How to Use Bria Extract Object in Gemini
Bria Extract Object pulls a named object from an image into a transparent PNG for product listings, ads, and composites. It targets the object you describe, with optional tight cropping and edge refinement.
Prompts to try with Bria Extract Object in Gemini
Copy an example into Gemini, or ask in your own words.
Use Bria Extract Object on this photo to isolate the red ceramic mug on the right. Return a transparent PNG cropped tightly around it.
Use Bria Extract Object to isolate the person in the yellow jacket at the left of this photo. Keep the original canvas dimensions.
Use Bria Extract Object to pull the blue sale sign from this image. Leave edge refinement off so I can inspect the lettering before using it.
Use Bria Extract Object to isolate the brown teddy bear in this photo. Try softer edge refinement and crop tightly around the cutout.
Use Bria Extract Object to extract the green chair beside the window. Keep a transparent background and check that the result isolates the chair rather than returning the whole photo.
How to set up Bria Extract Object in Gemini
Pick the way that suits you. Each takes about two minutes.
Use the Gemini connector
- Open Connected Apps
On your computer, go to gemini.google.com. At the bottom, click Settings › Connected Apps. If you don't see Connected Apps, click Personal Intelligence first, then Connected Apps.
- Add Spiral as a custom app
Under Custom apps, click Add a custom app and paste this MCP server URL:
https://api.spiral.ai/mcp
- Sign in to Spiral and approve
Follow the on-screen instructions. Spiral opens: sign in, pick the organization and click Authorize. No API key.
Use the Spiral skill
- Send Gemini 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 Bria Extract Object
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": "bria/extract-object", "input": { "image_url": "https://bria-datasets.s3.amazonaws.com/object-extraction/tools_construction_flatlay.jpg" } }'
Then paste one of the prompts above: Gemini finds Bria Extract Object on Spiral, shows the price and runs it.
Bria Extract Object providers and prices
Spiral runs Bria Extract Object through fal. Open a card for today's price, with every fee included.
Settings you can ask for
Bria Extract Object works from your image URL and prompt. Ask Gemini for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Autocrop | on or off | off | Tighten the output canvas to the extracted object. |
| Remove background | on or off | off | When True, refine the cutout alpha with background removal (RMBG). When False (default), use the SAM segmentation mask as the cutout's alpha -- faster, with no salient-object matting (helpful when RMBG over-trims text, logos, or graphics). |
Every API field of Extract Object is on its tool page: open its card above.
What can you do with Bria Extract Object in Gemini?
Pull a specific object out of a supplied image for a listing, presentation, or design with Bria Extract Object. Describe the target in plain language, then choose a tight crop or the original canvas.
Product listing cutouts
Extract a named product from a lifestyle photo, then crop tightly for a standalone listing asset.
Individual items from flat lays
Turn a multi-product flat lay into separate assets by requesting one clearly described item at a time.
Ad composition assets
Isolate a product as a transparent PNG for placement in a separately designed banner or ad.
A person from a group photo
Describe one person by a visible feature and position to prepare a cutout for a profile graphic or presentation.
Layers with original placement
Keep automatic cropping off when extracting an object that needs to retain its position on the original canvas.
Graphic assets from existing artwork
Extract a named graphic with edge refinement off, then inspect small lettering and logo details before reuse.
Reusable scene props
Pull a named chair, lamp, or other visible object from a scene to build a library of transparent design assets.
More on Bria Extract Object and Gemini
Overview
Bria Extract Object in other agents
Questions about Bria Extract Object in Gemini
Can Gemini use Bria Extract Object?
Yes. Add Spiral to Gemini as an MCP server, and Gemini can find and run Bria Extract Object like any built-in tool.
How much does Bria Extract Object cost in Gemini?
$0.026 per image. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini plan is separate.
Do I need a fal account to use Bria Extract Object in Gemini?
No. Spiral runs Bria Extract Object on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up Bria Extract Object in Gemini?
About two minutes: open Connected Apps, then add Spiral as a custom app, then sign in to Spiral and approve.
Does Gemini wait while Bria Extract Object runs?
Bria Extract Object runs in the background. Gemini starts the run, checks on it and gives you the image when it's ready.
How is Bria Extract Object different from background removal?
Bria Extract Object selects the object you name, including something outside the obvious foreground. Use it when you want one particular item from a scene.
What does Bria Extract Object return?
It returns an RGBA PNG cutout with a transparent background. You can use the cutout as an asset in a separate design or compositing step.
How do I select one of several similar objects?
Name the object and add a visible distinction, such as its color or position. Try “the yellow hammer” or “the sneaker on the left” instead of a broad description.
Does the output keep the original image dimensions?
With automatic cropping off, the cutout stays on a canvas matching the input dimensions. Enable automatic cropping when you want the canvas tightened around the object.
When should I use background removal refinement?
Try it when a photographic subject needs softer matte edges. Leave it off for text, logos, or graphics if refinement trims away detail you need.
Start using Bria Extract Object in Gemini
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Gemini:
set up https://spiral.ai/SKILL.md


