How to Use Bria GenFill in ChatGPT
Bria GenFill adds or replaces objects inside a masked part of an existing image. Use it for targeted changes such as swapping a prop or adding seasonal details while working with the surrounding scene.
Prompts to try with Bria GenFill in ChatGPT
Copy an example into ChatGPT, or ask in your own words.
Use Bria GenFill on the photo I provided. Replace the selected vase with a low terracotta bowl, sized to fit the table and casting a soft contact shadow.
Use Bria GenFill to add a small pumpkin inside the selected area beside the product in this photo. Match the existing light direction and make the pumpkin rest naturally on the surface.
Use Bria GenFill on this cupcake photo. Add one glossy red cherry to the selected area on top, with a short stem and a small shadow where it touches the frosting.
Use Bria GenFill to replace the selected table decoration with a clear glass vase holding three white tulips. Describe the glass, scale, and contact shadow explicitly.
Use Bria GenFill to compare a wooden bowl and a ceramic bowl in the selected part of this photo. Keep the photo, selection, and random seed the same while changing the object description.
How to set up Bria GenFill 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 Bria GenFill
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/bria/genfill", "input": { "image_url": "https://storage.googleapis.com/falserverless/bria/bria_genfill_img.png", "mask_url": "https://storage.googleapis.com/falserverless/bria/bria_genfill_mask.png", "prompt": "A red delicious cherry" } }'
Then paste one of the prompts above: ChatGPT finds Bria GenFill on Spiral, shows the price and runs it.
Bria GenFill providers and prices
Spiral runs Bria GenFill through fal. Open a card for today's price, with every fee included.
Settings you can ask for
Bria GenFill works from your image URL, mask URL, and prompt. Ask ChatGPT for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Negative prompt | what to leave out, in words | The negative prompt you would like to use to generate images. | |
| Seed | 0 to 2147483647 | The same seed and the same prompt given to the same version of the model will output the same image every time. | |
| Number of images | 1 to 4 | 1 | Number of Images to generate. |
Every API field of Bria GenFill is on its tool page: open its card above.
What can you do with Bria GenFill in ChatGPT?
Explore targeted visual changes to a photo you provide. Ask a chat agent to turn your idea into a concrete object description, then compare edits in the existing scene.
Product photo prop changes
Select a prop beside a product and replace it with a different object. For example, try a ceramic dish in place of a wooden tray.
Seasonal campaign edits
Add a pumpkin, wrapped gift, or spring arrangement to a selected area of an existing campaign photo.
Interior styling previews
Replace a vase or table decoration in a room photo to compare styling ideas before arranging a shoot.
Food photo additions
Add a cherry or another garnish to a selected area of a food photo. Describe its size, surface contact, and shadow.
Localized campaign details
Try a different decorative object in an existing campaign image to explore a regional creative brief.
Website image revisions
Replace a distracting decorative object in an existing website photo with a simpler prop that suits the page.
Material concept previews
Regenerate a selected object as ceramic, wood, or brushed metal to compare material directions in the same scene.
More on Bria GenFill and ChatGPT
Overview
Bria GenFill in other agents
Questions about Bria GenFill in ChatGPT
Can ChatGPT use Bria GenFill?
Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Bria GenFill like any built-in tool.
How much does Bria GenFill cost in ChatGPT?
$0.052 per generation. Billed on `num_images`, default 1. 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 Bria GenFill in ChatGPT?
No. Spiral runs Bria GenFill 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 in ChatGPT?
About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.
Does ChatGPT wait while Bria GenFill runs?
Bria GenFill runs in the background. ChatGPT starts the run, checks on it and gives you the image when it's ready.
What is Bria GenFill useful for?
Use Bria GenFill to add or replace an object within a selected part of an existing image. Practical examples include replacing a table prop, changing a decorative object, or adding seasonal campaign details.
What kind of mask works best?
Bria recommends blob-shaped masks for GenFill. Start with a compact region around the intended object rather than asking one selection to cover several unrelated changes.
How should I write a Bria GenFill prompt?
Describe the object you want inside the selected area, including its material and size. Explain how it should sit on the surface and ask for a contact shadow that matches the scene.
Does Bria GenFill increase image resolution?
Bria documents GenFill as returning the edited image at its original resolution. Treat it as an editing tool rather than an upscaling step.
How can I repeat a result?
Keep the source image, mask, prompt, and seed unchanged, and use the same model version. The documented repeatability guarantee depends on keeping the seed, prompt, and model version the same.
Start using Bria GenFill 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


