character-design-sheet

Согласованность персонажей на изображениях, созданных ИИ, с использованием референсных листов и техник LoRA. Охватывает разворотные виды, листы выражений, цветовые палитры и приёмы сохранения стиля. Используется для: дизайна персонажей, игрового арта, иллюстрации, анимации, комиксов, визуальных новелл. Триггеры: дизайн персонажа, лист персонажа, согласованность персонажа, референс персонажа, разворотный лист, лист выражений, арт персонажа, согласованный персонаж, концепт персонажа, референсный лист, создание персонажа, дизайн OC,...

npx skills add https://github.com/halt-catch-fire/skills --skill character-design-sheet

Install the belt CLI skill: npx skills add belt-sh/cli

Character Design Sheet

Create consistent characters across multiple AI-generated images via inference.sh CLI.

Quick Start

Requires inference.sh CLI (belt). Install instructions

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
}'

The Consistency Problem

AI image generation produces different-looking characters every time, even with the same prompt. This is the #1 challenge in AI art for any project requiring the same character across multiple images.

Solutions (Ranked by Effectiveness)

TechniqueConsistencyEffortBest For
FLUX LoRA (trained on character)Very highHigh (requires training data)Ongoing projects, many images
Detailed description anchorMedium-highLowQuick projects, few images
Same seed + similar promptMediumLowVariations of single pose
Image-to-image refinementMediumMediumRefining existing images
Reference image in promptVariesLowWhen model supports it

Reference Sheet Types

1. Turnaround Sheet

Shows the character from multiple angles:

┌────────┬────────┬────────┬────────┐
│        │        │        │        │
│ 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 (two images per call; repeat to add views)
belt app run infsh/stitch-images --input '{
  "image1": "front.png",
  "image2": "three-quarter.png",
  "orientation": "horizontal"
}'

2. Expression Sheet

Shows the character's face with different emotions:

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

Minimum 6 expressions: neutral, happy, angry, sad, surprised, thinking.

# 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. Outfit/Costume Sheet

Multiple outfits for the same character:

OutfitDescription
CasualBomber jacket, t-shirt, jeans
WorkBlazer, button-down, slacks
AthleticSports bra, leggings, running shoes
FormalEvening dress, heels

4. Color Palette Sheet

Document exact colors for consistency:

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)

The Description Anchor Technique

The most practical consistency technique: write a 50+ word detailed description and reuse it exactly in every prompt.

Template

[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]

Example

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

Use this exact block in EVERY prompt for this character, only changing the action/pose/scene.

Proportion Guide

StyleHead-to-Body RatioBest For
Realistic7.5 : 1Film, photorealistic
Heroic8 : 1Superheroes, action
Anime/Manga5-6 : 1Japanese animation style
Stylized4-5 : 1Western animation
Chibi/Super-deformed2-3 : 1Cute, comedic, mascots

Include proportion style in your prompts: "realistic proportions" vs "anime style proportions" vs "chibi proportions"

Using LoRA for Consistency

For projects requiring many images of the same character, train a 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 Training Tips:

  • Need 10-20 reference images of the character (consistent style)
  • Train on specific trigger word (e.g., "maya_chen")
  • Scale 0.7-0.9 balances consistency with prompt flexibility
  • Lower scale = more creative freedom, higher = more strict matching

Common Consistency Failures

IssueWhy It HappensMitigation
Hair color driftModel interprets "red hair" differently each timeUse specific shade: "auburn red #C0392B"
Eye color changeLow priority in generationMention eye color early in prompt
Outfit inconsistencyModel fills in details creativelyDescribe every clothing item explicitly
Age shiftVague age descriptionUse "mid-twenties" not "young"
Face structure changeDifferent generations = different facesUse LoRA or same seed base
Proportion shiftStyle interpretation variesSpecify "7.5 head proportions"

Character Bible Template

For ongoing projects, maintain a character bible document:

# 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

Common Mistakes

MistakeProblemFix
Vague descriptionsDifferent character every time50+ word detailed anchor
Inconsistent prompt structureVarying emphasis = varying resultsSame structure, only change action/scene
Generating one view onlyCan't use character in different contextsCreate full turnaround reference
No color documentationColors drift across generationsRecord exact hex codes
Skipping expression sheetCharacter feels one-dimensionalGenerate 6+ expressions
Not using LoRA for big projectsInconsistency compoundsTrain LoRA for 10+ image projects

Related Skills

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

Browse all apps: belt app list

Больше skills от halt-catch-fire

agent-browser
halt-catch-fire
Автоматизация браузера для AI-агентов через inference.sh. Навигация по веб-страницам, взаимодействие с элементами с помощью @e refs, создание скриншотов, запись видео. Возможности: веб-скрапинг, заполнение форм, клики, ввод текста, перетаскивание, загрузка файлов, выполнение JavaScript. Используется для: веб-автоматизации, извлечения данных, тестирования, просмотра страниц агентом, исследований. Триггеры: браузер, веб-автоматизация, скрапинг, навигация, клик, заполнение формы, скриншот, просмотр веб-страниц, playwright, headless-браузер, веб-агент, серфинг в интернете, запись видео
browser-automationweb-scrapingtesting
agent-tools
halt-catch-fire
We need to translate the given text from English to Russian, preserving product names, protocol names, URLs, numbers, and technical terms. The text is a description of an agent skill. We must not include the name "agent-tools" unless it appears in the source text. The source text does not contain "agent-tools" explicitly, so we ignore it. We translate only the content inside <text>. We must not add any extra commentary, labels, or formatting. The text: "Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation,
developmentapicreative
ai-avatar-video
halt-catch-fire
Создавайте AI-аватары и видео с говорящими головами через CLI inference.sh. Рекомендуется: P-Video-Avatar (самый быстрый, дешёвый, встроенный TTS). Также: OmniHuman, Fabric, PixVerse. Аудио: Inworld TTS-2 (100+ языков, управление эмоциями для персонажей), ElevenLabs, Kokoro. Возможности: аватары, управляемые аудио, текст-в-аватар, видео с синхронизацией губ, генерация говорящих голов, виртуальные ведущие, UGC-контент. Используйте для: AI-ведущие, обучающие видео, виртуальные инфлюенсеры, дубляж, маркетинговые видео, UGC-реклама, игровые аватары,...
videocreativemedia
ai-image-generation
halt-catch-fire
We need to translate the given text from English to Russian. The text describes an agent skill for AI image generation. We must preserve the name "ai-image-generation" but it's not in the text, so we don't include it. We preserve product names, protocol names, URLs, numbers, technical terms. No extra commentary. Translate the entire <text> content. The text: "Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to..." Translate
creativemediaimage
ai-video-generation
halt-catch-fire
Генерируйте AI-видео с помощью Google Veo, Seedance 2.0, HappyHorse, Wan, Grok и 40+ моделей через CLI inference.sh. Модели: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Возможности: текст-в-видео, изображение-в-видео, референс-в-видео, редактирование видео, липсинк, анимация аватаров, апскейлинг видео, звук фоли. Используйте для: видео для соцсетей, маркетинговый контент, объясняющие видео, демонстрации продуктов, AI-аватары. Триггеры: генерация видео, ai video,...
creativevideomedia
app-store-screenshots
halt-catch-fire
Создание скриншотов для App Store и Google Play с точными спецификациями платформ. Охватывает размеры для iOS/Android, порядок в галерее, макеты устройств и превью-видео. Используется для: оптимизации в магазинах приложений, ASO, скриншотов приложений, превью приложений, оформления в Play Store. Триггеры: скриншоты для магазина приложений, aso, оптимизация в магазине приложений, скриншоты для Play Store, превью приложения, оформление приложения, скриншоты для iOS, скриншоты для Android, изображения приложения, макет приложения, макет устройства, галерея приложения, оформление в магазине
designmarketingcreative
competitor-teardown
halt-catch-fire
We need to translate the given text from English to Russian, preserving the name "competitor-teardown" if it appears. The instruction says: "Do not include the name unless it appears in the source text." The name "competitor-teardown" appears in the source text as part of the triggers list: "competitor teardown" (without hyphen). Actually the source text has "competitor teardown" (two words) in the triggers. The name to preserve is "competitor-teardown" (with hyphen). But in the source text, it's written as "competitor teardown" (no hyphen). The instruction says "Name to preserve: competitor-teardown". So we should preserve that exact string if it appears. It does not appear exactly as "competitor-teardown" in the source text. However, the triggers list includes "competitor teardown". We need to decide: should we translate "competitor teardown" as a phrase? The instruction says "Preserve product names, protocol names, URLs
researchdata-analysismarketing
image-to-video
halt-catch-fire
We need to translate the given text from English to Russian. The text is a description of an agent skill for image-to-video conversion. We must preserve product names, protocol names, URLs, numbers, technical terms. The name "image-to-video" is not in the text, but "Wan 2.5 i2v", "Seedance", "Fabric", "Grok Video" are product names. Also "i2v" is a technical term. We should not add any extra commentary or labels. Just translate the text inside <text> tags. The text: "Still-to-video conversion guide: model selection, motion prompting, and camera movement. Covers Wan 2.5 i2v, Seedance, Fabric, Grok Video with when to use each. Use for: animating images, creating video from stills, adding motion, product animations. Triggers: image to video, i2v, animate image, still to video, add motion to image, image animation, photo to video, animate still, wan i2v