CtrlK
BlogDocsLog inGet started
Tessl Logo

tessl/pypi-rembg

Remove image background using advanced AI models including U-Net, BiRefNet, and SAM with support for multiple input formats and GPU acceleration

84

0.94x
Overview
Eval results
Files

rubric.jsonevals/scenario-9/

{
  "context": "This criteria evaluates how well the engineer uses the rembg package's specialized model capabilities to solve a domain-specific background removal problem. The evaluation focuses on correct model selection and proper usage of the rembg API for specialized segmentation tasks.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "Anime model usage",
      "description": "Uses the isnet-anime model (or equivalent anime-specialized model) when mode is 'anime'",
      "max_score": 25
    },
    {
      "name": "Portrait model usage",
      "description": "Uses the birefnet-portrait model (or equivalent portrait-optimized model like u2net_human_seg) when mode is 'portrait'",
      "max_score": 25
    },
    {
      "name": "Clothing model usage",
      "description": "Uses the u2net_cloth_seg model (or equivalent clothing-specialized model) when mode is 'clothing'",
      "max_score": 25
    },
    {
      "name": "Remove function usage",
      "description": "Uses the rembg.remove() function to perform background removal with appropriate model parameter",
      "max_score": 15
    },
    {
      "name": "Model specification",
      "description": "Correctly specifies the model using either the model parameter in remove() or by creating a session with new_session()",
      "max_score": 10
    }
  ]
}

Install with Tessl CLI

npx tessl i tessl/pypi-rembg

tile.json