← All models
Bria Product Holding edits a person photo to show the subject holding or carrying a product, using one to three product reference images and optional text instructions. Built on FIBO-Edit-1.5, it preserves the source aspect ratio by default and supports a selectable output aspect ratio.
images
Details
- Accepts
- image
Pricing
- Price
- 5 cr / image
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | integer | Random seed. The same seed with the same inputs returns the same image. |
| sync_mode | boolean | Return the image inline in the response instead of as a hosted URL. Adds latency. |
| instruction | — | Optional. A complete product-holding instruction already runs; this is appended to it. Use it for which hand, which way the label faces, or what must stay untouched. |
| aspect_ratio | — | Output aspect ratio. Left unset, the output keeps the ratio of the person image. |
| person_image_urlrequired | string | Photo of the person who will hold the product. Their identity, face, expression, clothing, pose and the background are preserved; only the arm and hand move. |
| product_image_urlsrequired | array | One to three reference images of the product to place: extra angles, its packaging, or a companion item. They describe one holding scene rather than three separate products. The product's geometry, colors, materials, branding and label text are reproduced as given. |
Output
| Field | Type | Description |
|---|---|---|
| image | — | The edited image, in the source aspect ratio unless aspect_ratio was set. |
| images | array | Single-element list holding the same image, kept for callers of the earlier Fibo Edit endpoint. |
| structured_instruction | object | The structured instruction the model ran, expanded from the built-in instruction plus anything passed in `instruction`. Returned so you can see how the brief was interpreted. |