Object Removal (Prompt)

Remove requested objects from a photo using a short text instruction. The model restores the background without requiring a mask.

By Runflow

Pricing: $0.48 per request

Overview

**Object Removal (Prompt)** removes requested objects from a photo using a short text instruction. Describe what should be removed, and the workflow rebuilds the cleaned area to match the surrounding image.

How it works

Send the source photo package and a concise prompt such as "remove glasses and laptop" or "remove jacket". Keep the prompt short and concrete; the public API accepts up to 7 words. The workflow returns the cleaned image through the standard Runflow output contract.

Common use cases

• Removing props or distractions without hand-drawing a mask
• Cleaning portraits and lifestyle images
• Preparing product and marketing images at scale
• Fast photo cleanup from natural-language instructions

Examples

• review 01
• review 02
• review 03
• review 06
• review 07
• review 08
• review 09
• review 10

Frequently asked questions

What is Object Removal (Prompt)?

A Runflow workflow that removes requested objects from a photo using a short text instruction instead of a customer-supplied mask.

What should I write in the prompt?

Use a short concrete command, such as remove glasses and laptop or remove jacket. The public input is capped at 7 words.

How much does Object Removal (Prompt) cost?

Simple fixed pricing: $0.48 per image.

When should I use the mask-based Object Removal model instead?

Use the mask-based model when you need exact pixel-level control over the removal area.

Can I use the outputs commercially?

Yes.

How long does Object Removal (Prompt) take?

Most requests complete in about 60-150 seconds, depending on image complexity and queue conditions.

Related models

• Product Isolation, Isolate the main product from a busy scene onto a clean background, using an optional text prompt to disambiguate the subject. Built for studio-grade product photography at scale.
• Object Removal, Remove an unwanted object or region from a photo. Mark the area to remove with a black-and-white mask. The model rebuilds the background using surrounding context.
• Tag Removal, Remove price tags, stickers, and labels from product images while preserving the underlying material and lighting. Ideal for re-listing inventory or cleaning up user-submitted photography.
• Model Removal, Remove the human model from a garment or apparel photo and recover a clean flat-lay or ghost-mannequin view. Designed for fashion catalogs and PDP hero shots.

Discoverable surfaces

• Dispatch endpoint: POST https://api.runflow.io/v1/models/object-removal/prompt/runs
• Agent skill (start here): https://www.runflow.io/.well-known/agent-skills/runflow/SKILL.md