image generation
Eraser
EraserBria Eraser enables precise removal of unwanted objects from images while maintaining high-quality outputs.
Model details
Example usage
Bria Eraser enables precise removal of unwanted objects from images while maintaining high-quality output. It's roughly 6B parameters in size, takes an image as input and produces an image as output, preserving the original resolution (no resize or downscale). It's trained exclusively on licensed data for safe, risk-free commercial use.
Available on Hugging Face: https://huggingface.co/spaces/briaai/BRIA-Eraser-API
Full documentation is available here.
✕
The model is available under a commercial-use license via Bria, trained exclusively on licensed data with full IP indemnification for generated outputs.
Input
1import os
2import requests
3
4url = os.environ["MODEL_API_URL"]
5
6payload = {
7 "image": "https://labs-assets.bria.ai/sandbox-example-inputs/eraser_image_example.jpg",
8 "mask": "https://labs-assets.bria.ai/sandbox-example-inputs/eraser_mask_example.jpg"
9}
10
11headers = {
12 "Content-Type": "application/json",
13 "api_token": os.environ['MODEL_API_KEY']
14}
15
16response = requests.post(url, json=payload, headers=headers)
17
18data = response.json()
19print(data)
20JSON output
1{
2 "result": {
3 "image_url": "string"
4 },
5 "request_id": "string"
6}
