99coins/ADetailer Head Accessory Segmentation / 帽子・王冠の検知

Anime Accessories Detection Model Detect Hats, Hair Ornaments, and Tiaras with Precision! This model is designed for use with ADetailer (an extension) and has been trained on 816 diverse anime images. Why This Model? Hats and hair ornaments are like a second face for anime characters. Yet, these intricate details can often blur or distort during image generation when they’re small. To address this challenge, this detection model was created! Using a segmentation-based approach, the model avoids the pitfalls of bounding box (bbox) methods, such as unintentionally including the character’s face.

<iframe src="https://silytics.si/embed/item/f7ada72a-cab4-46c0-bf15-c90d03d3323f" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 16 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.