暗香Lora,人物角色身穿汉服,背景梅花和山水。愿意是想在画面中体现中国古典人物,素雅和飘逸的风格。
灵感来源于【瑶圃先春图】和 【会真全图.西厢故事图卷】
因为素材图比较少,可能姿势比较单一,大家可以通过controlnet的插件尝试不同的Pose姿势和背景。
使用多个大模型anxiang Lora在Stable Diffusion制作的绘图作品,我会给出Stable Diffusion提示指令,各位可以自己尝试微调不同人物场景,请在社区分享您的作品,我会继续改进。喜欢请给我一个赞,谢谢!
(masterpiece, top quality, best quality, official art, beautiful and aesthetic:1.2), (1girl:1.4), extreme detailed,(joshua middleton comic cover art:1.1), (Action painting:1.2),(concretism:1.2),theater dance scene,(hypermaximalistic:1.5),colorful,highest detailed,<lora:anxiang:0.55>,
Negative prompt: (worst quality, low quality:2), monochrome, zombie,overexposure, watermark,text,bad anatomy,bad hand,extra hands,extra fingers,too many fingers,fused fingers,bad arm,distorted arm,extra arms,fused arms,extra legs,missing leg,disembodied leg,extra nipples, detached arm, liquid hand,inverted hand,disembodied limb, small breasts, loli, oversized head,extra body,completely nude, extra navel,easynegative,(hair between eyes),sketch, duplicate, ugly, huge eyes, text, logo, worst face, (bad and mutated hands:1.3), (blurry:2.0), horror, geometry, bad_prompt, (bad hands), (missing fingers), multiple limbs, bad anatomy, (interlocked fingers:1.2), Ugly Fingers, (extra digit and hands and fingers and legs and arms:1.4), ((2girl)), (deformed fingers:1.2), (long fingers:1.2),(bad-artist-anime), bad-artist, bad hand, extra legs ,(ng_deepnegative_v1_75t)
Steps: 30, Eta: 0.67, ENSD: 31337, Size: 512x768, Seed: 2405365521, Model: xxmix9realistic_v40, model: control_v11p_sd15_inpaint [ebff9138], weight: 1.0, Sampler: Euler a, CFG mode: Half Cosine Up, CFG scale: 12, Clip skip: 2, Mimic mode: Half Cosine Down, Model hash: 18ed2b6c48, Mimic scale: 7, resize mode: ResizeMode.INNER_FIT, (low quality: 2), control mode: ControlMode.BALANCED, "preprocessor: inpaint_global_harmonious, pixel perfect: True, (worst quality: 2), (normal quality: 2),lowres,watermark,", ADetailer model: face_yolov8n.pt, starting/ending: (0.0, 1.0), ADetailer prompt: "beautiful face,masterpiece, tsurime, ", ADetailer version: 23.7.1, CFG scale minimum: 4.5, ADetailer mask blur: 4, Mimic scale minimum: 5, preprocessor params: (-1, -1, -1)", ADetailer confidence: 0.3, Threshold percentile: 97, ADetailer dilate/erode: 32, ADetailer inpaint padding: 32, ADetailer negative prompt: "ng_deepnegative_v1_75t,badhandv4, ADetailer ControlNet model: control_v11p_sd15_inpaint [ebff9138], ADetailer ControlNet module: inpaint_global_harmonious, ADetailer denoising strength: 0.4, Dynamic thresholding enabled: True, ADetailer inpaint only masked: True
下载Lora模型
下载SD绘图工具
希望你喜欢使用这个AI模型,就像我们创造它一样!如果您有任何问题或建议,请在Qpipi社区分享。
使用Qpipi读图提示功能,获取图片TAG Prompt提示
开箱即用!ComfyUI:强大、模块化的 Stable Diffusion 操作界面和后端
强大的开源AI绘图工具Stable Diffusion Webui最全本地安装指南
Stable Diffusion一键安装懒人包新版,Easy Diffusion支持Windows、Mac绿色安装包
找不到你想要的AI绘画模型下载?请在SD社区或者评论留言告诉我们!
🎨享受精美的AI绘图乐趣!
© 版权声明
分享是一种美德,转载本站图文等内容,请保留 Qpipi.com 原文链接,谢谢你的支持!
THE END
- 最新
- 最热
只看作者