CONTENT CREATION

Process Dropbox product shots and sync cutout URLs into the Airtable catalog

Removes backgrounds on Dropbox drops, uploads cutouts to R2, then matches each image to its SKU and writes the public image URL and processing status back into an Airtable…

CategoryContent Creation
Enginesim
Difficultyintermediate
Triggerevent
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew product photo in DropboxDropboxDropbox
  • ActionRemove background via ReplicateReplicateReplicate
  • ActionUpload cutout to R2CloudflareCloudflare R2
  • LogicMatch filename to SKU in AirtableAirtableAirtable
  • OutputWrite image URL + status to Airtable recordAirtableAirtable

What it does

Closes the loop between raw photo intake and your product database. As images arrive in Dropbox, each gets a Replicate background removal and an R2 upload, then the workflow looks up the matching SKU in Airtable by filename convention and writes the cutout URL plus a processed timestamp onto that record.

When to use it

Use it when Airtable is your source of truth for the catalog and you want product rows to self-populate with clean image links as soon as photos are shot. Eliminates the copy-paste step between asset storage and the catalog, and surfaces which SKUs still lack imagery.

How it works

  1. 1A new Dropbox file triggers the run.
  2. 2Replicate removes the background and the cutout uploads to R2, yielding a public URL.
  3. 3The filename is parsed to extract the SKU code.
  4. 4A lookup finds the matching Airtable record by SKU; unmatched files branch to an exceptions note.
  5. 5The matched record is updated with the R2 image URL and an `image_status` of processed, keeping the catalog current.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect DropboxFiles and folders.
  2. 2
    Connect ReplicateImage, video, and model inference.
  3. 3
    Connect Cloudflare R2Object storage, S3-compatible.
  4. 4
    Connect AirtableBases, tables, views, automations.
  5. 5
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  6. 6
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  7. 7
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.