Stable Diffusion - Candy Land (糖果世界) LoRA 提示词配置与效果展示

欢迎关注我的CSDN:https://spike.blog.csdn.net/

本文地址:https://spike.blog.csdn.net/article/details/132145248

糖果世界 (Candy Land) 是一个充满甜蜜和奇幻的地方,由各种各样的糖果和巧克力构成。在糖果世界,可以看到:

  • 用棒棒糖和棉花糖做成的彩虹桥,在阳光下闪闪发光。
  • 用巧克力和牛奶做成的河流,在流淌的时候发出诱人的香气。
  • 用饼干和奶油做成的城堡,在高高的山峰上屹立着。
  • 用果冻和软糖做成的花园,在风中摇曳着。
  • 用糖果和蛋糕做成的小屋,在绿色的草地上散落着。

糖果世界是一个让人快乐和满足的地方,可以尽情地品尝各种美味的糖果和巧克力,不过,也要注意不要吃太多哦!

Candy Land 正向提示词设计:

bash 复制代码
# 质量
(masterpiece, best quality:1.2),highly detailed,extremely detailed,8k,

# 通用
1girl,solo,full body,pose,beautiful woman,looking at viewer,depth of field,sharp focus,full background,detailed eyes,detailed face,detailed hands,nice figure,

# 脸部
updo,curls,long hair,ponytail,smile,naughty face,purple eyes,

# 身体
head tilt,arms up,sitting,frilled skirt,center frills,heels,

# 其他
(hyperrealistic:0.2),(pinup:0.2),(bloom:0.2),

# 特色
fantasy,dynamic,shiny,details,perfect,beautiful,dreamy,heart,colorful,vivid,candyland,candy print,candy clothing,rainbow,syrup,cookie,macaron,chocolate bar,glitter,various colors,gradients,dripping,glaze,beads,<lora:Candyland:0.75>,

合并提示词:

bash 复制代码
(masterpiece, best quality:1.2),highly detailed,extremely detailed,8k,
1girl,solo,full body,pose,beautiful woman,looking at viewer,depth of field,sharp focus,full background,detailed eyes,detailed face,detailed hands,nice figure,
updo,curls,long hair,ponytail,smile,naughty face,purple eyes,
head tilt,arms up,sitting,frilled skirt,center frills,heels,
(hyperrealistic:0.2),(pinup:0.2),(bloom:0.2),
fantasy,dynamic,shiny,details,perfect,beautiful,dreamy,heart,colorful,vivid,candyland,candy print,candy clothing,rainbow,syrup,cookie,macaron,chocolate bar,glitter,various colors,gradients,dripping,glaze,beads,<lora:Candyland:0.75>,

Candy Land 负向提示词设计:

bash 复制代码
# Embeddings
(ng_deepnegative_v1_75t:1.2),EasyNegative,(badhandv4:1.1),

# 身体
bad anatomy,disfigure,(deformed limbs and arms and legs),(strange hands and fingers),toes,

# 通用
(nsfw,breast,cleavage:1.1),(worst quality, bad quality:1.1),jpeg artifacts,lowres,normal quality,low quality,

# 构图
cropped,border,out of frame,bad composition,blurry,debris,messy,

# 颜色
spikes,sepia,clutter,monochrome,greyscale,oversaturated,

# 其他
deformed,taut,ugly,skin tight,dirt face,

# 风格
realistic,

合并提示词:

复制代码
(ng_deepnegative_v1_75t:1.2),EasyNegative,(badhandv4:1.1),
bad anatomy,disfigure,(deformed limbs and arms and legs),(strange hands and fingers),toes,
(nsfw,breast,cleavage:1.1),(worst quality, bad quality:1.1),jpeg artifacts,lowres,normal quality,low quality,
cropped,border,out of frame,bad composition,blurry,debris,messy,
spikes,sepia,clutter,monochrome,greyscale,oversaturated,
deformed,taut,ugly,skin tight,dirt face,
realistic,

其他配置默认:

效果:

提示词 long sleeves,[crew neck|turtleneck],显著增加衣服数量。

提示词:

python 复制代码
(masterpiece, best quality:1.2),highly detailed,extremely detailed,8k,
1girl,solo,full body,pose,beautiful woman,looking at viewer,depth of field,sharp focus,full background,detailed eyes,detailed face,detailed hands,nice figure,
updo,curls,long hair,ponytail,smile,naughty face,purple eyes,
head tilt,arms up,sitting,frilled skirt,center frills,heels,long sleeves,[crew neck|turtleneck],
(hyperrealistic:0.2),(pinup:0.2),(bloom:0.2),
fantasy,dynamic,shiny,details,perfect,beautiful,dreamy,heart,colorful,vivid,candyland,candy print,candy clothing,rainbow,syrup,cookie,macaron,chocolate bar,glitter,various colors,gradients,dripping,glaze,beads,<lora:Candyland:0.75>,
Negative prompt: (nsfw:1.2),breast,cleavage,
(negative_hand,ng_deepnegative_v1_75t:1.3),EasyNegative, badhandv4,
bad anatomy,disfigure,(deformed limbs and arms and legs),(strange hands and fingers),toes,
(worst quality, bad quality:1.1),jpeg artifacts,lowres,normal quality,low quality,
cropped,border,(out of frame:1.1),bad composition,blurry,debris,messy,
spikes,sepia,clutter,monochrome,greyscale,oversaturated,
deformed,taut,ugly,skin tight,dirt face,
realistic,
Steps: 35, Sampler: DPM++ 2M SDE Karras, CFG scale: 7, Seed: 3100369101, Size: 512x768, Model hash: ed989d673d, Model: Dreamshaper_7, Denoising strength: 0.3, Clip skip: 2, ADetailer model: face_yolov8n.pt, ADetailer confidence: 0.3, ADetailer dilate/erode: 4, ADetailer mask blur: 4, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer model 2nd: hand_yolov8n.pt, ADetailer confidence 2nd: 0.3, ADetailer dilate/erode 2nd: 4, ADetailer mask blur 2nd: 4, ADetailer denoising strength 2nd: 0.4, ADetailer inpaint only masked 2nd: True, ADetailer inpaint padding 2nd: 32, ADetailer version: 23.7.6, Hires upscale: 2, Hires steps: 10, Hires upscaler: 4x-UltraSharp, Lora hashes: "Candyland: 80249b96f2ea", TI hashes: "ng_deepnegative_v1_75t: 54e7e4826d53, EasyNegative: 66a7279a88dd, badhandv4: 5e40d722fc3d", Version: v1.5.1
相关推荐
空白诗1 天前
CANN ops-nn 算子解读:Stable Diffusion 图像生成中的 Conv2D 卷积实现
深度学习·计算机视觉·stable diffusion
学易1 天前
第十五节.别人的工作流,如何使用和调试(上)?(2类必现报错/缺失节点/缺失模型/思路/实操/通用调试步骤)
人工智能·ai作画·stable diffusion·报错·comfyui·缺失节点
无名修道院1 天前
自学AI制作小游戏
人工智能·lora·ai大模型应用开发·小游戏制作
心疼你的一切2 天前
基于CANN仓库算力手把手实现Stable Diffusion图像生成(附完整代码+流程图)
数据仓库·深度学习·stable diffusion·aigc·流程图·cann
Niuguangshuo3 天前
DALL-E 3:如何通过重构“文本描述“革新图像生成
人工智能·深度学习·计算机视觉·stable diffusion·重构·transformer
Niuguangshuo3 天前
深入解析 Stable Diffusion XL(SDXL):改进潜在扩散模型,高分辨率合成突破
stable diffusion
Niuguangshuo3 天前
深入解析Stable Diffusion基石——潜在扩散模型(LDMs)
人工智能·计算机视觉·stable diffusion
迈火3 天前
SD - Latent - Interposer:解锁Stable Diffusion潜在空间的创意工具
人工智能·gpt·计算机视觉·stable diffusion·aigc·语音识别·midjourney
迈火11 天前
Facerestore CF (Code Former):ComfyUI人脸修复的卓越解决方案
人工智能·gpt·计算机视觉·stable diffusion·aigc·语音识别·midjourney
重启编程之路11 天前
Stable Diffusion 参数记录
stable diffusion