← All models
Bria Expand extends an image beyond its borders to any of 9 aspect ratios or a custom canvas up to 25 megapixels. Built on FIBO-Edit-1.5, with optional prompt guidance for the new area and the original pixels kept at full resolution.
images
Details
- Accepts
- text
Pricing
- Price
- 5 cr / image
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | — | Reuse the seed from a previous response to recreate that result. Omit it for a random one, which is reported in the response either way. |
| prompt | — | What should appear in the expanded area. Omit it and the model is asked only to extend the image, which is usually what you want for a plain canvas change. |
| image_urlrequired | string | The image to expand (file or URL). |
| sync_mode | boolean | If true, returns the image directly in the response (increases latency). |
| canvas_size | — | The desired size of the final image after the expansion, as [width, height]. Area must be under 25 megapixels. Pairs with 'original_image_location'. |
| aspect_ratio | — | The desired aspect ratio of the final image. Used over 'original_image_size' and 'original_image_location' if provided: the original is centred and the canvas grows around it. |
| preserve_alpha | boolean | Keep the input's transparency. The model works in RGB, so the alpha channel is not generated -- the original's own is extended outwards by replicating its edges, which is what expanding a cutout means. Turn it off to get a flattened RGB result. |
| negative_prompt | — | Not supported by this model, and refused rather than ignored -- see 'prompt'. Present only so a request written against the SDXL expansion endpoint fails loudly here instead of silently losing the field. |
| original_image_size | — | The desired size of the original inside the canvas, as [width, height]; it is resized to this before being placed. Ignored if 'aspect_ratio' is provided. |
| return_model_output | boolean | Also return the model's own frame, before the original was pasted back and the seam blended. Diagnostic only -- it does not change the returned image. Use it to tell a bad generation apart from a bad composite: a boundary already broken in that frame came from the model, not from post-processing. |
| original_image_location | — | Top-left corner of the original within the canvas, as [x, y]. May sit outside the canvas, in which case the original is cropped. Ignored if 'aspect_ratio' is provided. |
| retain_original_quality | boolean | Keep the original's own pixels at full resolution. Generation happens near one megapixel, so a larger canvas is scaled up afterwards; leave this on and the region the mask protected is not resampled at all. Turn it off for a uniformly soft result, which can hide the seam on a textured background. |
Output
| Field | Type | Description |
|---|---|---|
| seed | integer | The seed used, so the result can be reproduced. |
| image | — | The expanded image. |
| model_output | — | The model's own frame at the requested canvas size, with nothing pasted or blended into it. Only present when 'return_model_output' was set. |
| structured_instruction | object | The structured prompt the model conditioned on. |