Reference Inpaint

Inpaint a region of a target photo using a reference image as the visual guide. Provide the target, a black-and-white mask of the area to fill, and a reference image. The model paints the masked region with content matching the reference.

By Runflow

Pricing: $0.2 per request

Overview

**Reference Inpaint** fills a masked region of a target photo using the contents of a reference image as the visual guide. Provide the target, a black-and-white mask of the area to fill, and a reference image; the model paints the masked region with content matching the reference.

How it works

Send a zip containing three images: a target photo, a black-and-white mask of the same dimensions (white = inpaint, black = keep), and a reference image whose visual content should fill the masked area. The model analyses the reference, blends its content into the masked region of the target, and returns the composited image at the original resolution.

Common use cases

• Product placement: drop a product into a clean scene shot
• Background or texture swap: replace a background or surface with a reference
• Element insertion: add a piece of furniture, signage, or branding to a layout
• Concept iteration: try different visual options without re-shooting

Examples

• slot-1
• slot-2
• slot-3
• slot-7
• slot-9
• slot-10
• slot-12
• slot-14

Frequently asked questions

What is Reference Inpaint?

A first-party Runflow workflow that fills a masked region of a target photo using the contents of a reference image as the visual guide. The model paints the masked area to match the reference and blends with the surrounding pixels.

How much does Reference Inpaint cost on Runflow?

Simple fixed pricing: $0.55 per image.

What format should the inputs be?

Package the target image, mask, and reference image into a single zip and send the zip URL. The mask is a standard black-and-white image (white = inpaint, black = keep) at the same dimensions as the target. PNG, JPG, and WEBP are all supported.

How is this different from regular inpainting?

Regular inpainting fills a masked region using only the surrounding context. Reference Inpaint additionally takes a reference image so you can control exactly what content goes into the masked area.

Can I use the outputs commercially?

Yes.

How long does Reference Inpaint take?

60–150 seconds typically, depending on resolution and queue depth.

Related models

• Multi Angles, Re-render the same subject from a different camera angle. Pick a horizontal view, a vertical angle, and a shot distance: the model rotates the camera around the subject and re-renders the scene from that pose.
• Logo Inpaint, Place a logo onto a target image, with optional mask to constrain placement. When the mask is omitted, the workflow picks a placement automatically.
• Background Replace, Swap the background of any product photo for a new scene defined by a reference image and a short prompt. The model preserves the foreground subject while matching camera angle and lighting to the new background.
• Smart Resize, Resize an image to a target aspect ratio + resolution (1K, 2K, 4K) without distortion or cropping. Uses generative reframing to recompose the subject into the new frame.

Discoverable surfaces

• Dispatch endpoint: POST https://api.runflow.io/v1/models/reference-inpaint/runs
• Per-model spec (markdown): https://app.runflow.io/models/reference-inpaint/llms.txt
• Docs page: https://docs.runflow.io/models/reference-inpaint
• Public OpenAPI spec: https://docs.runflow.io/api/openapi.public.json
• Agent skill (start here): https://www.runflow.io/.well-known/agent-skills/runflow/SKILL.md