character-design-sheet

por beltsh

Consistencia de personajes en imágenes generadas por IA mediante hojas de referencia y técnicas LoRA. Abarca vistas de giro, hojas de expresiones, paletas de colores y trucos para mantener la coherencia del estilo. Úsalo para: diseño de personajes, arte para videojuegos, ilustración, animación, cómics y novelas visuales. Activadores: diseño de personajes, hoja de personaje, consistencia de personajes, referencia de personaje, hoja de vistas de giro, hoja de expresiones, arte de personajes, personaje coherente, concepto de personaje, hoja de referencia, creación de personajes, diseño de OC,...

npx skills add https://github.com/beltsh/superpowers --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

Más skills de beltsh

agent-browser
beltsh
Automatización del navegador para agentes de IA mediante inference.sh. Navega por páginas web, interactúa con elementos usando referencias @e, toma capturas de pantalla y graba vídeo. Capacidades: extracción de datos web, rellenado de formularios, clics, escritura, arrastrar y soltar, carga de archivos y ejecución de JavaScript. Úsalo para: automatización web, extracción de datos, pruebas, navegación de agentes e investigación. Activadores: navegador, automatización web, extraer datos, navegar, hacer clic, rellenar formulario, captura de pantalla, navegar por la web, playwright, navegador sin interfaz gráfica, agente web, navegar por internet, grabar vídeo.
browser-automationweb-scrapingtesting
agent-tools
beltsh
Ejecuta aplicaciones de IA mediante la CLI de inference.sh: generación de imágenes, creación de videos, LLM, búsqueda, 3D y automatización de Twitter. Modelos: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa y muchos más. Úsalo para ejecutar aplicaciones de IA, generar imágenes o videos, llamar a LLM, buscar en la web o automatizar Twitter. Activadores: inference.sh, infsh, modelo de IA, ejecutar IA, IA sin servidor, API de IA, flux, veo, API de Claude, generación de imágenes, generación de videos, tavily, búsqueda de Exa, API de Twitter, grok
mediaapibrowser-automation
ai-avatar-video
beltsh
Crea avatares de IA y videos de cabezas parlantes mediante la CLI de inference.sh. Recomendado: P-Video-Avatar (el más rápido y económico, con TTS integrado). También: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (más de 100 idiomas, control de emociones para personajes), ElevenLabs, Kokoro. Capacidades: avatares controlados por audio, conversión de texto a avatar, videos con sincronización labial, generación de cabezas parlantes, presentadores virtuales, contenido UGC. Úsalo para: presentadores de IA, videos explicativos, influencers virtuales, doblaje, videos de marketing, anuncios UGC, avatares de videojuegos,...
videoaudiomarketing
ai-image-generation
beltsh
Genera imágenes con IA con GPT-Image-2.6, FLUX, Gemini, Grok, Seedream, Reve y más de 50 modelos mediante la CLI de inference.sh. Modelos: GPT-Image-2.6 Flare, GPT-Image-2.6 Sunburst, FLUX Dev LoRA, FLUX.2 Klein LoRA, Nano Banana 2.1, Gemini 3 Pro Image, Grok Imagine 2.0, Seedream 5.5, Reve, ImagineArt. Funciones: texto a imagen, imagen a imagen, inpainting, LoRA, edición de imágenes, ampliación de resolución y renderizado de texto. Usos: arte con IA, maquetas de productos, arte conceptual, gráficos para redes sociales, recursos visuales de marketing, ilustraciones....
imagecreativemedia
ai-video-generation
beltsh
Genera vídeos con IA con Google Veo, Seedance 2.5, Kling, HappyHorse, Wan, Grok y más de 40 modelos mediante la CLI de inference.sh. Modelos: Veo 3.1, Seedance 2.5, Kling v4, Runway Gen-4.5, FLUX 3 Video, HappyHorse 1.0, Wan 2.7, Grok Imagine Video 1.5, P-Video 2, OmniHuman, Fabric. Funciones: texto a vídeo, imagen a vídeo, referencia a vídeo, edición de vídeo, sincronización labial, animación de avatares, mejora de resolución de vídeo y efectos de sonido. Úsalo para: vídeos para redes sociales, contenido de marketing, vídeos explicativos, demostraciones de productos, avatares con IA....
videomediacreative
app-store-screenshots
beltsh
Creación de capturas de pantalla para App Store y Google Play con especificaciones exactas de cada plataforma. Incluye dimensiones de iOS/Android, orden de la galería, maquetas de dispositivos y videos de vista previa. Úsalo para: optimización de tiendas de aplicaciones, ASO, capturas de pantalla de aplicaciones, vista previa de aplicaciones, ficha de Play Store. Activadores: capturas de pantalla de App Store, ASO, optimización de App Store, capturas de pantalla de Play Store, vista previa de aplicaciones, ficha de aplicación, capturas de pantalla de iOS, capturas de pantalla de Android, imágenes de aplicaciones para App Store, maqueta de aplicación, maqueta de dispositivo, galería de aplicaciones, ficha de tienda
designmarketingimage
competitor-teardown
beltsh
Análisis competitivo estructurado con matrices de características, análisis SWOT, mapas de posicionamiento y revisión de UX. Abarca marcos de investigación, comparación de precios, análisis de reseñas y entregables visuales. Úsalo para: investigación de mercado, inteligencia competitiva, presentaciones para inversores, estrategia de producto y apoyo a ventas. Activadores: análisis de competidores, análisis competitivo, análisis exhaustivo de competidores, investigación de mercado, inteligencia competitiva, análisis SWOT, comparación de competidores, panorama del mercado, revisión de competidores, análisis competitivo...
researchdata-analysisproductivity
image-to-video
beltsh
Guía de conversión de imagen fija a video: selección de modelos, indicaciones de movimiento y movimiento de cámara. Incluye Wan 2.7 i2v, Seedance 2.5, Kling v4 y Grok Imagine Video 1.5, y cuándo usar cada uno. Úsala para: animar imágenes, crear videos a partir de imágenes fijas, añadir movimiento y crear animaciones de productos. Activadores: imagen a video, i2v, animar imagen, imagen fija a video, añadir movimiento a una imagen, animación de imágenes, foto a video, animar imagen fija, wan i2v, image2video, dar vida a una imagen, animar foto, movimiento a partir de una imagen
videoimagecreative