How to Use Object Removal Bounding Box in ChatGPT
Object Removal Bounding Box erases a selected object and reconstructs the surrounding scene. Use it for a specific distraction in an existing photo, with one bounding box per run.
Prompts to try with Object Removal Bounding Box in ChatGPT
Copy an example into ChatGPT, or ask in your own words.
Use Object Removal Bounding Box on this photo to remove the red bag beside the bench. Show me the box you plan to use first.
Use Object Removal Bounding Box to erase the bottle on the left side of this beach photo. Show the edited area beside the original.
Use Object Removal Bounding Box to remove the spare fork beside the plate in this photo. Check the reconstructed tabletop before showing the result.
Use Object Removal Bounding Box to remove the cup from this desk photo. If its outline remains, slightly enlarge the removal area and compare.
Use Object Removal Bounding Box to remove the bag first, then the bottle in this photo. Use separate passes and show each result.
How to set up Object Removal Bounding Box 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 Bounding Box
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/bbox", "input": { "image_url": "https://v3.fal.media/files/zebra/o0DORfJawy-T9P_-NsvLY.png" } }'
Then paste one of the prompts above: ChatGPT finds Object Removal Bounding Box on Spiral, shows the price and runs it.
Object Removal Bounding Box providers and prices
Spiral runs Object Removal Bounding Box through fal. Open a card for today's price, with every fee included.
Settings you can ask for
Object Removal Bounding Box works from your image 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 · Bbox is on its tool page: open its card above.
What can you do with Object Removal Bounding Box in ChatGPT?
Turn a photo editing request into a targeted removal with a box around the unwanted object. Review the reconstructed area in the conversation before deciding whether to keep it.
Product photo cleanup
Remove a stray prop beside a product, then inspect the product's edges against the original.
Portrait background edits
Select a distracting object behind the subject and review the reconstructed area before keeping the edit.
Interior photo cleanup
Erase a temporary item, such as a bag beside a sofa, for an edited interior presentation.
Travel photo edits
Remove a discarded bottle from a scenic photo without choosing a different crop.
Food photography
Remove an unwanted utensil beside a plated dish and inspect the replacement tabletop texture.
Website image preparation
Clean a distracting object from a selected website photo and compare the result at its intended display size.
More on Object Removal Bounding Box and ChatGPT
Overview
Object Removal Bounding Box in other agents
Questions about Object Removal Bounding Box in ChatGPT
Can ChatGPT use Object Removal Bounding Box?
Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Object Removal Bounding Box like any built-in tool.
How much does Object Removal Bounding Box 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 Bounding Box in ChatGPT?
No. Spiral runs Object Removal Bounding Box 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 Bounding Box 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 Bounding Box runs?
Object Removal Bounding Box runs in the background. ChatGPT starts the run, checks on it and gives you the image when it's ready.
What is Object Removal Bounding Box useful for?
Use it to remove a specific distraction from an existing image, such as a cup on a table or a bag beside a chair. It reconstructs the scene where the selected object appeared.
Does it also remove an object's visual effects?
The documented scope includes the selected object's visual effects. Compare the edited area with the original before accepting the result.
Can I select several separate objects at once?
Only one bounding box is supported per run. For separate objects, review the first edit before using it as the starting image for another pass.
What should I try if an object's outline remains?
Try increasing mask expansion slightly, then compare the boundary with the first result. This enlarges the removal area, so inspect nearby details too.
Does it recover the real background behind an object?
The documentation describes reconstruction with contextually appropriate content. Treat that as a plausible replacement, not proof of what was hidden in the original photograph.
Start using Object Removal Bounding Box 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


