<h3 id="sdxl-1.0-3wt5ymqkx">SDXL 1.0版本说明：</h3>我所使用到的Lora权重系数是:0.85，(我训练的Lora兼容性较好，您完全可以测试其他权重，找到适合您的为止）触发词：Looking through the bathroom door, a woman appeared in front of her with her arms raised, wearing handcuffs, leg shackles and toe cuffs我所使用的采样器为DPM++ 2M SDE-Karras，采样步数:30提示词相关系数4.5即可，您可以出横图、竖图、方图、任意格式的图均可，您可搭配自己的专属人像Lora来使用（女人是否穿衣服或穿什么样的服装取决于您的提示词描述）<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/51fd128c-1199-4e6a-b5fe-e4a74c77e1f1/width=525/51fd128c-1199-4e6a-b5fe-e4a74c77e1f1.jpeg" /><h3 id="sdxl-1.0-version-description:-m0h3saghf">SDXL 1.0 version description:</h3>The Lora weight coefficient I used is: 0.85, (the Lora I trained is more compatible, you can test other weights until you find the one that suits you)Trigger word: Looking through the bathroom door, a woman appeared in front of her with her arms raised, wearing handcuffs, leg shackles and toe cuffsThe sampler I used is DPM++ 2M SDE-Karras, sampling steps: 30The prompt word correlation coefficient is 4.5, you can produce horizontal, vertical, square, or any format of pictures, you can use it with your own exclusive portrait Lora (whether the woman wears clothes or what kind of clothes she wears depends on your prompt word description)<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/0b262e49-9354-4921-b6c6-d6de64fc8f05/width=525/0b262e49-9354-4921-b6c6-d6de64fc8f05.jpeg" />基于VAE模型训练的下载链接(Download link based on VAE model training)：<a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/sdxl-vae/resolve/main/sdxl_vae.safetensors">sdxl_vae.safetensors</a>如果你喜欢我的Lora，在决定是否使用“buzz”来鼓励我之前，你可以仔细查看我的主页作品。祝君出图愉快！If you like my Lora, you can take a closer look at my homepage works before deciding whether to use "buzz" to encourage me. I wish you happy drawing!

Files with SHA256: 76b0e4c8c01bcadcaffb90a0aca0a6267d7dc15fd9ac89c5be6cccb18bb7c26e