Extensions/ComfyUI Handy Nodes
ComfyUI Extension

ComfyUI Handy Nodes

Handy Nodes - chunk large video, audio, and convenience nodes, Multi Image and Prompt nodes, etc.

By trashkollector·Created about a year ago·Updated 8 days ago· 4
trashkollector/TKNodes
Nodes34
On cloudLocal install
CategoryTKNodes, audio
Stars4
Updated8 days ago

Nodes (34)

Audio Merge/Fuse

Mix your audio tracks without leaving ComfyUI — the Audio Merge/Fuse node

TKNodes
Speaker Talk Times

The boring little input node your diarization workflow is built on

TKNodes
Resample Audio for new FPS

The node that stops your video/audio sync from falling apart in V2V

TKNodes
Audio → Waveform Tensor

How to get raw samples out of ComfyUI's AUDIO type

audio
Calculate LTX Frames

The math node that keeps your chunks on LTX's picky frame grid

TKNodes/video
Cross Dissolve Effect

Make your stitched-together video segments feel like one take

TKNodes
Fade in Video

The two-minute fix for videos that start on a jarring hard cut

TKNodes
Large Video Chunker
TKNodes/video
Identify Speakers using Silence Breaks

Fake speaker detection that actually works for AI dialogue

TKNodes
Merge audio list to master audio

Concat a list of clips into one clean track

HandyNodes-KT
Multi Image + Prompt

One clean widget for a batch of image-to-video scenes

TKNodes/image
Multi Image Select

Load twelve reference images into one looper-friendly list

TKNodes/image
Multi Prompt

Four prompts, one wire, and the node on the other end

TKNodes/prompt
GUI - Photo User Inputs

One pair of dials so your photo workflow has a single place to set size

TKNodes
Print Value to log

The debug node that tells you what's actually flowing through your wires

debug
Enhanced Prompt with camera descriptives

Dress up your prompts the way video models actually want

TKNodes
Prompt Looper

Alternate up to four scenes in a loop without a spaghetti graph

TKNodes
Prompt Looper Advanced

Loop through image+prompt lists without retyping anything

TKNodes
Smart Audio Chunker

Split long audio on silence so generation never cuts a word in half

HandyNodes-KT
Smart Video Chunker

Silence-based video+audio chunking for LTX 2.3 and Wan 2.2

TKNodes
Snap Frames to boundry rules

End the clumsy frame-count math for LTX and Wan

TKNodes
Extract nTh Audio track

Pull one speaker's dialogue out of the full mix, LTX-ready

TKNodes
Get a Track details from Track

A two-way switch that swaps prompt and start image per speaker

TKNodes
User supplied tracks

Count the real number of talk tracks across two speakers

TKNodes
Video Transition Detector

Finding real scene boundaries in your video

TKNodes/video
Scene Detection - Get Video Chunk at index

Cut on Scene Changes, Not on Frame 81

TKNodes
Scene Detection - Get Total Transitions

How Many Chunks Did the Detector Actually Make?

TKNodes
Trim Audio (Booleans)

Trim the edges off audio without rebuilding the workflow

TKNodes
Trim Frames and Audio

Trim an image sequence and its audio to the exact frame you asked for

TKNodes
Trim Padding used for Smooth Transition

Strip the crossfade padding back off your video chunks

TKNodes/video
Video Audio Fuse

Bolt up to three audio streams onto your video in one node

TKNodes
Video User Inputs

Pick a video resolution by dragging a dot, not doing math

TKNodes
Video User Inputs Basic

The stripped-down resolution picker when you just need W and H

TKNodes
Video User Inputs - V2

One node for video width, height, frames and fps

TKNodes
Readme

See workflow folder for example workflows of various nodes

TKLargeVideoChunker

Used to chunk very large files to avoid out of memory conditions. Also chunks audio. Must run within FOR LOOP/END

<img width="600" alt="Screenshot 2026-10-31 123957" src="https://github.com/user-attachments/assets/8af55403-179c-4dd3-b0d9-aaeeb53e6b47" />

TKSmartVideoChunker

Silence-based video/audio chunking for LTX 2.3 / Wan 2.2. Looks for silence in audio to create chunk breaks.
This is helpful when speakers take a breath and we don't cut off speaker while talking. Chunking is required to get around VRAM issues. For Low VRAM set chunk size lower"

Silence-based video/audio chunking for LTX 2.3 or Wan 2.2. Slices at native fps, resamples to target_fps, and snaps to a valid frame count

<img width="432" alt="Screenshot 2026-08-05 131620" src="https://github.com/user-attachments/assets/839ac1e9-1feb-44c0-9039-2de24a1dca77" />

TKSmartAudioChunker

Silence based audio chunker.. used in workflow for Singing or Talking, so it never breaks middle sentence. TKSmartVideoChunker will call this node for the audio breaks.

TKMultiImagePrompt

Manager a group of images and prompts in a uniform way. Used together with FOR LOOP START / END <img width="611" height="694" alt="Screenshot 2026-10-31 124505" src="https://github.com/user-attachments/assets/e7d9ec07-4afe-4639-84bf-2520ce96666d" />

TKPromptLooperAdv

Prompt Looper can handle unlimited number of images/prompts within a looping construct

<img width="600" alt="Screenshot 2026-10-31 125301" src="https://github.com/user-attachments/assets/37939d48-b5ea-4b2c-9cac-78c09620594e" />

TKSceneDetection

Video Scene Detection

<img width="600" alt="Screenshot 2026-10-31 124133" src="https://github.com/user-attachments/assets/30234a7f-dc77-4a08-a083-e47fbbcf8204" />

TKVideoUserInputsV2

Convenience node for collection size data for video.

<img width="500" alt="Screenshot 2026-10-31 125749" src="https://github.com/user-attachments/assets/8fe3f31a-51f9-4ed9-9006-d55937a26fd0" />

TKPrintValueToLog

Print value to log, helpful for debug or status of workflow

TKNodes (Handy Nodes for ComfyUI)

A dictionary that contains the friendly/humanly readable titles for the nodes

NODE_DISPLAY_NAME_MAPPINGS = { "TKLargeVideoChunker": "Large Video Chunker",

 "TKTransitionDetector": "Video Transition Detector",
 "TKTransitionDetectorChunk": "Scene Detection - Get Video Chunk at index",
 "TKTransitionScenesCount": "Scene Detection - Get Total Transitions",
 
 "TKPromptEnhanced": "Enhanced Prompt with camera descriptives",
 "TKTrimAudioWithBooleans": "Trim Audio (Booleans)",
 "TKCalcLTXFrames":    "Calculate LTX Frames ",
 "TKVideoUserInputs": "Video User Inputs",
 "TKVideoUserInputsV2": "Video User Inputs - V2",
 "TKPhotoUserInputs": "GUI - Photo User Inputs",
 "TKVideoUserInputsBasic": "Video User Inputs Basic",
 "TKVideoAudioFuse": "Video Audio Fuse",
 "TKAudioFuse": "Audio Merge/Fuse",
 "TKSmartAudioChunker": "Smart Audio Chunker",
 "TKSmartVideoChunker": "Smart Video Chunker",
 "TKSimpleVideoChunker":"Simple Video Chunker",
 "TKAudioUnwrap": "Audio → Waveform Tensor",
 "TKPrintValueToLog": "Print Value to log",
 "TKSpeakerAudioTrackExtractor": "Extract nTh Audio track",
 "TKMergeAudioList": "Merge audio list to master audio",
 "TKTotalTracksInAudio": "User supplied tracks",
 "TKLocateSpeakersUsingSilenceBreaks": "Identify Speakers using Silence Breaks",
 "TKTrimImageOverlap": "Trim Padding used for Smooth Transition",
 "TKSpeakerDataFromTrack" : "Get a Track details from Track",
 "TKAudioSpeakerTalkTime": "Speaker Talk Times",
 "TKFadeInVideo": "Fade in Video",
 "TKPromptLooper": "Prompt Looper",
 "TKCrossDissolve":"Cross Dissolve Effect",
 "TKTrimFrames": "Trim Frames and Audio",

 "TKSnapFrames" : "Snap Frames to boundry rules",
 "TKAudioToFPSMatcher" :"Resample Audio for new FPS",
 "TKMultiImagePrompt": "Multi Image + Prompt",
 "TKPromptLooperAdv": "Prompt Looper Advanced",
 "TKMultiImageSelect": "Multi Image Select",
 "TKMultiPrompt": "Multi Prompt",

}

Manager install

Search for "Handy Nodes" in Comfy Manager

for manual install

https://github.com/trashkollector/TKNodes

go to the custom_nodes folder in comfy

git clone https://github.com/trashkollector/TKNodes

Workflows https://github.com/trashkollector/TKNodes/tree/main/workflow