How to Use Object Removal Mask in ChatGPT
Object Removal Mask removes selected objects and reconstructs the scene behind them. Unlike Object Removal, which identifies targets from text, it lets you specify the removal area with a mask.
Prompts to try with Object Removal Mask in ChatGPT
Copy an example into ChatGPT, or ask in your own words.
Use Object Removal Mask on this photo and the attached mask to remove the stray cup. Show me the edited image and a close view of the filled tabletop.
Use Object Removal Mask to remove the distraction marked in this portrait's mask. Inspect the result around the subject's hair and tell me what needs review.
Use Object Removal Mask on this room photo and mask. Try expanding the selection by 5 pixels, then check the reconstructed floor and wall edges.
Use Object Removal Mask to remove the marked litter from this landscape photo. Check the result for a remaining outline or shadow.
Use Object Removal Mask on this product photo and mask. Compare no selection expansion with a 5-pixel expansion, and show which result leaves the cleaner object boundary.
How to set up Object Removal Mask in ChatGPT
Pick the way that suits you. Each takes about two minutes.
Use the ChatGPT connector
- Add a custom MCP server
In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.
https://api.spiral.ai/mcp
- Click Connect
ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.
- Sign in to Spiral and approve
Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.
Use the Spiral skill
- Send ChatGPT this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Object Removal Mask
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "fal", "model": "fal-ai/object-removal/mask", "input": { "image_url": "https://v3.fal.media/files/zebra/o0DORfJawy-T9P_-NsvLY.png", "mask_url": "https://v3.fal.media/files/tiger/7nq9-v-lJtBCPnK1332fr.png" } }'
Then paste one of the prompts above: ChatGPT finds Object Removal Mask on Spiral, shows the price and runs it.
Object Removal Mask providers and prices
Spiral runs Object Removal Mask through fal. Open a card for today's price, with every fee included.
Settings you can ask for
Object Removal Mask works from your image URL and mask URL. Ask ChatGPT for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Model | low_quality, medium_quality, high_quality, or best_quality | best_quality | |
| Mask expansion | 0 to 50 | 15 | Amount of pixels to expand the mask by. Range: 0-50 |
Every API field of Object Removal · Mask is on its tool page: open its card above.
What can you do with Object Removal Mask in ChatGPT?
Object Removal Mask lets you clean up a photo by marking the distraction you want removed. Ask for a close inspection of the filled area before choosing the edited image.
Product photo cleanup
Use Object Removal Mask to remove a stray prop from a product photo. Mask the prop and inspect the product outline and nearby surface after editing.
Portrait background cleanup
Use Object Removal Mask to remove a distracting object behind a portrait subject. Review the edit near hair, clothing, and other details you want to keep.
Travel photo cleanup
Use Object Removal Mask to remove a selected distraction from a travel photo. Check reconstructed pavement, railings, and building edges before sharing.
Interior photography
Use Object Removal Mask to remove a loose cable or discarded packaging from a room photo. Inspect the reconstructed wall or floor against the original.
Food photo retouching
Use Object Removal Mask to remove an unwanted utensil or napkin from a tabletop composition. Keep the selection clear of the dish and review the filled surface.
Outdoor scene cleanup
Use Object Removal Mask to remove a piece of litter from a landscape photo. Check the replacement texture and any remaining trace of the object's shadow.
More on Object Removal Mask and ChatGPT
Overview
Object Removal Mask in other agents
Questions about Object Removal Mask in ChatGPT
Can ChatGPT use Object Removal Mask?
Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Object Removal Mask like any built-in tool.
How much does Object Removal Mask cost in ChatGPT?
$0.0078 per image. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your ChatGPT plan is separate.
Do I need a fal account to use Object Removal Mask in ChatGPT?
No. Spiral runs Object Removal Mask on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up Object Removal Mask in ChatGPT?
About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.
Does ChatGPT wait while Object Removal Mask runs?
Object Removal Mask runs in the background. ChatGPT starts the run, checks on it and gives you the image when it's ready.
What is Object Removal Mask useful for?
Use it to remove a selected object from an existing photo and fill the space with scene-appropriate content. Practical tasks include removing a stray prop, background distraction, or piece of litter.
How do I specify exactly what should disappear?
Mark the removal area with white pixels in the mask. For a precise edit, inspect the selection around the target before running the removal.
Can Object Removal Mask remove an object's visual effects too?
The documented capability includes removing an object's visual effects. After editing, check for leftover shadows or reflections as well as the object itself.
How should I adjust mask expansion?
Try a small expansion when the target sits close to something you want to keep. If the result leaves an outline, compare it with a slightly wider selection and inspect both results.
Does Object Removal Mask recover the original hidden background?
The documentation describes reconstruction with contextually appropriate content. Treat that as a plausible fill rather than proof of what was behind the object, and inspect important details before using the image.
Start using Object Removal Mask in ChatGPT
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into ChatGPT:
set up https://spiral.ai/SKILL.md


