Remove image background using advanced AI models including U-Net, BiRefNet, and SAM with support for multiple input formats and GPU acceleration
84
Pending
Does it follow best practices?
Impact
84%
0.94xAverage score across 10 eval scenarios
Pending
The risk profile of this skill
{
"context": "This criteria evaluates how well the engineer uses the rembg package to implement a command-line image background removal tool. The focus is on correct usage of rembg's remove() function and proper handling of image data formats supported by the package.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Uses remove function",
"description": "The solution imports and calls the remove() function from the rembg package to process the image",
"max_score": 50
},
{
"name": "Correct input format",
"description": "The solution passes image data to rembg.remove() in one of the supported formats (bytes, PIL.Image object, or numpy array) rather than attempting to pass file paths directly",
"max_score": 25
},
{
"name": "Output handling",
"description": "The solution correctly handles the output from rembg.remove(), which returns the same type as the input (bytes, PIL.Image, or numpy array), and saves it appropriately to preserve the alpha channel",
"max_score": 25
}
]
}evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10