qa_check
Run a quality control check on generated images to evaluate accuracy, consistency, and composition, returning a structured verdict with scores and issues.
Instructions
Run a quality-control check on a generated image and return a structured verdict.
Call this immediately after generating an image, before showing it to the user.
Parameters:
image_path: Absolute path to the generated image to review.
reference_images: Optional list of reference image paths to compare against (e.g. character/style references). Up to 3 are used.
character_rules: Free-text rules the image must follow, e.g. "The pilot has NO eyebrows; the jacket has horizontal stripes."
style_notes: Free-text description of the expected visual style.
scene_type: One of solo, portrait, battle, combat, group, action, interview. Adjusts composition expectations (e.g. portraits may face camera).
pass_threshold: Minimum overall score (0-1) to pass. Default 0.7.
Returns a dict with: passed (bool), overall_score, character_accuracy, style_consistency, quality_score, composition_score (all 0-1), issues (list of {severity, category, description, recommendation}), should_regenerate (bool), notes, and model.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| image_path | Yes | ||
| scene_type | No | group | |
| style_notes | No | ||
| pass_threshold | No | ||
| character_rules | No | ||
| reference_images | No |