使用介绍
v3.1 更新训练集(550张)
所有样图均使用Animagine XL V3.1生成。推荐强度:0.8。
使用人物LoRA时,使用sd-webui-lora-block-weight扩展的OUTALL功能可以减少样式LoRA对人物特征的影响。
使用提示: | CLIP SKIP: 2 STRENGTH: 0.8 |
封面提示
1girl, sensitive, solo, long hair, breasts, looking at viewer, blush, blue eyes, blonde hair, gloves, dress, hair between eyes, bare shoulders, upper body, outdoors, parted lips, pointy ears, day, elbow gloves, halterneck, sunlight, elf, gem
Negative prompt: lowres, mosaic censoring, bar censor, stripe, censored, 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,
Steps: 80, Size: 768x1280, Seed: 470661104094595, Model: large\animagineXLV31_v31.safetensors, Sampler: dpmpp_2m_sde_gpu_sgm_uniform, Clip skip: 2, CFG Scale: 6.0, Model hash: e3c47aedb0
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。