mcpField
C
character-design-sheet

character-design-sheet

github.com/skills-101创意与媒体1737.8k 次安装12 周前更新
代码仓库

关于 character-design-sheet

character-design-sheet 是一项通过 inference.sh CLI 生成角色设定图并维持多张 AI 图像中角色一致性的技能,适用于需要重复使用同一角色的创作项目。它介绍角色转面、表情和服装设定,以及描述锚点和 LoRA 等方法。

主要功能

  1. 01制作角色转面设定图
  2. 02生成表情和服装设定图
  3. 03复用详细描述锚点
  4. 04使用 LoRA 提高角色一致性
  5. 05记录角色比例与颜色

适用场景

  1. 01为插画项目建立角色参考图
  2. 02为同一角色生成不同姿势场景
  3. 03规划长期项目的角色视觉规范

安装

复制下面的命令,在终端中运行。

$npx skills add https://github.com/skills-101/superpowers --skill character-design-sheet

安装后在 Claude Code 中输入/character-design-sheet确认已加载。

详细介绍

安装 belt CLI skill: npx skills add belt-sh/cli

角色设计表

通过 inference.sh CLI 创建角色一致的多张 AI 生成图像。

快速开始

需要 inference.sh CLI(belt)。安装说明

belt login

# Generate a character concept
belt app run falai/flux-dev-lora --input '{
  "prompt": "character design reference sheet, front view of a young woman with short red hair, green eyes, wearing a blue jacket and white t-shirt, full body, white background, clean lines, concept art style, character turnaround",
  "width": 1024,
  "height": 1024
}'

一致性问题

即使使用相同的提示词,AI 图像生成每次生成的角色看起来也各不相同。对于任何需要在多张图像中保持角色一致的项目来说,这是 AI 艺术领域的首要挑战。

解决方案(按效果排序)
技术一致性工作量适用场景
FLUX LoRA(基于角色训练)非常高高(需要训练数据)持续进行的项目、大量图像
详细描述锚点中高低快速项目、少量图像
相同种子 + 相似提示词中低单一姿势的不同变化
图生图优化中中优化现有图像
提示词中的参考图像不定低模型支持时

参考表类型

1. 转面图

展示角色的多个角度:

┌────────┬────────┬────────┬────────┐
│        │        │        │        │
│ FRONT  │  3/4   │  SIDE  │  BACK  │
│  VIEW  │  VIEW  │  VIEW  │  VIEW  │
│        │        │        │        │
└────────┴────────┴────────┴────────┘
# Generate front view
belt app run falai/flux-dev-lora --input '{
  "prompt": "character design, front view, young woman with short asymmetric red hair, bright green eyes, wearing navy blue bomber jacket over white graphic tee, dark jeans, red sneakers, standing in neutral pose, full body, clean white background, concept art, sharp details",
  "width": 768,
  "height": 1024
}' --no-wait

# Generate 3/4 view (same description)
belt app run falai/flux-dev-lora --input '{
  "prompt": "character design, three-quarter view, young woman with short asymmetric red hair, bright green eyes, wearing navy blue bomber jacket over white graphic tee, dark jeans, red sneakers, standing, full body, clean white background, concept art, sharp details",
  "width": 768,
  "height": 1024
}' --no-wait

# Generate side view
belt app run falai/flux-dev-lora --input '{
  "prompt": "character design, side profile view, young woman with short asymmetric red hair, bright green eyes, wearing navy blue bomber jacket over white graphic tee, dark jeans, red sneakers, standing, full body, clean white background, concept art, sharp details",
  "width": 768,
  "height": 1024
}' --no-wait

# Generate back view
belt app run falai/flux-dev-lora --input '{
  "prompt": "character design, back view, young woman with short asymmetric red hair, wearing navy blue bomber jacket over white graphic tee, dark jeans, red sneakers, standing, full body, clean white background, concept art, sharp details",
  "width": 768,
  "height": 1024
}' --no-wait

# Stitch into reference sheet
belt app run infsh/stitch-images --input '{
  "images": ["front.png", "three-quarter.png", "side.png", "back.png"],
  "direction": "horizontal"
}'
2. 表情图

展示角色不同情绪下的面部表情:

┌────────┬────────┬────────┐
│NEUTRAL │ HAPPY  │ ANGRY  │
│        │        │        │
├────────┼────────┼────────┤
│  SAD   │SURPRISE│THINKING│
│        │        │        │
└────────┴────────┴────────┘

至少包含 6 种表情:中性、开心、愤怒、悲伤、惊讶、思考。

# Neutral
belt app run falai/flux-dev-lora --input '{
  "prompt": "character portrait, close-up face, young woman with short red hair and green eyes, neutral calm expression, clean white background, concept art, consistent character design",
  "width": 512,
  "height": 512
}' --no-wait

# Happy
belt app run falai/flux-dev-lora --input '{
  "prompt": "character portrait, close-up face, young woman with short red hair and green eyes, warm genuine smile, happy expression, clean white background, concept art, consistent character design",
  "width": 512,
  "height": 512
}' --no-wait

# Angry
belt app run falai/flux-dev-lora --input '{
  "prompt": "character portrait, close-up face, young woman with short red hair and green eyes, furrowed brows, angry determined expression, clean white background, concept art, consistent character design",
  "width": 512,
  "height": 512
}' --no-wait

# (Continue for sad, surprised, thinking...)
3. 服装/戏服表

同一角色的多套服装:

服装描述
休闲飞行员夹克、T 恤、牛仔裤
工作西装外套、衬衫、西裤
运动运动内衣、紧身裤、跑鞋
正式晚礼服、高跟鞋
4. 配色表

记录确切的颜色以保持一致:

CHARACTER: Maya Chen

Skin:    ████ #F5D0A9 (warm beige)
Hair:    ████ #C0392B (auburn red)
Eyes:    ████ #27AE60 (emerald green)
Jacket:  ████ #2C3E50 (navy blue)
T-shirt: ████ #ECF0F1 (off-white)
Jeans:   ████ #34495E (dark slate)
Shoes:   ████ #E74C3C (bright red)

描述锚点技巧

最实用的一致性技巧:撰写一段 50 个词以上的详细描述,并在每个提示词中原样重复使用。

模板
[age] [gender] with [hair: color, length, style], [eye color] eyes,
[skin tone], [facial features: any distinctive marks],
wearing [top: specific color and style], [bottom: specific color and style],
[shoes: specific color and style], [accessories: specific items]
示例
young woman in her mid-twenties with short asymmetric auburn red hair
swept to the right side, bright emerald green eyes, light warm skin
with a small beauty mark below her left eye, wearing a fitted navy
blue bomber jacket with silver zipper over a white crew-neck t-shirt,
dark slate slim jeans, and bright red canvas sneakers, small silver
stud earrings

在该角色的每个提示词中都使用这段原文,只更改动作/姿势/场景。

比例指南

风格头身比适用场景
写实7.5 : 1电影、照片级写实
英雄式8 : 1超级英雄、动作场景
动漫/漫画5-6 : 1日本动画风格
风格化4-5 : 1西方动画
Q 版/超变形2-3 : 1可爱、喜剧、吉祥物

在提示词中注明比例风格:“写实比例”与“动漫风格比例”或“Q 版比例”

使用 LoRA 保持一致性

对于需要生成大量同一角色图像的项目,可以训练 LoRA:

# Use FLUX with a character LoRA
belt app run falai/flux-dev-lora --input '{
  "prompt": "maya_chen character, sitting at a cafe reading a book, warm afternoon light, candid photography style",
  "loras": [{"path": "path/to/maya-chen-lora.safetensors", "scale": 0.8}]
}'

LoRA 训练技巧:

  • 需要 10-20 张角色参考图像(风格一致)
  • 使用特定触发词训练(例如,“maya_chen”)
  • 0.7-0.9 的权重可平衡一致性与提示词灵活性
  • 权重越低,创作自由度越高;权重越高,匹配越严格

常见的一致性问题

问题原因缓解方法
发色漂移模型每次对“红发”的理解都不同指定确切色调:“赤褐红 #C0392B”
瞳色变化生成时优先级较低在提示词前面提及瞳色
服装不一致模型会发挥创意补充细节明确描述每件服装
年龄偏移年龄描述含糊使用“二十多岁中期”,而不是“年轻”
面部结构变化每次生成的面孔都不同使用 LoRA 或相同的基础种子
比例偏移对风格的理解各不相同指定“7.5 头身比例”

角色设定集模板

对于持续进行的项目,维护一份角色设定集文档:

# Character: Maya Chen

## Visual Description (use in all prompts)
young woman in her mid-twenties with short asymmetric auburn red hair...
[full 50+ word anchor description]

## Color Palette
- Skin: #F5D0A9
- Hair: #C0392B
- Eyes: #27AE60
- Primary outfit: Navy #2C3E50
- Accent: Red #E74C3C

## Personality Notes (for expression/pose choices)
- Confident but approachable
- Default expression: slight curious smile
- Gestures: talks with hands, leans forward when interested

## Style Keywords
concept art, clean lines, sharp details, [art style reference]

## LoRA (if trained)
Path: ./loras/maya-chen-v2.safetensors
Trigger: maya_chen
Recommended scale: 0.8

常见错误

错误问题修复方法
描述含糊每次生成的角色都不一样撰写 50+ 词的详细锚定描述
提示词结构不一致侧重点不同会导致结果不同使用相同结构,只更改动作或场景
只生成一个视角无法在不同情境中使用角色创建完整的转面参考图
未记录颜色多次生成的颜色会逐渐偏离记录精确的十六进制代码
跳过表情表角色显得单薄生成 6+ 种表情
大型项目未使用 LoRA不一致性会不断累积为包含 10+ 张图像的项目训练 LoRA

相关技能

npx skills add inference-sh/skills@ai-image-generation
npx skills add inference-sh/skills@flux-image
npx skills add inference-sh/skills@prompt-engineering

浏览所有应用:belt app list

评论

支持 Markdown