Extensions/ComfyUI Timesaver Nodes
ComfyUI Extension

ComfyUI Timesaver Nodes

ComfyUI nodes from Timesaver.

By AlexYez·Created 2 years ago·Updated 3 days ago· 21
AlexYez/comfyui-timesaver
Nodes88
On cloudLocal install
CategoryTS/Text, TS/Video
Stars21
Updated3 days ago

Nodes (88)

TS Angle Select

Point the camera, get the prompt for that exact view

TS/Text
TS Animation Preview

Actually see your animation before you pay for the encode

TS/Video
TS Audio Loader

The audio loader with a waveform you can actually use

TS/Audio
TS Audio Preview

Audition audio in the graph before you commit to a file

TS/Audio
TS Audio Visualizer

SoundCloud-style waveform images, generated in the graph

TS/Audio
TS Auto Tile Size

Stop doing tile math in your head

TS/Image/Tiles
TS Batch Load Image

The name lies — it loads one image, and that's the point

TS/Image/Batch
TS Batch Prompt Loader

Run a hundred prompts through the same workflow

TS/Text
TS Batch Source

Turn one graph into a hundred independent runs

TS/Utils
TS Batch Write

Get your results on disk before the batch finishes

TS/Files
TS Remove Background

BiRefNet background removal with hair you can believe

TS/Image/Cutout
TS Color Match

Make every shot agree with one reference frame

TS/Image/Color
TS Compare

The before/after wipe that doesn't lie about video

TS/Utils
TS Crop To Mask

Crop to the interesting part, process only that

TS/Image/Tiles
TS DLSS Upscaler

This node borrows your GPU's game upscaler for real frames

TS/Video
TS Edit Align

Your Qwen Edit Came Back Three Pixels Off — Here's How to Put It Back

TS/Image/Retouch
TS Files Downloader

Download every model a workflow needs, in one shot

TS/Files
TS Film Emulation

Cinematic film looks without leaving the graph

TS/Image/Color
TS Float Slider

A clean float knob, and not a math node in sight

TS/Utils
TS Frame Interpolation

Buttery-smooth video from choppy model output

TS/Video
TS Free VRAM

A wire that clears your GPU at the exact right moment

TS/Utils
TS Get Image Megapixels

How big is that image, actually?

TS/Image/Batch
TS Get Image Size

The longer side or the shorter side — pick one

TS/Image/Batch
TS Group Bypasser

A bypass switch for every group in your workflow

TS/Utils
TS H3 Audio Inject

Make MiniMax H3 say the line you actually recorded

TS/Video
TS H3 Fast VAE Decode
TS/Video
TS H3 Regenerate
TS/Video
TS H3 Regenerate Model
TS/Video
TS Ideogram Designer

Design Ideogram 4 prompts visually, not in JSON

TS/Ideogram
TS Image Batch Cut

Trim the junk frames off the front and back

TS/Image/Batch
TS Image Batch to Image List

Split and iterate

TS/Image/Batch
TS Image Depth

Depth maps for stills that actually hold their range

TS/Image/Depth
TS Image List to Image Batch

The glue node that turns a list of images back into a batch

TS/Image/Batch
TS Image Prompt Injector

Get an LLM's prompt into the sampler without rewiring anything

TS/Image/Batch
TS Image Resize

The resize node that finally covers every mode you actually use

TS/Image/Size
TS Image Tile Merger

Stitch processed tiles back into one seamless image

TS/Image/Tiles
TS Image Tile Splitter

Cut a huge image into overlapping tiles your GPU can actually handle

TS/Image/Tiles
TS Int Slider

A clean integer knob so you don't drag a math node onto your graph

TS/Utils
TS Krea 2 Text Fusion

Krea 2 Keeps Ignoring You — This Is the One Number That Fixes It

TS/Utils
TS Lama Cleanup

Paint over the tourist, watch the watermark vanish, no Photoshop trip required

TS/Image/Retouch
TS Langevin Inpaint

An inpaint sampler that makes the repair agree with its surroundings

TS/Image/Retouch
TS Latent Upscale

The right way to upscale MiniMax H3 video without melting your GPU

TS/Video
TS Load Checkpoint

A Checkpoint Loader for a File Nothing Else on Your Disk Can Open

TS/Loaders
TS Load Diffusion Model

The `UNETLoader` for Locked Files, Plus the Detail Everyone Else Would Have Missed

TS/Loaders
TS Load LoRA, model only

For Video Graphs There's No CLIP Wire — This Is the LoRA Loader That Admits It

TS/Loaders
TS LoRA Loader

Six LoRAs in one node, reorder by dragging, and it expands into the real thing

TS/utils
TS LoRA Unmerged

Your turbo LoRA is getting rounded off before it ever runs

TS/Utils
TS LTX Final Latent Selector

Pick which LTX stage wins before you decode, so the loser never runs

TS/Video/HDR
TS LTX First/Last Frame

Pin the start and end frames, let LTX interpolate between them

TS/Video
TS LTX HDR Decode

The one decode that gives you both a watchable preview and a true HDR master

TS/Video/HDR
TS LTX HDR Guide

One node per guide frame that feeds both LTX stages — and never runs the wrong branch

TS/Video/HDR
TS LTX Load HDR EXR

Read an EXR the way the HDR pipeline needs — without flattening everything above 1.0

TS/Video/HDR
TS LTX HDR Settings

One switch that turns the whole LTX 2.5 HDR path on — and off for free

TS/Video/HDR
TS LTX HDR Stats

Is the HDR range still there? This node answers with numbers

TS/Video/HDR
TS LTX HDR VAE

The same VAE file, forced to float32 — because that's where HDR lives

TS/Video/HDR
TS Math Int

Two integers in, one integer out — the math node that stops the Primitive tangles

TS/Utils
TS Matting (ViTMatte)

From a sloppy SAM mask to real hair-level transparency

TS/Image/Cutout
TS Model Resize

Stop Googling \"832×480 or 1280×720?\" — Pick the Model and Let the Node Do the Maths

TS/Image/Size
TS Multi Reference

Three reference images into the conditioning stream, one node

TS/Conditioning
TS Music Stems

Karaoke, remixes, and clean vocals — all inside the graph

TS/Audio
TS NAG

At CFG 1 Your Negative Prompt Is Decoration — NAG Puts It Back

TS/Utils
TS Prompt Builder

Wildcard prompts that don't put a swimsuit on a winter street

TS/Text
TS Prompt Library

51 edit prompts someone already tested, free to copy

TS/Text
TS Qwen 3

A local Qwen VLM that captions, describes, and writes your prompts

TS/LLM
TS Resolution Selector

The 'always a valid canvas size' node you'll stick in every workflow

TS/Image/Size
TS Restore From Crop

Paste the sharpened face back without a visible seam

TS/Image/Tiles
TS RT Prompt Enhancer

Gemma 4 sitting in your graph, no buttons, no API key

TS/LLM
TS RTX Upscaler

Real-time upscaling on NVIDIA's hardware — speed over invention

TS/Video
TS SAM Media Loader

Stop hand-typing SAM3 point JSON — just click the picture

TS/Image/Cutout
TS Shifted Sigmas

The sampling schedule your Qwen turbo LoRA was actually distilled on

TS/Utils
TS Silero Stress

The Russian text fixer that stops TTS from saying the wrong word

TS/Text
TS Silero TTS

Russian text-to-speech that lives inside your graph

TS/Audio
TS Smart Batch

Batch two images without breaking when one isn't there

TS/Image/Batch
TS Smart Inpaint

The one-node inpaint that does the crop, sample, and stitch itself

TS/Image/Retouch
TS Smart Switch

A switch that doesn't blow up when a branch isn't wired

TS/Utils
TS Song Creator

The lyrics box that puts the stress where you meant it

TS/Text
TS Style Prompt Selector

157 art styles you can browse instead of guessing the phrase

TS/Text
TS Super Prompt

Speak your idea, get a production-ready prompt back

TS/LLM
TS Super Prompt RT

Prompt enhancement on Google's phone runtime — twice as fast, a fifth of the VRAM

TS/LLM
TS Universal Inpaint Sampler

Inpaint any model — no Fill checkpoint, no ControlNet, just this sampler

TS/Image/Retouch
TS VAE Fix

Your Qwen decode has a 2-pixel grid — TS VAE Fix deletes it before your upscaler eats it

TS/Image/Retouch
TS Video Cut

The trim node that keeps picture and sound in sync

TS/Video
TS Video Depth

Steady depth maps for whole clips — not 24 flickering stills

TS/Video
TS Video Info

Turn video_info into numbers you can actually route on

TS/Video
TS Video Loader

A video loader with a timeline, so a two-second cut doesn't cost an hour

TS/Video
TS Video Saver

H.264 to share, ProRes to edit, EXR to master

TS/Video
TS Whisper

Local transcription with SRT out — no API key, no cloud

TS/Audio
TS YouTube Chapters

Your Resolve markers, turned into a YouTube chapter list in one step

TS/Files
Readme
<div align="center"> <img src="icon.png" alt="Timesaver" width="100" />

Timesaver Nodes for ComfyUI

Nodes for images, video, audio and prompts, plus tools for organizing workflows.

Русский · Workflow examples · License

</div>

Installation

In ComfyUI Manager, search for Timesaver. For a manual installation, run these commands from the ComfyUI directory:

cd custom_nodes
git clone https://github.com/AlexYez/comfyui-timesaver
cd comfyui-timesaver
python -m pip install -r requirements.txt

Use the Python interpreter that runs ComfyUI. Restart ComfyUI, then search for TS on the canvas. No separate frontend build is required.

To update a manual installation, run git pull --ff-only from the pack directory, install updated requirements with the same interpreter and restart ComfyUI.

<a id="-node-reference"></a> <a id="image"></a><a id="video"></a><a id="hdr"></a><a id="audio"></a><a id="llm"></a><a id="text"></a><a id="ideogram"></a><a id="files"></a><a id="loaders"></a><a id="utils"></a><a id="conditioning"></a>

Using the nodes

  • Image — resize and alignment, masks, inpainting and restoration.
  • Video — loading, trimming, saving, upscaling and HDR tools.
  • Audio and prompts — audio editing, speech tools, prompt construction and model-assisted rewriting.
  • Workflow tools — sliders, switches, file downloads and graph layout commands.

Open a node’s help in ComfyUI for its inputs and options. The same English and Russian reference and example workflows are available here.

Some nodes need model weights, an optional Python package or a separately installed application. Check the node's input tooltips and follow any dependency message in the ComfyUI console. If a node is missing, look for [TS Timesaver] in that console. Start ComfyUI with TS_VERBOSE_STARTUP=1 for the full registration report. See package metadata for version and dependency details.

На русском

Timesaver добавляет ноды обработки изображений, видео, звука и промптов, а также инструменты для работы с графом.

Подсказки по конкретным нодам доступны в ComfyUI и в справочнике. Готовые графы собраны в примерах workflow.

В ComfyUI Manager найдите Timesaver. Для ручной установки клонируйте пак в custom_nodes и установите зависимости командами выше. Используйте Python, которым запускается ComfyUI. После перезапуска найдите ноды по TS в поиске канваса.

Для ручного обновления выполните git pull --ff-only в папке пака, установите обновлённые зависимости тем же Python и перезапустите ComfyUI. Для отдельных нод могут понадобиться модели, дополнительные пакеты или внешние приложения. Смотрите подсказки к входам и сообщения в консоли ComfyUI. Если нода не появилась, найдите в консоли [TS Timesaver]. Флаг окружения TS_VERBOSE_STARTUP=1 включает полный отчёт регистрации при запуске.

Код распространяется по лицензии MIT. У сторонних моделей, SDK и приложений собственные условия.