUI-MiniMaxH3-Loop

Seamless looping video with MiniMax H3 in ComfyUI: circular padding, loop decode, ControlNet restyling and loop-safe interpolation.

查看仓库•4 个节点

包含节点

image/animation

Loop Interpolate

model/conditioning/minimax

MiniMax H3 Loop Control Video

model/latent/minimax

MiniMax H3 Loop Decode

model/patch/minimax

MiniMax H3 Loop

comfy-workflow-io-nodes

暂无描述信息。

查看仓库•10 个节点

包含节点

Workflow IO/Inputs

Workflow IO Bool Input
Workflow IO Enum Input
Workflow IO Float Input
Workflow IO Image Input
Workflow IO Int Input
Workflow IO Seed Input
Workflow IO Text Input
Workflow IO Video Input

Workflow IO/Outputs

Workflow IO Image Output
Workflow IO Video Output

ComfyUI-Fluxtapoz

ComfyUI nodes for image editing with Flux, such as RF-Inversion and more

查看仓库•22 个节点

包含节点

fluxtapoz

Apply Flux Regional Conds
Configure Modified Flux
Create Flux Regional Cond
Flip Flux Sigmas
Flow Edit Guider
Flow Edit Sampler
Flux DeGuidance
Flux Forward ODE Sampler
Flux Inverse Sampler
Flux Mix Noise
Flux Reverse ODE Sampler
Inverse Flux Model Pred
Outverse Flux Model Pred
Regional Style Model Apply
RF-Edit Double Layers Override
RF-Edit Forward Sampler
RF-Edit Prep Attn Inj
RF-Edit Reverse Sampler
RF-Edit Single Layers Override

fluxtapoz/attn

Apply Flux PAG Attention
Apply Flux SEG Attention
Flux Attention Override

ComfyUI-GIMM-VFI

ComfyUI nodes to use GIMM-VFI frame interpolation

查看仓库•2 个节点

包含节点

GIMM-VFI

(Down)Load GIMMVFI Model

PyramidFlowWrapper

GIMM-VFI Interpolate

ComfyUI-Image-Filters

Image and matte filtering nodes for ComfyUI `image/filters/*`

查看仓库•60 个节点

包含节点

Image-Filters/conditioning

ConditioningSubtract
Inpaint Condition Apply
Inpaint Condition Encode
IP2P Conditioning Advanced

Image-Filters/image

AdaIN (Image)
Alpha Clean (DEPRECATED, use MaskClean)
Alpha Matte (DEPRECATED, use ImageMatting)
Batch Align (RAFT)
Batch Average Image
Batch Normalize (Image)
Better Film Grain
Bilateral Filter Image
Blur Image (Fast)
Clamp Image
Color Match Image
Convert Normals
Depth To Normals
Difference Checker
Enhance Detail
Exposure Adjust
Frequency Combine
Frequency Separate
Game Of Life
Guided Filter Image
Image Constant Color (HSV)
Image Constant Color (RGB)
Image Matting
Keyer
Median Filter Image
Normal Map (Simple)
Poisson Noise Image
Relight (Simple)
Remap Range
Restore Detail
Shuffle Channels
Tonemap
UnTonemap

Image-Filters/image/frames

Extract N Frames
Merge Frames By Index

Image-Filters/image/jitter

Batch Average Un-Jittered
Jitter Image
Un-Jitter Image

Image-Filters/latent

AdaIN (Latent)
AdaIN Filter (Latent)
Batch Normalize (Latent)
Clamp Outliers
LatentNormalizeShuffle
Offset Latent Image
RandnLikeLatent
Sharpen Filter (Latent)
Upscale Hunyuan3Dv2 Latent By

Image-Filters/mask

Blur Mask (Fast)
Dilate/Erode Mask
Mask (Alpha) Clean
Pack Video Mask

Image-Filters/sampling

CustomNoise

Image-Filters/utils

Latent Stats
Print Sigmas
Show Sigmas
Visualize Latents

ComfyUI-Lotus

ComfyUI nodes to use Lotus depth/normal prediction. NOTE:The necessary models can be downloaded from ComfyUI-Manager.

查看仓库•2 个节点

包含节点

ComfyUI-Lotus

Load Lotus Model
Lotus Sampler

NormalCrafterWrapper

暂无描述信息。

查看仓库•2 个节点

包含节点

NormalCrafter

Detail Transfer
NormalCrafter (Process Video)

comfyui-plate-relight

暂无描述信息。

查看仓库•3 个节点

包含节点

image/postprocessing

Add Light from Passes (plate + light)
Light Transfer (plate keeps its pixels)
Temporal Deflicker (flow-guided, for AI passes)

Comfyui-SecNodes

暂无描述信息。

查看仓库•3 个节点

包含节点

SeC

Coordinate Plotter
SeC Model Loader
SeC Video Segmentation

String Converter

Nodes: Convert String To Int, Convert String To Float

查看仓库•2 个节点

包含节点

utils

Convert String To Float
Convert String To Int

Tiled Diffusion & VAE for ComfyUI

The extension enables large image drawing & upscaling with limited VRAM via the following techniques: 1.Two SOTA diffusion tiling algorithms: [a/Mixture of Diffusers](https://github.com/albarji/mixture-of-diffusers) and [a/MultiDiffusion](https://github.com/omerbt/MultiDiffusion) 2.pkuliyi2015's Tiled VAE algorithm.

查看仓库•4 个节点

包含节点

_for_testing

SpotDiffusion Parameters
Tiled Diffusion
Tiled VAE Decode
Tiled VAE Encode

ComfyUi-Untwisting-RoPE

暂无描述信息。

查看仓库•3 个节点

包含节点

model_patches/Untwisting RoPE

RF Inversion
Unofficial Extensions
Untwisting RoPE

ComfyUI Upscaler TensorRT

This project provides a Tensorrt implementation for fast image upscaling inside ComfyUI (3-4x faster)

查看仓库•2 个节点

包含节点

tensorrt

Load Upscale Tensorrt Model
Upscaler Tensorrt ⚡

Various ComfyUI Nodes by Type

Nodes: JWInteger, JWFloat, JWString, JWImageLoadRGB, JWImageResize, ...

查看仓库•55 个节点

包含节点

jamesWalker55

Apply Mask Sequence to Latent
Audio Blend
Datetime String
Extract Image Sequence From Batch
Float
Float Absolute Value
Float Add
Float Divide
Float Maximum
Float Minimum
Float Multiply
Float Subtract
Float to Integer
Float to String
Get Image Batch Count
Image Contrast
Image Crop to Closest SDXL Resolution
Image Extract From Batch
Image Flip
Image Levels
Image Mix
Image Resize
Image Resize by Factor
Image Resize by Longer Side
Image Resize by Shorter Side
Image Resize to Closest SDXL Resolution
Image Resize to Square
Image Saturation
Image Stack Channels
Integer
Integer Absolute Value
Integer Add
Integer Divide
Integer Maximum
Integer Minimum
Integer Multiply
Integer Subtract
Integer to Float
Integer to String
Join Mask Sequence
Loop Image Sequence
Mask Like Image Size
Mask Resize
Mask Sequence From Mask
RAFT Estimate
RAFT Flow to Image
String
String (Multiline)
String Concatenate
String Get Line
String Replace
String Split
String to Float
String to Integer
String Unescape

CustomNodeComfyMath

暂无描述信息。

查看仓库•53 个节点

包含节点

math/bool

BoolBinaryOperation
BoolUnaryOperation

math/conversion

BoolToInt
BreakoutVec2
BreakoutVec3
BreakoutVec4
ComposeVec2
ComposeVec3
ComposeVec4
FloatToInt
FloatToNumber
IntToBool
IntToFloat
IntToNumber
NumberToFloat
NumberToInt

math/float

FloatBinaryCondition
FloatBinaryOperation
FloatUnaryCondition
FloatUnaryOperation
NumberBinaryCondition

math/graphics

NearestSDXLExtendedResolution
NearestSDXLResolution
SDXLExtendedResolution
SDXLResolution

math/int

IntBinaryCondition
IntBinaryOperation
IntUnaryCondition
IntUnaryOperation

math/number

NumberBinaryOperation
NumberUnaryOperation

math/Number

NumberUnaryCondition

math/vec2

Vec2BinaryCondition
Vec2BinaryOperation
Vec2ScalarOperation
Vec2ToScalarBinaryOperation
Vec2ToScalarUnaryOperation
Vec2UnaryCondition
Vec2UnaryOperation

math/vec3

Vec3BinaryCondition
Vec3BinaryOperation
Vec3ScalarOperation
Vec3ToScalarBinaryOperation
Vec3ToScalarUnaryOperation
Vec3UnaryCondition
Vec3UnaryOperation

math/vec4

Vec4BinaryCondition
Vec4BinaryOperation
Vec4ScalarOperation
Vec4ToScalarBinaryOperation
Vec4ToScalarUnaryOperation
Vec4UnaryCondition
Vec4UnaryOperation

Masquerade Nodes

This is a low-dependency node pack primarily dealing with masks. The author recommends using Impact-Pack instead (unless you specifically have trouble installing dependencies).

查看仓库•20 个节点

包含节点

Masquerade Nodes

Blur
Change Channel Count
Combine Masks
Constant Mask
Convert Color Space
Create Rect Mask
Cut By Mask
Get Image Size
Image To Mask
Incrementer
Make Image Batch
Mask Morphology
Mask To Region
Mix Color By Mask
Mix Images By Mask
Paste By Mask
Prune By Mask
Separate Mask Components
Unary Image Op
Unary Mask Op

RES4LYF

Advanced samplers with new noise scaling math to enable SDE sampling with all publicly available rectified flow models; new unsampling/noise inversion methods and other advanced techniques for inpainting and/or guiding the sampling process with latent images. 40 sampler types, 20 noise types, 7 noise scaling modes, in a single node. Also includes a wide variety of QoF and other utility nodes for manipulating sigmas, latents, images, and more.

查看仓库•285 个节点

包含节点

advanced/conditioning

CrossAttn_EraseReplace_HiDream

essentials/mask

Mask Bounding Box Aspect Ratio

image

Mask Sketch

RES4LYF/conditioning

CLIPTextEncodeFluxUnguided
ClownRegionalConditioning
ClownRegionalConditioning_AB
ClownRegionalConditioning_ABC
ClownRegionalConditioning2
ClownRegionalConditioning3
ClownRegionalConditionings
ConditioningAdd
ConditioningAverageScheduler
ConditioningBatch4
ConditioningBatch8
ConditioningDownsample (T5)
ConditioningOrthoCollin
ConditioningTruncate
ConditioningZeroAndTruncate
StableCascade_StageB_Conditioning64
StyleModelApplyStyle

RES4LYF/images

Film Grain
Frame Select
Frames Concat
Frames Slice
Frequency Separation Hard Light
Frequency Separation Hard Light LAB
Frequency Separation Linear Light
Image Channels LAB
Image Crop Location Exact
Image Gaussian Blur
Image Get Color Swatches
Image Grain Add
Image Median Blur
Image Pair Split
Image Repeat Tile To Size
Image Sharpen FS
Masks From Color Swatches
Masks From Colors
SetImageSize
SetImageSizeWithScale

RES4LYF/latents

EmptyLatentImage64
EmptyLatentImageCustom
Frame Select Latent
Frame Select Latent Raw
Frames Concat Latent
Frames Concat Latent Raw
Frames Slice Latent
Frames Slice Latent Raw
Latent Batcher
Latent Channels From To
Latent Clear State Info
Latent Display State Info
Latent Get Channel Means
Latent Match Channelwise
Latent Normalize Channels
Latent Replace State Info
Latent to Cuda
Latent to RawX
Latent Transfer State Info
Latent TrimVideo State Info
LatentBatch_channels
LatentBatch_channels_16
LatentPhaseMagnitude
LatentPhaseMagnitudeMultiply
LatentPhaseMagnitudeOffset
LatentPhaseMagnitudePower
LatentUpscaleWithVAE

RES4LYF/legacy/sampler_extensions

Legacy2_ClownInpaint
Legacy2_ClownInpaintSimple
Legacy2_ClownsharKSamplerAutomation
Legacy2_ClownsharKSamplerAutomation_Advanced
Legacy2_ClownsharKSamplerGuide
Legacy2_ClownsharKSamplerGuides
Legacy2_SamplerOptions_GarbageCollection

RES4LYF/legacy/sampler_options

Legacy2_ClownOptions_FrameWeights
Legacy2_ClownOptions_SDE_Noise

RES4LYF/legacy/samplers

Legacy_ClownSampler
Legacy_ClownsharKSampler
Legacy_ClownsharKSamplerGuides
Legacy_SharkSampler
Legacy2_ClownSampler
Legacy2_ClownSamplerAdvanced
Legacy2_ClownsharKSampler

RES4LYF/legacy/samplers/ultracascade

UltraSharkSampler Tiled

RES4LYF/legacy/samplers/UltraCascade

Legacy2_UltraSharkSampler

RES4LYF/loaders

ClownModelLoader
FluxLoader
SD35Loader

RES4LYF/masks

Frames Concat Masks
Frames Latent ReverseOrder
Frames Masks Uninterpolate
Frames Masks ZeroOut
MaskEdge
MaskFloatToBoolean
Masks Unpack 16
Masks Unpack 4
Masks Unpack 8
MaskToggle
TemporalCrossAttnMask
TemporalMaskGenerator
TemporalSplitAttnMask
TemporalSplitAttnMask (Midframe)

RES4LYF/model

ClownpileModelWanVideo

RES4LYF/model_patches

FluxGuidanceDisable
FluxOrthoCFGPatcher
ReAuraPatcher
ReAuraPatcherAdvanced
ReChromaPatcher
ReChromaPatcherAdvanced
ReFluxPatcher
ReFluxPatcherAdvanced
ReHiDreamPatcher
ReHiDreamPatcherAdvanced
ReLTXVPatcher
ReLTXVPatcherAdvanced
ReReduxPatcher
ReSD35Patcher
ReSD35PatcherAdvanced
ReSDPatcher
ReWanPatcher
ReWanPatcherAdvanced
TorchCompileModelAura
TorchCompileModelFluxAdv
TorchCompileModels
TorchCompileModelSD35

RES4LYF/model_shift

ModelSamplingAdvanced
ModelSamplingAdvancedResolution
ModelTimestepPatcher

RES4LYF/noise

AdvancedNoise
LatentNoiseBatch_fractal
LatentNoiseBatch_gaussian
LatentNoiseBatch_gaussian_channels
LatentNoiseBatch_perlin
LatentNoised
LatentNoiseList

RES4LYF/patchers

LayerPatcher

RES4LYF/precision

Conditioning Recast FP64
Set Precision
Set Precision Advanced
Set Precision Universal
Sigmas Recast

RES4LYF/sampler_extensions

ClownGuide
ClownGuide AdaIN (HiDream)
ClownGuide AttnInj (HiDream)
ClownGuide Mean
ClownGuide Style
ClownGuide_FrequencySeparation
ClownGuide_Style_EdgeWidth
ClownGuide_Style_TileSize
ClownGuide_StyleNorm_Advanced_HiDream
ClownGuides
ClownGuides Sync
ClownGuides Sync_Advanced
ClownGuidesAB
ClownStyle_Attn_MMDiT
ClownStyle_Attn_UNet
ClownStyle_Block_MMDiT
ClownStyle_Block_UNet
ClownStyle_Boost
ClownStyle_MMDiT
ClownStyle_ResBlock_UNet
ClownStyle_SpatialBlock_UNet
ClownStyle_TransformerBlock_UNet
ClownStyle_UNet

RES4LYF/sampler_options

ClownOptions Automation
ClownOptions Combine
ClownOptions Cycles
ClownOptions Detail Boost
ClownOptions Extra Options
ClownOptions Frameweights
ClownOptions Implicit Steps
ClownOptions Momentum
ClownOptions SDE
ClownOptions SDE Mask
ClownOptions Sigma Scaling
ClownOptions Step Size
ClownOptions Swap Sampler
ClownOptions Tile
ClownOptions Tile Advanced
ClownOptions_FlowGuide
ClownSamplerSelector
SharkOptions
SharkOptions Guide Cond
SharkOptions Guide Conds
SharkOptions Guider Input
SharkOptions Start Step
SharkOptions UltraCascade Latent

RES4LYF/samplers

BongSampler
ClownSampler
ClownSamplerAdvanced
ClownsharkChainsampler
ClownsharKSampler
SharkChainsampler
SharkSampler

RES4LYF/schedulers

ClownScheduler
Constant Scheduler
Linear Quadratic Advanced
Sigmas Iteration Karras
Sigmas Iteration Polyexp
Tan Scheduler
Tan Scheduler 2
Tan Scheduler 2 Simple

RES4LYF/sigmas

Sigmas Abs
Sigmas AdaptiveNoiseFloor
Sigmas AdaptiveStep
Sigmas Add
Sigmas Append
Sigmas ArcCosine
Sigmas ArcSine
Sigmas ArcTangent
Sigmas Attractor
Sigmas CatmullRom
Sigmas Chaos
Sigmas Cleanup
Sigmas CNFInverse
Sigmas CollatzIteration
Sigmas Concat
Sigmas ConwaySequence
Sigmas Count
Sigmas CrossProduct
Sigmas DeleteBelowFloor
Sigmas DeleteDuplicates
Sigmas DotProduct
Sigmas Easing
Sigmas Fmod
Sigmas Frac
Sigmas From Text
Sigmas GammaBeta
Sigmas Gaussian
Sigmas GaussianCDF
Sigmas GilbreathSequence
Sigmas HarmonicDecay
Sigmas Hyperbolic
Sigmas If
Sigmas InvLerp
Sigmas KernelSmooth
Sigmas LambertW
Sigmas LangevinDynamics
Sigmas Lerp
Sigmas LinearSine
Sigmas Logarithm2
Sigmas Modulus
Sigmas Mult
Sigmas Noise Inversion
Sigmas NormalizingFlows
Sigmas Pad
Sigmas Percentile
Sigmas PersistentHomology
Sigmas Power
Sigmas QuantileNorm
Sigmas Quotient
Sigmas ReactionDiffusion
Sigmas Resample
Sigmas Rescale
Sigmas RiemannianFlow
Sigmas SetFloor
Sigmas Sigmoid
Sigmas SmoothStep
Sigmas Split
Sigmas Split Value
Sigmas SquareRoot
Sigmas Start
Sigmas StepwiseMultirate
Sigmas TimeStep
Sigmas Truncate
Sigmas Unpad
Sigmas Variance Floor
Sigmas ZetaEta
Sigmas2 Add
Sigmas2 Mult
SigmasPreview
SigmasSchedulePreview

RES4LYF/text

TextBox1
TextBox2
TextBox3
TextBoxConcatenate
TextConcatenate
TextShuffle
TextShuffleAndTruncate
TextTruncateTokens

RES4LYF/utilities

SeedGenerator

RES4LYF/vae

PrepForUnsampling
StableCascade_StageC_VAEEncode_Exact
VAEEncodeAdvanced
VAEStyleTransferLatent

websocket_image_save

暂无描述信息。

查看仓库•1 个节点

包含节点

image

Save Image (Websocket)