How to Use Bria GenFill v2 in Gemini
Bria GenFill v2 adds objects to selected areas of an existing image, such as a vase on a table or a prop beside a product. It favors blob-shaped masks and keeps the original resolution and pixels outside the mask.
Prompts to try with Bria GenFill v2 in Gemini
Copy an example into Gemini, or ask in your own words.
Use Bria GenFill v2 with this photo and mask to add a small cream ceramic vase. Place it flat on the table, about one-third the height of the nearby chair back, with a soft contact shadow.
Use Bria GenFill v2 with this food photo and mask. Add a ripe lemon resting beside the plate, with natural peel texture and a contact shadow matching the scene.
Use Bria GenFill v2 with this product photo and selected region. Add a small folded cotton towel beside the soap. Describe the fabric texture, scale, and contact with the counter.
Use Bria GenFill v2 with this room photo and mask to add a compact wooden stool. Match its scale to the nearby furniture and request a grounded contact shadow.
Use Bria GenFill v2 with this desk photo and mask. Add a matte black pencil cup holding three wooden pencils. Keep it smaller than the monitor stand and resting firmly on the desk.
How to set up Bria GenFill v2 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 GenFill v2
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/genfill/v2", "input": { "image_url": "https://bria-datasets.s3.us-east-1.amazonaws.com/Fibo_edit/flower.png", "mask_url": "https://bria-datasets.s3.us-east-1.amazonaws.com/Fibo_edit/flower_input_mask.png", "instruction": "A beautiful colorful butterfly" } }'
Then paste one of the prompts above: Gemini finds Bria GenFill v2 on Spiral, shows the price and runs it.
Bria GenFill v2 providers and prices
Spiral runs Bria GenFill v2 through fal. Open a card for today's price, with every fee included.
Settings you can ask for
Bria GenFill v2 works from your image URL and mask URL. Ask Gemini for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | 5555 | Random seed for reproducibility. |
| Steps number of | 20 to 50 | 30 | Number of inference steps. |
Every API field of Genfill v2 · Image to Image is on its tool page: open its card above.
What can you do with Bria GenFill v2 in Gemini?
Turn an existing photo into a focused object-editing brief and an edited image. A chat agent can help specify the object's material, size, placement, and contact shadow before applying the selected mask.
Product photo props
Add a ceramic dish or wooden tray beside a product. Keep the product outside the mask and describe the prop's scale and contact shadow.
Interior styling concepts
Explore a vase, table lamp, or decorative bowl in a room photo by selecting the area where the object should appear.
Food photo additions
Add a lemon, a small bowl of berries, or another ingredient beside a plated dish while leaving the dish outside the mask.
Seasonal ad concepts
Add a pumpkin, wrapped gift, or other seasonal prop to a selected area of an existing campaign photo.
Editorial still-life edits
Place a notebook, pencil, or cup into a selected tabletop area for an article illustration.
Website image refreshes
Add a relevant object to an existing website photo. Keep the subject outside the mask and retain the source image's pixel dimensions.
More on Bria GenFill v2 and Gemini
Overview
Bria GenFill v2 in other agents
Questions about Bria GenFill v2 in Gemini
Can Gemini use Bria GenFill v2?
Yes. Add Spiral to Gemini as an MCP server, and Gemini can find and run Bria GenFill v2 like any built-in tool.
How much does Bria GenFill v2 cost in Gemini?
$0.052 per 1,048,576 megapixels. Minimum 1,048,576 pixels. 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 GenFill v2 in Gemini?
No. Spiral runs Bria GenFill v2 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 GenFill v2 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 GenFill v2 runs?
Bria GenFill v2 runs in the background. Gemini starts the run, checks on it and gives you the image when it's ready.
What is Bria GenFill v2 best suited for?
Adding an object to a selected area of an existing image. Practical examples include a lamp on a desk, fruit beside a plate, or a decorative prop beside a product.
What mask shape works best?
Bria GenFill v2 is optimized for blob-shaped masks. Prefer a rounded selection around the intended object area when planning an edit.
Does Bria GenFill v2 change the rest of the image?
Bria documents that areas outside the mask remain unchanged. Keep anything you need to preserve outside the selected region.
Does Bria GenFill v2 increase image resolution?
Generative Fill returns the image at its original resolution. Treat it as a content edit; use a separate upscaling step when you need larger pixel dimensions.
How should I describe the object I want?
Name the object, its material, and its size relative to nearby objects. Describe how it sits on the surface and request a contact shadow.
Start using Bria GenFill v2 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


