Skip to content
cccskills
FreePublished on GitHub

ai-studio-image

Generate realistic photo-style images with Google AI Studio for social posts and educational materials. Adjust aspect ratios, lighting, settings, and subtle imperfections to create a natural smartphone-photo look suited to each use.

OriginalShow the original description

Geracao de imagens humanizadas via Google AI Studio (Gemini). Fotos realistas estilo influencer ou educacional com iluminacao natural e imperfeicoes sutis.

See how to install

Good for

  • Natural lifestyle images for social posts
  • Photo-style illustrations for courses and tutorials
  • Portrait or landscape images for different platforms
  • Variations with different lighting and settings

Files included (8)

  • SKILL.md11.7 KB
  • references/prompt-engineering.md5.1 KB
  • references/setup-guide.md3.1 KB
  • scripts/config.py25.0 KB
  • scripts/generate.py21.9 KB
  • scripts/prompt_engine.py17.2 KB
  • scripts/requirements.txt78 B
  • scripts/templates.py19.3 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Supporting material availability

This catalog copy contains the inline guidance below, but does not include the following supporting paths. They are external prerequisites, not bundled files:

  • <support-root>/references/api-reference.md

Ask for the original supporting material or an existing installation before using a step that depends on these paths; this catalog does not identify a verified download source for them. Resolve each path relative to that installation, inspect its contents, and verify any applicable license and execution prerequisites. Do not run a command or claim a referenced procedure was followed until its required file exists. Do not fabricate the missing scripts or treat an unrelated file with the same name as equivalent. Independent steps fully documented here can proceed within the user’s authorized scope; report any dependent step as unavailable.

AI Studio Image — Especialista em Imagens Humanizadas

Overview

Geracao de imagens humanizadas via Google AI Studio (Gemini). Fotos realistas estilo influencer ou educacional com iluminacao natural e imperfeicoes sutis.

When to Use This Skill

  • When the user mentions "gera imagem" or related topics
  • When the user mentions "gerar foto" or related topics
  • When the user mentions "criar imagem" or related topics
  • When the user mentions "foto realista" or related topics
  • When the user mentions "imagem humanizada" or related topics
  • When the user mentions "foto influencer" or related topics

Do Not Use This Skill When

  • The task is unrelated to ai studio image
  • A simpler, more specific tool can handle the request
  • The user needs general-purpose assistance without domain expertise

How It Works

A diferenca entre uma imagem de IA e uma foto real esta nos detalhes imperceptiveis: a leve granulacao de um sensor de celular, a iluminacao que nao e perfeita, o enquadramento ligeiramente descentralizado, a profundidade de campo caracteristica de uma lente pequena. Esta skill injeta sistematicamente essas qualidades em cada geracao.

Ai Studio Image — Especialista Em Imagens Humanizadas

Skill de geracao de imagens via Google AI Studio que transforma qualquer prompt em fotos com aparencia genuinamente humana. Cada imagem gerada parece ter sido tirada por uma pessoa real com seu celular — nao por uma IA.

1. Configurar Api Key

O usuario precisa de uma API key do Google AI Studio:


## Windows

set GEMINI_API_KEY=sua-api-key-aqui

## Linux/Mac

export GEMINI_API_KEY=sua-api-key-aqui

Ou crie um arquivo .env em C:\Users\renat\skills\ai-studio-image\:

GEMINI_API_KEY=sua-api-key-aqui

2. Instalar Dependencias

pip install -r C:\Users\renat\skills\ai-studio-image\scripts\requirements.txt

3. Gerar Sua Primeira Imagem

python C:\Users\renat\skills\ai-studio-image\scripts\generate.py --prompt "mulher jovem tomando cafe em cafeteria" --mode influencer --format square

Workflow Principal

Quando o usuario pedir para gerar uma imagem, siga este fluxo:

Passo 1: Identificar O Modo

Pergunte ou deduza pelo contexto:

ModoQuando UsarCaracteristicas
influencerPosts de redes sociais, lifestyle, branding pessoalEstetica atraente mas natural, cores vibrantes sem saturacao excessiva, composicao que prende atencao
educacionalMaterial de curso, tutorial, apresentacao, infograficoVisual limpo, profissional, foco no conteudo, elementos claros e legiveis

Se o usuario nao especificar, use influencer como padrao para conteudo de redes sociais e educacional para qualquer coisa relacionada a ensino/apresentacao.

Passo 2: Identificar O Formato

FormatoAspect RatioUso Ideal
square1:1Feed Instagram, Facebook, perfis
portrait3:4Instagram portrait, Pinterest
landscape16:9YouTube thumbnails, banners, desktop
stories9:16Instagram/Facebook Stories, TikTok, Reels

Se nao especificado, deduza pelo contexto (stories → 9:16, feed → 1:1, etc).

Passo 3: Transformar O Prompt

Esta e a etapa mais importante. Nunca envie o prompt do usuario diretamente para a API. Sempre passe pelo motor de humanizacao:

python C:\Users\renat\skills\ai-studio-image\scripts\prompt_engine.py --prompt "prompt do usuario" --mode influencer

O motor de humanizacao adiciona camadas de realismo:

Camada 1 — Dispositivo e Tecnica:

  • Fotografado com smartphone (iPhone/Samsung Galaxy)
  • Lente de celular com profundidade de campo natural
  • Sem flash — apenas luz ambiente
  • Leve ruido de sensor (ISO elevado em baixa luz)

Camada 2 — Iluminacao Natural:

  • Luz do sol indireta / golden hour / luz de janela
  • Sombras suaves e organicas
  • Sem iluminacao de estudio
  • Reflexos naturais em superficies

Camada 3 — Imperfeicoes Humanas:

  • Enquadramento ligeiramente imperfeito (nao centralizado matematicamente)
  • Foco seletivo natural (algo levemente fora de foco no background)
  • Micro-tremor de maos (nitidez nao e absoluta)
  • Elementos aleatorios do ambiente real

Camada 4 — Autenticidade:

  • Expressoes faciais genuinas (nao poses de estudio)
  • Roupas e cenarios do dia-a-dia
  • Textura de pele real (poros, marcas sutis — sem pele de porcelana)
  • Proporcoes corporais realistas

Camada 5 — Contexto Ambiental:

  • Cenarios reais (nao fundos genericos de stock)
  • Objetos do cotidiano no ambiente
  • Iluminacao consistente com o cenario
  • Hora do dia coerente com a atividade

Passo 4: Gerar A Imagem

python C:\Users\renat\skills\ai-studio-image\scripts\generate.py \
  --prompt "prompt humanizado gerado no passo anterior" \
  --mode influencer \
  --format square \
  --model gemini-2-flash-exp \
  --output C:\Users\renat\skills\ai-studio-image\data\outputs\

Modelos disponiveis (em ordem de recomendacao):

ModeloVelocidadeQualidadeCustoUso Ideal
gemini-2-flash-expRapidoAltaGRATISPadrao — usar sempre
imagen-4MedioAlta$0.03/imgAlta qualidade (requer --force-paid)
imagen-4-ultraLentoMaxima$0.06/imgImpressao, 2K (requer --force-paid)
imagen-4-fastRapidoBoa$0.02/imgVolume alto (requer --force-paid)
gemini-flash-imageRapidoAlta$0.039/imgEdicao de imagem (requer --force-paid)
gemini-pro-imageMedioMaxima+4K$0.134/imgReferencia, 4K (requer --force-paid)

Passo 5: Apresentar E Iterar

Mostre o resultado ao usuario. Se precisar ajustar:

  • Reluz: Ajustar iluminacao
  • Reenquadrar: Mudar composicao
  • Mais/menos natural: Ajustar nivel de imperfeicoes
  • Mudar cenario: Alterar ambiente

Templates Pre-Configurados

Para cenarios comuns, use templates prontos. Execute:

python C:\Users\renat\skills\ai-studio-image\scripts\templates.py --list

Templates disponiveis:

Modo Influencer

TemplateDescricao
cafe-lifestylePessoa em cafeteria/restaurante com bebida/comida
outdoor-adventureAtividade ao ar livre, natureza, viagem
workspace-minimalMesa de trabalho elegante, home office
fitness-naturalExercicio/wellness com visual natural
food-flat-layComida vista de cima, flat lay casual
urban-streetCenario urbano, street style
golden-hour-portraitRetrato com luz dourada do por-do-sol
mirror-selfieSelfie no espelho, casual e espontaneo
product-in-useProduto sendo usado naturalmente por pessoa
behind-scenesBastidores, making of, dia-a-dia real

Modo Educacional

TemplateDescricao
tutorial-stepPessoa demonstrando passo de tutorial
whiteboard-explainPessoa explicando em quadro/lousa
hands-on-demoMaos fazendo demonstracao pratica
before-afterComparacao antes/depois
tool-showcaseFerramenta/software sendo utilizado
classroom-naturalAmbiente de aula/workshop
infographic-humanPessoa apontando para dados/graficos
interview-setupSetup de entrevista/podcast natural
screen-recording-humanPessoa com notebook mostrando tela
team-collaborationEquipe trabalhando junta naturalmente

Usar template:

python C:\Users\renat\skills\ai-studio-image\scripts\generate.py \
  --template cafe-lifestyle \
  --custom "mulher ruiva, 30 anos, lendo livro" \
  --format square

Nivel De Humanizacao

Controle quanto "imperfeicao" injetar:

NivelEfeito
ultraMaximo realismo — parece 100% foto de celular
natural (padrao)Equilibrio perfeito entre qualidade e realismo
polishedMais limpo, ainda natural mas com mais cuidado estetico
editorialEstilo revista, natural mas com producao
python C:\Users\renat\skills\ai-studio-image\scripts\generate.py \
  --prompt "..." --humanization natural

Hora Do Dia

A iluminacao muda drasticamente:

OpcaoDescricao
morningLuz matinal suave, tons frios-quentes
golden-hourPor-do-sol/nascer, tons dourados
middayLuz dura do meio-dia, sombras marcadas
overcastDia nublado, luz difusa uniforme
nightIluminacao artificial, tons quentes
indoorLuz de interiores, mista

Geracao Em Lote

Para gerar multiplas variacoes:

python C:\Users\renat\skills\ai-studio-image\scripts\generate.py \
  --prompt "..." --variations 4 --format square

Instagram Skill

Gere imagens e publique diretamente:

  1. Use ai-studio-image para gerar a foto
  2. Use instagram skill para publicar com caption otimizada

Canva Integration

As imagens geradas podem ser enviadas para o Canva para adicao de texto/branding.

Troubleshooting

ProblemaSolucao
GEMINI_API_KEY not foundConfigure a variavel de ambiente ou crie .env
quota exceededAguarde reset do rate limit ou upgrade do plano
image blockedAjuste o prompt — pode conter conteudo restrito
low quality outputAumente humanization para ultra, tente outro modelo

Referencias

Para guias detalhados, consulte:

  • references/setup-guide.md — Instalacao e configuracao completa
  • references/prompt-engineering.md — Tecnicas avancadas de prompt para imagens humanizadas
  • references/api-reference.md — Documentacao da API do Google AI Studio

Best Practices

  • Provide clear, specific context about your project and requirements
  • Review all suggestions before applying them to production code
  • Combine with other complementary skills for comprehensive analysis

Common Pitfalls

  • Using this skill for tasks outside its domain expertise
  • Applying recommendations without understanding your specific context
  • Not providing enough project context for accurate analysis

Related Skills

  • comfyui-gateway - Complementary skill for enhanced analysis
  • image-studio - Complementary skill for enhanced analysis
  • stability-ai - Complementary skill for enhanced analysis

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Assess a new or existing AI project by examining its code, goals, and constraints. Recommend skills confirmed to exist in the available registry, then outline tasks and implementation phases with dependencies, completion criteria, and checks.

  • Planning the first steps of a new AI project
  • Assessing technical issues in an existing project
  • Selecting relevant skills from an available registry
sickn33/agentic-awesome-skills48.3KUpdated Oct 21, 2026

007

FreeSummary

Review code and infrastructure for security risks, map potential threats, and plan stronger defenses. The skill covers OWASP checks, attack and defense exercises, and incident response, with validation required for each environment.

  • Reviewing code and infrastructure security
  • Mapping threats with STRIDE or PASTA
  • Planning stronger security settings
sickn33/agentic-awesome-skills48.3KUpdated Oct 21, 2026

Turn a repeatable task into an Andru.ia skill with clear inputs, outputs, examples, and limits. Draft SKILL.md, check the folder structure and required validations, and prepare a pull request describing the changes for review.

  • Creating a skill for a repeatable task
  • Improving an existing skill’s examples and limits
  • Validating skill files and preparing a pull request
sickn33/agentic-awesome-skills48.3KUpdated Oct 21, 2026

Prepare an industry briefing once a project's sector is defined. It covers sector context, potentially applicable regulations, familiar interface patterns, technology choices, and risks, while separating verified evidence from hypotheses and questions requiring further review.

  • Researching industry requirements before product design
  • Checking regulations for a project's jurisdiction
  • Choosing interface patterns familiar to target users
sickn33/agentic-awesome-skills48.3KUpdated Oct 21, 2026

Create presentation drafts from text, outlines, or documents through the 2slides API. Match a reference image's style, choose themes, add AI voice narration, and export slide images or audio for review and use.

  • Create a presentation from text or an outline
  • Summarize a document into slides
  • Match slide styling to a reference image
sickn33/agentic-awesome-skills48.3KUpdated Oct 21, 2026

Plan a 360-degree or peer feedback process and create empty response templates from confirmed requirements. Produces consistent CSV, SQL, JSON Schema, or Notion property mappings while keeping visibility choices and scoring configuration separate.

  • Plan an anonymous peer feedback process
  • Create a CSV template for feedback responses
  • Align feedback fields across SQL and JSON Schema
sickn33/agentic-awesome-skills48.3KUpdated Oct 21, 2026

See all skills by sickn33

Report a problem with this skill