Technical Specifications of bria/expand-image
| Specification | Details |
|---|---|
| Model ID | bria/expand-image |
| Provider / model family | Bria Expand, an image expansion and outpainting model from Bria |
| Primary task | Expand an image beyond its original borders by generating new pixels to fit a wider or taller composition |
| API operation type | Image editing / outpainting endpoint |
| Official Bria endpoint | POST /v2/image/edit/expand on Briaโs image editing API |
| Input image formats | JPEG, JPG, PNG, WEBP; image can be provided as base64 or as a publicly accessible URL |
| Output behavior | Returns an expanded image URL; Bria v2 can return synchronous results or asynchronous responses with request_id and status_url depending on processing mode |
| Aspect ratio controls | Supports preset ratios such as 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, and 16:9, plus custom float ratios from 0.5 to 3.0 |
| Canvas controls | Can use explicit canvas_size, original_image_size, and original_image_location when not using aspect_ratio |
| Canvas limits | Recommended canvas area is within 5000ร5000 pixels total area, with a maximum allowed area of 25 million pixels for explicit canvas sizing |
| Prompt support | Optional English-language prompt can guide the expansion; if omitted, Bria can auto-generate a prompt from the input image |
| Moderation options | Supports prompt moderation and visual output moderation controls in the Bria API |
| Commercial positioning | Bria describes the model as trained exclusively on licensed data for safe commercial use |
What is bria/expand-image?
bria/expand-image is CometAPIโs platform identifier for Briaโs image expansion model, designed to extend an existing image beyond its original boundaries while preserving visual continuity. In practice, it is an outpainting model: instead of cropping an image to fit a new format, it generates additional content around the original image so the final result matches a target aspect ratio or canvas layout.
This model is aimed at workflows such as adapting creatives for social media placements, converting portrait images into landscape banners, creating extra background around a subject, or reframing product and marketing visuals without manually editing every asset. Briaโs documentation places this capability inside its broader image editing API suite, alongside tools like background editing, erasing, generative fill, and upscaling.
A notable part of Briaโs positioning is enterprise and commercial readiness. Bria states that its models are trained on licensed data and markets them as suitable for lower-risk commercial usage, which may matter for teams building production design, brand, or ecommerce pipelines.
Main features of bria/expand-image
- High-quality image outpainting: Extends images beyond their borders by generating new pixels that continue the original scene, instead of simply stretching or cropping the source.
- Aspect-ratio adaptation: Lets you expand to common target formats like
16:9,9:16,1:1, and more, which is useful for repurposing one asset across channels. - Precise canvas placement: Supports
canvas_size,original_image_size, andoriginal_image_locationso developers can control exactly where the original image sits inside the new composition. - Optional prompt guidance: Accepts a text prompt to steer the newly generated regions; if no prompt is supplied, the service can automatically derive one from the image.
- Flexible input methods: Accepts either base64-encoded image data or a publicly accessible image URL, making it straightforward to connect with web apps, asset pipelines, and automation systems.
- Production-friendly API flow: Bria v2 supports asynchronous processing with
request_idandstatus_url, which is useful for longer-running image jobs and backend orchestration. - Built-in moderation options: Includes prompt and output moderation settings to help teams enforce policy controls in production integrations.
- Commercial-use positioning: Bria markets the model as trained on licensed data for safer commercial deployment, which can be relevant for enterprise content operations.
How to access and integrate bria/expand-image
Step 1: Sign Up for API Key
To get started, sign up on CometAPI and generate your API key from the dashboard. Once you have an API key, you can authenticate requests to the bria/expand-image model and any other supported models on the platform.
Step 2: Send Requests to bria/expand-image API
Use CometAPI's Bria-compatible endpoint at POST /bria/image/edit/expand-image.
curl https://api.cometapi.com/bria/image/edit/expand-image \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $COMETAPI_API_KEY" \
-d '{
"prompt": "A paper boat floating on calm water at sunrise.",
"num_results": 1
}'
Step 3: Retrieve and Verify Results
The API returns a task ID. Poll GET /bria/{task_id} to check processing status and retrieve the output image URL when complete.