作者: | Chenkin |
最后更新: | 2024年4月11日 |
文件类型: | LORA |
基本模型: | SDXL 1.0 |
模型版本: | v3.0 |
使用介绍
V3.0 verson
更好的还原度,更好的人体,更温馨的画风
训练模型:Animagine XL V3.1
推理模型:Animagine XL V3.1
训练分辨率:1024*1024
建议输出分辨率:1024*1280 /832*1216
推荐型号重量:0.8~1
24.4.10更新:Animagine XL V3.1训练
封面提示词
<lora:comiclo_a31:1>,1girl, solo, black hair, fruit, black eyes, tree, food, coat, hair ornament, orange (fruit), looking at viewer, upper body, short hair, closed mouth, bangs, fur trim, outdoors, hair bobbles, jacket, hood down, day, leaf, zipper, mandarin orange, winter clothes, frown, twintails, branch, turtleneck, long sleeves, sunlight, expressionless
Negative prompt: lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, white border,
Steps: 20, Size: 832x1216, Seed: 3059131888, Model: animagine-xl-3.1, Version: v1.8.0, Sampler: DPM++ 2M Karras, CFG scale: 7, Clip skip: 2, Model hash: e3c47aedb0, Downcast alphas_cumprod: True, Discard penultimate sigma: True
本内容及资源均来自网络,版权归原作者所有,仅供个人学习研究,请勿商用和侵犯他人肖像,如需商用请联系原作者。若原作者内容有侵权之处请速联系我们,我们将会在24小时内删除。