# RMBG-3.0

> RMBG-3.0 removes backgrounds and returns a transparent PNG. It holds up on hard cases: group shots, motion blur, mesh and openwork, shadows and reflections. It keeps product text and logos intact. Built on Fibo 2.0 and trained only on licensed data.


## Overview

- **Endpoint**: `https://fal.run/bria/rmbg-3`
- **Model ID**: `bria/rmbg-3`
- **Category**: image-to-image
- **Kind**: inference
**Description**: Remove backgrounds with clean cutouts on hard images: group shots, mesh, hair and product text. Bria RMBG-3.0 returns a transparent PNG. Licensed data.

RMBG-3.0 is Bria's background removal model. Send one image in image_url and get back image, a PNG with an alpha channel at the same size as the input. It is built for the cases that usually fail: it keeps every person in a group shot and motion-blurred limbs, clears the gaps in chain-link, cages, bicycle spokes, chair rungs and openwork instead of filling them in, keeps packaging, white products and dark lids solid, leaves shadows and reflections out of the cutout, and keeps product text, labels and logos intact.

It is a 4-step distilled model built on Bria's Fibo 2.0, trained only on licensed data, with clear commercial rights. A request takes a few seconds per image. sync_mode returns the image directly in the response, with added latency.

Truly transparent objects such as glass, veils, nets, smoke and splashes still tend to come out opaque, and in busy, low-contrast scenes it can sometimes pull in nearby grass, props or a watermark.

For editing the image after the cutout, use Fibo 2.0 Edit. For video, use Bria Video Background Removal v3.

**Tags**: background removal, remove background API, transparent PNG, alpha matte, image segmentation, product cutout, e-commerce, catalog automation, hair matting, commercial use, licensed AI



## Pricing

Billing is calculated per image. Your request will cost **$0.018** per image. For example, removing the background from **100 images** costs **$1.80**.

For more details, see [fal.ai pricing](https://fal.ai/pricing).

## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:


- **`image_url`** (`string`, _required_):
  Input image to remove the background from (file or URL).
  - Examples: "https://labs-assets.bria.ai/fal-examples/rmbg-3/crochet/input.png", "https://labs-assets.bria.ai/fal-examples/rmbg-3/scarf/input.png", "https://labs-assets.bria.ai/fal-examples/rmbg-3/dandelion/input.png"

- **`sync_mode`** (`boolean`, _optional_):
  If true, returns the image directly in the response (increases latency).
  - Default: `false`



**Required Parameters Example**:

```json
{
  "image_url": "https://labs-assets.bria.ai/fal-examples/rmbg-3/crochet/input.png"
}
```


### Output Schema

The API returns the following output format:

- **`image`** (`Image`, _required_):
  The input image with its background removed: a PNG with an alpha channel.



**Example Response**:

```json
{
  "image": {
    "url": "",
    "content_type": "image/png",
    "file_name": "z9RV14K95DvU.png",
    "file_size": 4404019,
    "width": 1024,
    "height": 1024
  }
}
```


## Usage Examples

### cURL

```bash
curl --request POST \
  --url https://fal.run/bria/rmbg-3 \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
     "image_url": "https://labs-assets.bria.ai/fal-examples/rmbg-3/crochet/input.png"
   }'
```

### Python

Ensure you have the Python client installed:

```bash
pip install fal-client
```

Then use the API client to make requests:

```python
import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "bria/rmbg-3",
    arguments={
        "image_url": "https://labs-assets.bria.ai/fal-examples/rmbg-3/crochet/input.png"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)
```

### JavaScript

Ensure you have the JavaScript client installed:

```bash
npm install --save @fal-ai/client
```

Then use the API client to make requests:

```javascript
import { fal } from "@fal-ai/client";

const result = await fal.subscribe("bria/rmbg-3", {
  input: {
    image_url: "https://labs-assets.bria.ai/fal-examples/rmbg-3/crochet/input.png"
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);
```


## Deploy your own model

To run your own weights, a fine-tune or a custom pipeline on the GPUs that serve this API, deploy it on fal Serverless. GPUs from H100 (80GB) to B300 (288GB), billed per second; an H100 is $4.50/h list, as low as $2.49/h. Prices, GPU specs and deploy steps: [fal Serverless](https://fal.ai/serverless.md).

## Additional Resources

### Documentation

- [Model Playground](https://fal.ai/models/bria/rmbg-3)
- [API Documentation](https://fal.ai/models/bria/rmbg-3/api)
- [OpenAPI Schema](https://fal.ai/api/openapi/queue/openapi.json?endpoint_id=bria/rmbg-3)

### fal.ai Platform

- [Platform Documentation](https://fal.ai/docs/documentation)
- [Python Client](https://fal.ai/docs/api-reference/client-libraries/python)
- [JavaScript Client](https://fal.ai/docs/api-reference/client-libraries/javascript)

### Other agent-readable surfaces

This file covers one model. To find anything else:

- [Platform overview](https://fal.ai/llms.txt): Entry points and representative endpoint IDs
- [Documentation index](https://fal.ai/docs/llms.txt): Every documentation page
- [Full documentation text](https://fal.ai/docs/llms-full.txt): The whole documentation inlined
- [Pricing](https://fal.ai/pricing.md): Model API and Serverless GPU prices
- [fal Serverless](https://fal.ai/serverless.md): Deploy your own models: GPU prices, specs and steps
- Any other model: `https://fal.ai/models/<endpoint-id>/llms.txt`
