ActionOpenAIUpdated June 2026

How do I edit an image with OpenAI (inpainting)?

Short answer: Drop the "OpenAI → Edit Image" action anywhere in your workflow, map the inputs from upstream nodes, and publish.

Use this action All 16 OpenAI actions

Inputs

The fields this action accepts.

Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.

Field	Type	Required	Description
Image URL or base64 image_url	string	Required	Source image (PNG, max 25MB)
Mask URL (optional) mask_url	string	Optional	PNG mask — transparent areas are edited
Prompt prompt	string	Required	Add a sunset behind the mountain
Model model	options	Optional	Model. Options: gpt-image-1 (best), dall-e-2
Size size	options	Optional	Size. Options: 1024×1024, 1536×1024, 1024×1536
Num Images n	string	Optional	Num Images

Sample request

{
  "image_url": "e.g. https://example.com/path",
  "mask_url": "e.g. https://example.com/path",
  "prompt": "Add a sunset behind the mountain",
  "model": "{{trigger.model}}",
  "size": "{{trigger.size}}"
}

Returns

{
  "data": [
    {
      "url": "https://example.com/edited.png"
    }
  ],
  "created": 1700000000
}

Use these fields in downstream nodes for routing, logging, or error handling.

Triggered by

Apps that pair well as the trigger for Edit Image.

Any of these apps can fire this action as part of a workflow.

Google Sheets → OpenAI

2 Google Sheets triggers

HubSpot → OpenAI

18 HubSpot triggers

FAQ

Questions about Edit Image.

What does the Edit Image action do in OpenAI?

Edits an image with a prompt and optional mask using gpt-image-1 (or dall-e-2). Supports inpainting (mask defines the region to regenerate). Great for product retouching or asset variations.

What inputs does Edit Image require?

Required: Image URL or base64, Prompt. Every input accepts a static value or a variable from any upstream node in your workflow.

Can I use dynamic inputs from earlier workflow nodes?

Yes. Any field on this action can pull values from upstream nodes, whether that's a form response, a trigger payload, an AI output, or a lookup result.

What happens if OpenAI returns an error?

The workflow pauses on the failed node, the error message is captured in the run log, and you can retry the run with one click. Auto-retry policies are configurable per workflow with exponential backoff up to 5 attempts.

Does Edit Image support batch operations?

Yes. Run Edit Image inside a Loop node to process arrays. Tiny Command handles OpenAI's rate limits automatically so you don't have to throttle manually.

More actions