<h1 id="heading-6">Box series - Dragon and Maiden</h1>Model idea: 2023 New Year dragon.Model use: illustration, packaging.Bottom mold recommendation: The whole net first | SHMILY classical colorful _v1.0,VAE is recommended: vae- FT-MSE-84000-EMA-Pruned.safetensorsSampler recommended: DPM++ 2M Karras,Recommended number of iteration steps: 30It is recommended to open the HD repair: the magnification algorithm is R-ESRGAN 4x+ Anime6B, magnification is 2 times, and the redraw amplitude is 0.3~0.6ADetailer is enabled. Recommended AD model: face_<a target="_blank" rel="ugc" href="http://yolov8n.pt">yolov8n.pt</a>The recommended weight of lora is 0.5-0.85CFG: 5.5CLIP Recommended: 2The generalization is very good and can be combined with other lora, I hope you can return more pictures and praise more, thank you<h1 id="heading-7">盒子系列——龙与少女</h1>模型创意：2023新年龙。模型用途：插画，包装。底模推荐：全网首发｜SHMILY古典炫彩_v1.0，VAE推荐开：vae-ft-mse-840000-ema-pruned.safetensors采样器推荐：DPM++ 2M Karras，迭代步数推荐：30推荐开启高清修复：放大算法为R-ESRGAN 4x+ Anime6B，放大2倍，重绘幅度为0.3~0.6ADetailer开启，AD模型推荐：face_<a target="_blank" rel="ugc" href="http://yolov8n.pt">yolov8n.pt</a>lora权重推荐0.5-0.85CFG为：5.5CLIP推荐：2泛化性很好可结合其他lora，希望大家多返图多点赞，谢谢

Box series - Dragon and Maiden<盒子系列——龙与少女>

盒子系列——龙与少女_新春1.0.safetensors

v1.0

模型创意：2023新年龙。模型用途：插画，包装。底模推荐：全网首发｜SHMILY古典炫彩_v1.0，VAE推荐开：vae-ft-mse-840000-ema-pruned.safetensors采样器推荐：DPM++ 2MKarras，迭代步数推荐：30推荐开启高清修复：放大算法为R-ESRGAN 4x+Anime6B，放大2倍，重绘幅度为0.3~0.6ADetailer开启，AD模型推荐：face_<a target="_blank" rel="ugc"href="http://yolov8n.pt">yolov8n.pt</a>lora权重推荐0.5-0.85CFG为：5.5CLIP推荐：2泛化性很好可结合其他lora，希望大家多返图多点赞，谢谢

盒子系列——龙与少女

The recommended weight of lora is 0.5-0.85Box series - Dragon and Maiden<ul><li>Model idea: 2023 New Year dragon.</li><li>Model use: illustration, packaging.</li><li>Bottom mold recommendation: The whole net first | SHMILY classical colorful _v1.0,</li><li>VAE is recommended: vae- FT-MSE-84000-EMA-Pruned.safetensors</li><li>Sampler recommended: DPM++ 2M Karras,</li><li>Recommended number of iteration steps: 30</li><li>It is recommended to open the HD repair: the magnification algorithm is R-ESRGAN 4x+ Anime6B, magnification is 2 times, and the redraw amplitude is 0.3~0.6</li><li>ADetailer is enabled. </li><li>Recommended AD model: face_yolov8n.pt</li><li>CFG: 5.5</li><li>CLIP Recommended: 2</li></ul>The generalization is very good and can be combined with other lora, I hope you can return more pictures and praise more, thank you

Files with SHA256: b9c7b6e26df94eb5f7858107354a5137dc0691d19fd84360550437986c967d1e