Mindket

Photoroom background removal for new Google Drive images

Newversion 1 · updated

Overview

An n8n workflow that watches a Google Drive folder, sends each new image to Photoroom to remove its background, adds the colour and padding you choose, and saves the PNG in a second Drive folder.

Photoroom background removal for new Google Drive images is an n8n workflow in the Marketing & SEO category, listed by Mindket. It is free. This is version 1, last updated on . Download it on this page or copy its JSON, then import it into an n8n canvas. Nothing runs until you activate it in n8n.

At a glance

Runs in
  • n8n Cloud: import the file and publish it
  • Your own n8n server: the same file and steps
  • Google Drive: one folder to watch and a different folder for the results
  • Photoroom: an API key from your account

Platform

Connects 2 apps

How it works

Trigger

New image in a Drive folder

It starts when a new file appears in the Google Drive folder you watch, checked every minute. It brings:

  • The file’s name and Drive id
  • The image itself, downloaded from Drive

Actions

  1. Downloads the new image and reads its size
  2. Reads your choices: background colour, padding, output size, output folder and key
  3. Sends the image to Photoroom, which removes the background and applies your colour and padding
  4. Saves the result as a PNG named BG-Removed plus the original name in your output folder

Result

A PNG with the background removed, your colour and padding applied, saved in a second Google Drive folder

Integrations

What you need before you start.

Google Drive

Image source and storage

Watches the input folder, downloads each image and saves the result.

NeedsA Google Drive OAuth2 credential and two folders

Photoroom

Image editing

Removes the background and applies the colour and padding.

NeedsA Photoroom API key

Workflow check

Checked by Mindket on 13 Nov 2026

Steps
12 steps, starting on a Google Drive event
AI
No step calls an AI model
Sign-ins
Signs in to: Google Drive, Google service account and a web service
API keys
No API key is left in the file; 1 blank in it for your own key
Step types
Mindket’s checker reads all 9 of its step types

Read from the workflow’s file, not from a run.

About

What it is

This n8n workflow cuts the background out of photos you drop in a Google Drive folder. Every minute it looks for new files. Each new image is downloaded, and its size is read. A Set step holds your choices: the background colour, the padding, the output size and the folder for results. Photoroom removes the background and applies those choices. Google Drive stores the finished PNG. Twelve nodes run it, beside two sticky notes.

Who it suits

Anyone with a steady flow of product or portrait photos who wants clean cut-outs without opening an editor. Skip it if every photo needs hand retouching. Each image is sent to Photoroom.

Who uses it, and how
IndustryWho uses itHow they use itExample
Online shopsCatalogue teamsPut every product on one plain white backgroundA team drops forty shots in a folder and gets white-backed PNGs back.
MarketingDesignersMake cut-outs with a transparent background for bannersA designer sets the colour to transparent and drags the PNGs into a layout.
FashionSmall brandsClean up photos of clothes before a marketplace uploadA seller adds 5% padding so every item sits centred.
Print on demandShop ownersGet same-size cut-outs for mock-upsAn owner keeps the original size so the files match the artwork.

You need to know n8n’s settings: import a file, add one Google Drive credential and paste an API key.

Where to use it

Any n8n that can reach Google Drive and Photoroom will run it.

  • n8n Cloud: import the file and publish it
  • Your own n8n server: the same file and steps
  • Google Drive: one folder to watch and a different folder for the results
  • Photoroom: an API key from your account

Setup

Download saves a zip with workflow.json and Mindket’s setup notes in your downloads folder. Setup is one credential, one key and two folders.

What you need first
NeedDetail
n8nOn n8n Cloud or on a server of your own
Google DriveAn OAuth2 credential and two folders, one for input and one for results
PhotoroomAn API key for the Image Editing API. A key that starts with sandbox_ makes free test calls with a watermark
  1. In n8n, create a workflow, open its menu, choose Import from File and pick workflow.json.
  2. Add a Google Drive credential and select it in Watch for New Images, Download Image and both upload nodes.
  3. In Watch for New Images, replace <YOUR_INPUT_FOLDER_ID> with the id of the folder to watch.
  4. Open Config. Replace <YOUR_PHOTOROOM_API_KEY> with your key, and replace <YOUR_OUTPUT_FOLDER_ID> in the folder address with the id of a second folder.
  5. Publish the workflow, then drop one test image in the input folder.

How to use it

Leave it running and drop photos in the input folder. The results appear in the output folder a short while later. Start with a sandbox key and a few images to check the colour and the padding.

What to change for a different result
To changeWhere
The background colourbg_color in Config, a name, a hex value or transparent
The space around the subjectpadding in Config, such as 5%
Keep each image’s size or use one sizekeepInputSize and outputSize in Config
The foldersWatch for New Images and the folder address in Config
The output file nameThe name field in both upload nodes

Example

You drop shoe.jpg in the input folder, with the colour set to white and padding of 5%.

BG-Removed-shoe.png

The output folder gets a PNG with the shoe on a white background, and 5% of space around it.

For newcomers and experts

If you are new. n8n draws a workflow as boxes joined by lines, and each box, a node, does one job. This one watches a folder, asks Photoroom to cut out the subject and saves the result. Test with one image before you drop in a hundred.

For experts. One loop handles one image at a time.

Where to look closer
NodeWhat it doesWhat to know
Watch for New ImagesPolls one folder for new filesIt fires for any new file, not only images
ConfigHolds the colour, padding, sizes, folder and keyThe key sits in a plain field, so keep a shared copy private
Get Image SizeReads the size of the imageThe size string feeds the original-size branch
Merge Image With SettingsJoins the image and the settings by positionIt expects one settings item for each image
Loop Over ImagesPasses one image at a timeThe finished branch is not connected
Use Fixed Size?Picks the fixed size or the original sizeTrue means fixed
Remove Background Fixed SizePosts the image to Photoroom as a formThe reply is the picture

Good to know

Run a few images first, because every image is one paid Photoroom call.

  • Fixes: the size read from the image is now cut at any plus sign before it goes to Photoroom, which expects only a width and a height. The folder, the key and the output address are placeholders
  • Cost and data: each image is sent to Photoroom. Its documentation says a sandbox_ key allows 1,000 free calls a month, up to 100 a day, with a watermark on the result
  • Folders: the output folder must differ from the input folder, or the workflow would process its own results
  • Format: Photoroom accepts PNG, JPEG, WebP and AVIF and returns PNG by default, which is what the upload names expect
  • Not run: Mindket did not run it against Google Drive or Photoroom, and the Photoroom settings follow its documentation read on 12 November 2026
  • Credentials: the JSON holds none

README and files

README

Photoroom background removal for new Google Drive images

An n8n workflow that cuts the background out of photos you drop in a Google Drive folder. Every minute it looks for new
files. Each new image goes to Photoroom, which removes the background and applies the colour and padding you chose. The
result is saved as a PNG in a second Drive folder.

What is inside

  • workflow.json: the workflow as n8n exports it, fourteen nodes. Two are sticky notes. It holds no credential.
  • README.md: these notes.

What we changed from the original copy

  • The Photoroom key, the output folder address and the input folder were empty or filled with a prompt. They are now the
    placeholders <YOUR_PHOTOROOM_API_KEY>, <YOUR_OUTPUT_FOLDER_ID> and <YOUR_INPUT_FOLDER_ID>.
  • When you keep each image's size, Remove Background Original Size sends the size that Get Image Size read. That string
    can end in an offset such as +0+0, and Photoroom's documentation says the value is a width and a height. The
    expression now cuts the string at the first plus sign.
  • Several nodes had names like Upload Picture to Google Drive1. The two background steps, the two upload steps, the size
    check, the loop and the merge now say what they do. The wiring is unchanged.
  • The two sticky notes are rewritten in plainer words.

Before you start

  • A Google account whose Drive you can connect to n8n with OAuth2.
  • A Photoroom API key. A key that starts with sandbox_ makes free test calls, and the result carries a watermark.
  • Two Drive folders: one to watch and a different one for the results.

Set it up

  1. In n8n, create a workflow, open its menu and choose Import from File. Pick workflow.json.
  2. Add a Google Drive OAuth2 credential and select it in Watch for New Images, Download Image,
    Upload Fixed Size Picture and Upload Original Size Picture.
  3. In Watch for New Images, replace <YOUR_INPUT_FOLDER_ID> with the id of the folder to watch, the part of its address
    after /folders/.
  4. Open Config. Replace <YOUR_PHOTOROOM_API_KEY> with your key. In OutputDriveFolder, replace
    <YOUR_OUTPUT_FOLDER_ID> with the id of the results folder.
  5. Publish the workflow, then drop one test image in the input folder.

How a run goes

  1. Watch for New Images finds a new file and hands its id to two nodes.
  2. Download Image fetches the file, and Get Image Size reads its size. Split Out keeps the size and the image.
  3. Config makes one item with your settings and the original file name.
  4. Merge Image With Settings joins the two by position, and Loop Over Images passes one image at a time.
  5. Use Fixed Size? checks keepInputSize. When it is false, Remove Background Fixed Size uses outputSize. When it is
    true, Remove Background Original Size uses the size that was read.
  6. Photoroom answers with the picture. An upload node saves it as BG-Removed-<original name>.png in the results folder,
    and the loop takes the next image.

Change the result

  • The background colour: bg_color in Config. It takes a colour name, a hex value or transparent.
  • The space around the subject: padding in Config, such as 5%.
  • One size for all images: set keepInputSize to false and give outputSize as a width and a height, like 1600x1600.
  • The folders: the trigger node for the input and OutputDriveFolder for the results.

Good to know

  • Each image is one call to Photoroom. Photoroom's documentation says a sandbox_ key allows 1,000 free calls a month, at
    most 100 a day, and adds a watermark.
  • The output folder must differ from the input folder. If they match, the workflow processes its own results.
  • Photoroom accepts PNG, JPEG, WebP and AVIF and returns PNG unless you ask for another format, so the upload names end in
    .png.
  • Watch for New Images fires for every new file, including files that are not images. Keep the input folder to pictures only.
  • The key sits in a plain field in Config. On a shared n8n, move it to an HTTP header credential.
  • Mindket did not run this workflow against Google Drive or Photoroom. These notes follow n8n's published node code and
    Photoroom's documentation, read on 12 November 2026.
Files
NOTICE.md  653 B
README.md  4 KB
workflow.json  12 KB

3 files, 17 KB, downloaded as a zip.

What’s new

  • Version 1 · 2026-11-12

Reviews

No ratings yet

Write a review

No reviews yet.

More from Mindket

See all from Mindket

Huashu Design

alchaincyf · Skill

Turns a one-line request in your AI agent into a finished design: a launch animation, a clickable app prototype, an editable slide deck, an infographic or a se…

New29.4k

Guizang PPT Skill

op7418 · Skill

Skill that makes single-file HTML slide decks, slide illustrations and platform covers in two visual styles, with a presenter mode for rehearsal. For speakers…

New29.8k

Claude Code Skills & Plugins

alirezarezvani · Skill

Adds 411 ready-made skills for Claude Code and other coding agents, grouped by role from engineering and product to marketing, finance and compliance. Installs…

New29.8k

Similar in Marketing & SEO

See all in Marketing & SEO

Pixel Art XL

nerijs · Kit

A pixel art style add-on for Stable Diffusion XL that turns text prompts into pixel-style images, with an optional LCM LoRA for faster runs. For game makers, d…

New

Licon MSR for LTX-2.5

LiconStudio · Kit

Keeps characters, clothing, objects and backgrounds consistent in generated video by feeding the model up to five reference images. A LoRA for LTX-2.5 in Comfy…

New

Flux.2-Klein-9B-MatchingPose

nhathoangfoto · Kit

A LoRA for FLUX.2 Klein 9B that puts a character into the pose shown by a mannequin reference while keeping the character's face and style. For artists and des…

New