CONTENT CREATION

Composite cut-outs onto branded backdrops from an Airtable queue

Pulls product rows marked Ready-to-style from Airtable, generates an on-brand backdrop scene, composites the transparent cut-out onto it.

CategoryContent Creation
Enginesim
Difficultyintermediate
Triggerschedule
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerScheduled scan of Airtable styling queueAirtableAirtable
  • ActionGenerate branded backdrop sceneImage generation
  • ActionComposite cut-out onto backdrop via ReplicateReplicateReplicate
  • ActionUpload finished hero shot to S3AWS S3
  • OutputUpdate Airtable row with hero image and Styled statusAirtableAirtable

What it does

Produces consistent, on-brand hero shots by placing already-cut-out products onto a generated lifestyle backdrop that matches your brand palette and scene prompt, then files the result against the right product.

When to use it

Use it once you have transparent cut-outs and want polished marketing imagery without a photo studio. Great for seasonal refreshes where the same products need a new branded look on demand.

How it works

  1. 1The flow runs on a schedule and queries Airtable for rows where Status is Ready-to-style.
  2. 2For each row it reads the brand scene prompt and palette stored on the record.
  3. 3A backdrop is produced with the image generation step using that prompt.
  4. 4Replicate composites the transparent product PNG onto the generated backdrop, matching scale and shadow.
  5. 5The composited hero image is uploaded to cloud storage and the Airtable row is updated with the final image link and a Styled status, so downstream publishing can pick it up.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect AirtableBases, tables, views, automations.
  2. 2
    Connect Image generationManaged Nano Banana image renders, metered per image.
  3. 3
    Connect ReplicateImage, video, and model inference.
  4. 4
    Connect AWS S3Buckets, objects, signed URLs.
  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.