0.5 credits<\/strong><\/p>\nThis endpoint analyzes a model photo before you run the try-on. It checks whether the image meets the requirements the pipeline needs: is there one person clearly visible, are they facing forward, is the body large enough in the frame, is the pose readable?<\/p>\n
The response tells you two things: whether the image is usable (is_good: true\/false<\/code>), and which garment types that model image can support (good_clothes_types: [\"upper\", \"lower\", \"full\"]<\/code>). A full-body standing photo will return all three. A cropped torso shot might only return\u00a0upper<\/code>.<\/p>\nError codes are specific, not generic:<\/p>\n
\n400001<\/code>\u00a0\u2014 No person detected<\/li>\n400002<\/code>\u00a0\u2014 More than one person in frame<\/li>\n400003<\/code>\u00a0\u2014 Person not facing forward<\/li>\n400004<\/code>\u00a0\u2014 Person too small in image<\/li>\n410001<\/code>\u00a0\u2014 Warning: person slightly small, crop recommended<\/li>\n410002\/410003<\/code>\u00a0\u2014 Warning: pose is unclear, results may vary<\/li>\n<\/ul>\nThe difference between 400x and 410x codes matters in production. A 400x means the image will fail or produce a bad result \u2014 reject it before spending a try-on credit. A 410x means the image is borderline \u2014 you can proceed but should warn the user the result may not be optimal.<\/p>\n
Why most competitors don’t have this:<\/strong>\u00a0FASHN.ai, Claid, and Kling don’t offer a dedicated model validation endpoint. You find out your image is unsuitable when the generation fails or produces a distorted result \u2014 after the credit is consumed.<\/p>\n