CONTENT CREATION

Batch-generate marketplace variant shots from a Drive drop

Processes a Google Drive folder of cut-outs to render per-marketplace variant shots at required aspect ratios and backgrounds, then organizes the outputs into channel subfolders.

CategoryContent Creation
Enginesim
Difficultyintermediate
Triggerschedule
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerScheduled scan of Google Drive cut-out intake folderGoogle DriveGoogle Drive
  • ActionComposite white-background marketplace variant via ReplicateReplicateReplicate
  • ActionGenerate lifestyle variant backdropImage generation
  • ActionUpload variants to per-channel Drive subfoldersGoogle DriveGoogle Drive
  • OutputLog generated variants in Airtable trackerAirtableAirtable

What it does

Takes a batch of transparent product cut-outs and produces every variant a multi-channel seller needs: white-background square for Amazon, lifestyle scene for Instagram, and a wide banner crop, all from one source image.

When to use it

Use it when the same product must be listed across marketplaces that each demand different image specs, and re-exporting one shot at a time is wasting your team's day. Best for catalog launches and channel expansions.

How it works

  1. 1A scheduled run scans a Google Drive intake folder and collects all cut-out PNGs added since the last run.
  2. 2For each cut-out, a clean white-background variant is composited via Replicate at marketplace square dimensions.
  3. 3A lifestyle variant backdrop is produced with the image generation step and the product is composited onto it.
  4. 4Each rendered variant is uploaded into a per-channel subfolder in Google Drive named for the product SKU.
  5. 5A summary of generated variants per SKU is written to an Airtable tracking table so merchandising knows what is ready to list.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect Google DriveDocs, sheets, slides, files.
  2. 2
    Connect ReplicateImage, video, and model inference.
  3. 3
    Connect Image generationManaged Nano Banana image renders, metered per image.
  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.