image-studio
Automated image generation tool that routes requests between specialized human-centric and artistic AI models.
Install
mkdir -p .claude/skills/image-studio && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18949" && unzip -o skill.zip -d .claude/skills/image-studio && rm skill.zipInstalls to .claude/skills/image-studio
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Studio de geracao de imagens inteligente — roteamento automatico entre ai-studio-image (fotos humanizadas/influencer) e stability-ai (arte/ ilustracao/edicao). Detecta o tipo de imagem solicitada e escolhe o modelo ideal automaticamente.Key capabilities
- →Generate hyper-realistic photos of people using ai-studio-image.
- →Create art, illustrations, and image manipulations with Stability-AI.
- →Edit existing images through inpainting, search-replace, and erasing.
- →Upscale image resolution and remove backgrounds.
- →Automatically route image generation requests to the appropriate AI model.
- →Generate images with specific styles like photorealistic, anime, or oil-painting.
How it works
The skill analyzes the user's image request to determine if it is a realistic photo of a person, an illustration, art, or an image editing task. Based on this analysis, it automatically selects either ai-studio-image for humanized photos or Stability-AI for art, illustration, and editing, then constructs an optimized p
Inputs & outputs
When to use image-studio
- →Generating human-like photos
- →Creating illustrations
- →Editing existing images
About this skill
IMAGE-STUDIO: Gerador de Imagens Inteligente
Overview
Studio de geracao de imagens inteligente — roteamento automatico entre ai-studio-image (fotos humanizadas/influencer) e stability-ai (arte/ ilustracao/edicao). Detecta o tipo de imagem solicitada e escolhe o modelo ideal automaticamente. Geracao, edicao, upscale, remocao de fundo, inpainting e geracao de fotos realistas de pessoas em um unico workflow.
When to Use This Skill
- When you need specialized assistance with this domain
Do Not Use This Skill When
- The task is unrelated to image studio
- A simpler, more specific tool can handle the request
- The user needs general-purpose assistance without domain expertise
How It Works
Voce e o Diretor Criativo Visual — escolhe o pincel certo para cada obra. Fotos humanizadas com Gemini, arte e edicao com Stability. Um comando, o modelo ideal, o resultado perfeito.
1. Matriz De Decisao
A primeira pergunta e sempre: qual modelo serve melhor?
PEDIDO DO USUARIO
↓
E uma FOTO REALISTA de pessoa/influencer?
↓ SIM: ai-studio-image
↓ NAO → E uma ILUSTRACAO, ARTE ou DESENHO?
↓ SIM: stability-ai (generate/ultra/core)
↓ NAO → E uma EDICAO de imagem existente?
↓ SIM: stability-ai (img2img/inpaint/search-replace/erase)
↓ NAO → E um UPSCALE ou REMOCAO DE FUNDO?
↓ SIM: stability-ai (upscale/remove-bg)
↓ NAO: perguntar mais detalhes
Ai-Studio-Image (Gemini 2.0 Flash — Free)
Especialidade: Fotos hiper-realistas de pessoas com toque humano
| Pedido | Exemplo |
|---|---|
| Foto de influencer | "foto estilo instagram de mulher em cafe" |
| Foto de perfil profissional | "headshot profissional homem terno" |
| Foto lifestyle | "pessoa na praia com celular, luz dourada" |
| Conteudo educacional humanizado | "professor ensinando com quadro" |
| Foto produto com pessoa | "mulher segurando smartphone" |
Vantagens:
- Gratuito (gemini-2.0-flash-exp)
- 5 camadas de humanizacao narrativa (device, lighting, imperfection, authenticity, environment)
- 20 templates pre-configurados (10 influencer + 10 educacional)
- Imperfeicoes sutis que tornam a foto credivel
Limitacoes:
- 1 imagem por vez, ~9s
- ~1K resolucao
- Nao suporta aspect_ratio customizado
- 50 imgs/dia free tier
Stability-Ai (Sd3.5 Large — Community)
Especialidade: Arte, ilustracao, edicao e manipulacao de imagens
| Pedido | Modo | Exemplo |
|---|---|---|
| Arte/ilustracao | generate | "dragon flying over mountains, fantasy" |
| Maxima qualidade | ultra | "portrait photography, studio lighting" |
| Rapido/iteracao | core | "anime cat kawaii" |
| Transformar imagem | img2img | "transforme em pintura a oleo" |
| Ampliar resolucao | upscale | "aumentar imagem para 4K" |
| Upscale criativo | upscale-creative | "ampliar com detalhes adicionais" |
| Remover fundo | remove-bg | "fundo transparente (PNG)" |
| Editar area | inpaint | "substituir roupa por terno" |
| Substituir objeto | search-replace | "trocar carro vermelho por azul" |
| Apagar objeto | erase | "remover pessoa do fundo" |
15 Estilos: photorealistic, anime, digital-art, oil-painting, watercolor, pixel-art, 3d-render, concept-art, comic, minimalist, fantasy, sci-fi, sketch, pop-art, noir
Limitacoes:
- Créditos (Community License)
- Nao especializado em fotos realistas de pessoas
3.1 Geracao Simples
Usuario: "crie uma imagem de X"
1. Analisar: tipo de imagem + objetivo
2. Selecionar: modelo ideal (decision matrix acima)
3. Construir prompt: otimizado para o modelo escolhido
4. Gerar: executar com parametros corretos
5. Apresentar: mostrar resultado + metadados
6. Oferecer: variacoes, ajustes, versao alternativa
3.2 Geracao Com Ai-Studio-Image
Usar sistema de templates e prompt engine:
## Template Especifico
python generate.py --template "instagram-lifestyle" --customization "cafe, manha, sorriso"
## Prompt Customizado
python generate.py --prompt "mulher jovem em home office, luz natural, laptop"
## Modo Humanizado Maximo (5 Camadas)
python generate.py --prompt "..." --humanization maximum
3.3 Geracao Com Stability-Ai
Mapear para modo correto:
## Arte/Ilustracao
python generate.py generate --prompt "..." --style fantasy --aspect-ratio 16:9
## Foto Alta Qualidade
python generate.py ultra --prompt "..." --style photorealistic
## Editar Imagem Existente
python generate.py inpaint --image imagem.jpg --mask mascara.png --prompt "adicionar chapeu"
## Remover Fundo
python generate.py remove-bg --image produto.jpg
## Upscale
python generate.py upscale --image small.jpg --scale 4
Para Ai-Studio-Image (Fotos Realistas)
Estrutura ideal:
[Sujeito principal] + [Acao/pose] + [Ambiente] + [Iluminacao] + [Detalhe humano]
Exemplo:
"jovem mulher brasileira, 25 anos, sorrindo naturalmente,
sentada em cafe moderno, luz natural pela janela,
segurando xicara de cafe, roupa casual chique,
cabelo levemente bagunçado, foco suave no fundo"
Evitar:
- Termos de arte (oil painting, digital art)
- Nomes de artistas
- Estilos nao-fotograficos
Para Stability-Ai (Arte/Ilustracao)
Estrutura ideal:
[Sujeito] + [Acao] + [Estilo artistico] + [Iluminacao cinematica] +
[Qualidade] + [Artista de referencia] + [Cores]
Exemplo:
"majestic dragon soaring over misty mountains,
digital art style, cinematic lighting,
highly detailed, Greg Rutkowski, vibrant colors,
4k, masterpiece"
Negativos uteis:
"blurry, low quality, watermark, text, ugly, deformed,
extra fingers, bad anatomy, worst quality"
2. Formato De Resposta
IMAGE-STUDIO — [tipo de geracao]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🎨 Modelo: [ai-studio-image / stability-ai]
📋 Modo: [template / generate / inpaint / etc]
⏱️ Tempo: ~Xs
✅ Imagem gerada!
📁 Salva em: [caminho]
📐 Dimensao: XxY px
💾 Tamanho: X KB
🔧 Prompt usado:
"[prompt otimizado]"
💡 Variacoes disponiveis:
1. stability-ai versao arte
2. ai-studio-image versao humanizada
3. Ajuste de estilo/iluminacao
Post Instagram
Usuario: "imagem para post de lancamento do produto Auri"
→ image-studio decide: foto realista de produto com pessoa
→ ai-studio-image: "pessoa segurando dispositivo Alexa,
ambiente moderno, luz natural, expressao animada"
→ Resultado: foto humanizada pronta para Instagram
Thumbnail Youtube
Usuario: "thumbnail para video de IA com impacto"
→ image-studio decide: arte digital de alto impacto
→ stability-ai ultra: "AI robot face, glowing eyes,
dark background, dramatic lighting, digital art, 4k"
→ Resultado: thumbnail atraente e profissional
Foto De Perfil
Usuario: "foto profissional para LinkedIn"
→ image-studio decide: foto realista de pessoa
→ ai-studio-image template "linkedin-headshot":
"homem profissional, terno azul, fundo neutro,
luz de estudio, expressao confiante"
→ Resultado: headshot convincente
3. Fallback E Redundancia
Se ai-studio-image falha (limite diario, erro de API):
→ Tentar stability-ai modo ultra com prompt adaptado
→ Informar usuario sobre mudanca de modelo
Se stability-ai falha (créditos insuficientes):
→ Tentar ai-studio-image com prompt adaptado
→ Se mesmo tipo nao suportado: orientar sobre recarga
Se ambos falham:
→ Gerar prompt detalhado que usuario pode usar manualmente
→ Sugerir DALL-E, Midjourney, Leonardo AI como alternativas
4. Localizacao Das Skills
ai-studio-image:
Scripts: C:\Users\renat\skills\ai-studio-image\
Gerar: python generate.py [--template T] [--prompt P]
stability-ai:
Scripts: C:\Users\renat\skills\stability-ai\
Gerar: python generate.py [MODE] --prompt P --style S
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
ai-studio-image- Complementary skill for enhanced analysiscomfyui-gateway- Complementary skill for enhanced analysisstability-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.
Limitations
- →Ai-studio-image generates one image at a time, with approximately 9-second processing.
- →Ai-studio-image has a resolution limit of approximately 1K and does not support custom aspect ratios.
- →Stability-AI is not specialized in realistic photos of people.
How it compares
This skill automates the selection of the most suitable AI image generation model based on the user's request, unlike manually choosing and configuring a specific model.
Compared to similar skills
image-studio side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| image-studio (this skill) | 0 | 2mo | Review | Beginner |
| jimeng-mcp-skill | 19 | 4mo | Caution | Intermediate |
| gemini-logo-remover | 9 | 7mo | Review | Beginner |
| ai-image | 9 | 8mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by asnk633
View all by asnk633 →You might also like
jimeng-mcp-skill
wwwzhouhui
使用jimeng-mcp-server进行AI图像和视频生成。当用户请求从文本生成图像、合成多张图片、从文本描述创建视频或为静态图像添加动画时使用此技能。支持四大核心能力:文生图、图像合成、文生视频、图生视频。需要jimeng-mcp-server在本地运行或通过SSE/HTTP访问。
gemini-logo-remover
bear2u
Remove Gemini logos, watermarks, or AI-generated image markers using OpenCV inpainting. Use this skill when the user asks to remove Gemini logo, AI watermark, or any logo/watermark from images.
ai-image
tyrchen
Generate AI images using OpenAI's gpt-image-1 model with customizable aspect ratios and artistic themes. Use when the user wants to create images, generate artwork, or mentions image generation with specific styles like Ghibli, futuristic, Pixar, oil painting, or Chinese painting.
baoyu-article-illustrator
JimLiu
Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style two-dimension approach. Use when user asks to "illustrate article", "add images", "generate images for article", or "为文章配图".
nano-banana-pro-prompts-recommend-skill
YouMind-OpenLab
Recommend suitable prompts from 6000+ Nano Banana Pro image generation prompts based on user needs. Use this skill when users want to: - Generate images with AI (Nano Banana Pro model) - Find inspiration for image generation prompts - Get prompt recommendations for specific use cases (portraits, landscapes, product photos, etc.) - Create illustrations for articles, videos, podcasts, or other content - Translate and understand prompt techniques
image-generation
onyx-dot-app
Generate images using nano banana.