Because it is based on LoRA but is trained with Conv2DMain tag : gusset, Secondary tag : pantyhose, thighband pantyhose, panties under pantyhose, no panties, Color tag : color pantyhose, color panties, Pose tag : from behind, from below, ass, sitting, standing, LoRA str : 1 Denoising str : &lt;0.4Conv2D requires need extensions <a target="_blank" rel="ugc" href="https://github.com/KohakuBlueleaf/a1111-sd-webui-lycoris￼or￼https://github.com/kohya-ss/sd-webui-additional-networks">https://github.com/KohakuBlueleaf/a1111-sd-webui-lycoris </a>or<a target="_blank" rel="ugc" href="https://github.com/KohakuBlueleaf/a1111-sd-webui-lycoris￼or￼https://github.com/kohya-ss/sd-webui-additional-networks"> https://github.com/kohya-ss/sd-webui-additional-networks</a><img src="https://i.imgur.com/UqTCaUb.png" />

Files with SHA256: abb274247a69f1c88dbd1a05009575ee1ea20f9fc23ffb723ebdad9d77a6888a