v2:本次v2更新加强训练了倒立人像、被遮挡面部的识别能力，同时增强了结构一致性，用法参见v1。经测试，采样器推荐：dpmpp_3m_sde+karras<hr />The v2 update has enhanced the recognition ability of inverted portraits and occluded faces, while also improving structural consistency. For usage, please refer to v1.recommended sampler：dpmpc_3m_ste+karras<hr /><hr />V1:用这个lora可以直出二次元头接三次元身体的图片，省去了自己PS的时间，也避免了看到转换效果一般的真人面部。训练集使用中英双语，皆可触发lora效果。中文提示词：把动画角色的身体转换成写实风格，保持头部风格不变。保持体型和原图一致。英文提示词：Transform the body of the anime character into a realistic style while keeping the head style unchanged.Keep the body shape consistent with the original image.权重建议：0.7-1<hr />With this lora, you can directly create a picture of a anime head connected to a third dimension body, which saves your PS time and avoids seeing a real face with ordinary conversion effects. The training set uses both Chinese and English, which can trigger the Lora effect.Chinese prompt: 把动画角色的身体转换成写实风格，保持头部风格不变。保持体型和原图一致。English prompt: Transform the body of the anime character into a realistic style while keeping the head style unchanged.Keep the body shape consistent with the original image.Weight: 0.7-1<hr />最后，感谢以下AI内容创作者（排名不分先后）给予的训练集帮助<a target="_blank" rel="ugc" href="https://www.pixiv.net/users/84309178">https://www.pixiv.net/users/84309178</a><a target="_blank" rel="ugc" href="https://www.pixiv.net/users/92969522">https://www.pixiv.net/users/92969522</a><a target="_blank" rel="ugc" href="https://www.pixiv.net/users/18674580">https://www.pixiv.net/users/18674580</a><a target="_blank" rel="ugc" href="https://www.pixiv.net/users/92077297">https://www.pixiv.net/users/92077297</a><a target="_blank" rel="ugc" href="https://www.pixiv.net/users/104182689">https://www.pixiv.net/users/104182689</a><a target="_blank" rel="ugc" href="https://www.pixiv.net/users/83125362">https://www.pixiv.net/users/83125362</a><a target="_blank" rel="ugc" href="https://www.pixiv.net/users/45359735">https://www.pixiv.net/users/45359735</a>以及其他给予了帮助的朋友。训练使用的所有素材均为AI生成，示例图片仅作为测试模型泛化性，与训练素材无关。

Qwen edit2511__2to3 keep the head

本次v2更新加强训练了倒立人像、被遮挡面部的识别能力，同时增强了结构一致性，用法参见v1。The v2 update has enhanced the recognition ability of inverted portraits and occluded faces, while also improving structural consistency. For usage, please refer to v1.

Files with SHA256: 485b9ad3051bdbadfc0ac16c2222de0c072f8b9aa1db8d2451ba643ca0a86bb7