CONTENT CREATION

Process the Airtable photo-edit queue on a schedule

Runs on a schedule, pulls every Airtable row marked Needs Edit, upscales and cleans each linked image through Replicate, and flips the row to Ready with the new asset URL attached.

CategoryContent Creation
Enginesim
Difficultyintermediate
Triggerschedule
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerScheduled timer fires
  • ActionQuery Airtable for rows marked Needs EditAirtableAirtable
  • LogicSkip rows missing a source image
  • ActionUpscale and clean each image with ReplicateReplicateReplicate
  • ActionUpload finished asset to R2CloudflareCloudflare R2
  • OutputUpdate Airtable row to Ready with asset URLAirtableAirtable

What it does

Works an Airtable backlog of product photos in batches. On each scheduled run it finds rows flagged for editing, sends their images through an upscale-then-background-clean pass on Replicate, and updates the row with the finished asset and a Ready status.

When to use it

Use it when your catalog team triages photos in Airtable and wants editing to happen automatically overnight or hourly instead of one-off. It keeps a single source of truth in the table while offloading the actual image work.

How it works

  1. 1A scheduled timer fires (for example every hour).
  2. 2The flow queries Airtable for all rows where status equals `Needs Edit`.
  3. 3A logic step skips any row missing a source image so it can be fixed manually.
  4. 4Each remaining image is upscaled and then background-cleaned via two Replicate model calls.
  5. 5The finished image is uploaded to R2 for durable hosting.
  6. 6The Airtable row is updated with the R2 URL and its status set to `Ready`.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect AirtableBases, tables, views, automations.
  2. 2
    Connect ReplicateImage, video, and model inference.
  3. 3
    Connect Cloudflare R2Object storage, S3-compatible.
  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.