CONTENT CREATION

Auto-upscale and clean Dropbox product drops for the marketplace

Watches a Dropbox intake folder, upscales each new product photo and strips its background with Replicate, then writes the polished image back and logs the result in Airtable.

CategoryContent Creation
Enginesim
Difficultybeginner
Triggerevent
Steps5
Setup~5 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew file added to Dropbox intake folderDropboxDropbox
  • ActionUpscale image with Replicate modelReplicateReplicate
  • ActionRemove background with Replicate cutout modelReplicateReplicate
  • ActionSave finished PNG to Dropbox export folderDropboxDropbox
  • OutputLog source, output, and status in AirtableAirtableAirtable

What it does

Turns raw seller uploads into marketplace-ready hero shots without anyone touching an editor. Every photo dropped into the intake folder is upscaled to a consistent resolution, has its background removed, and is filed back into a clean export folder with a tracking row in Airtable.

When to use it

Use it when sellers or photographers dump unedited product shots into a shared Dropbox folder and your team is manually upscaling and cutting out backgrounds before listing. It removes the repetitive editing step and guarantees every listing image meets the same spec.

How it works

  1. 1A new file landing in the Dropbox `/intake` folder triggers the run.
  2. 2The image is sent to a Replicate upscaling model to lift it to the target resolution.
  3. 3The upscaled output is passed to a Replicate background-removal model to produce a transparent cutout.
  4. 4The finished PNG is written to the Dropbox `/marketplace-ready` folder under the same base name.
  5. 5An Airtable row records the source file, output link, and processing status for the catalog team.

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 AirtableBases, tables, views, automations.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    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.