LLM Skills
HiggsfieldGenerate images and videos from a single promptTry HiggsfieldSponsored
~/catalog/image generation//SKILL
Image generationGitHub source

Aux Studios Image

/SKILL

Create humanized images with Google AI Studio (Gemini). Realistic influencer-style or educational photos with natural lighting

sickn33sickn33
★48.5k
May 22, 2026
MIT License
// skill content

--- name: ai-studio-image description: Generation of humanized images using Google AI Studio (Gemini). Realistic influencer-style or educational photos with natural lighting and subtle imperfections. risk: safe source: community date_added: '2026-03-06' author: renat tags: - image-generation - ai-studio - google - photography tools: - claude-code - antigravity - cursor - gemini-cli - codex-cli --- # AI Studio Image : Expert in Humanized Images ## Overview Generation of humanized images via Google AI Studio (Gemini). Realistic influencer-style or educational photos with natural lighting and subtle imperfections. ## When to Use This Skill - When the user mentions "generate image" or related topics - When the user mentions "generate photo" or related topics - When the user mentions "create image" or related topics - When the user mentions "realistic photo" or related topics - When the user mentions "humanized image" or related topics - When the user mentions "influencer photo" or related topics ## Do Not Use This Skill When - The task is unrelated to AI Studio images - A simpler, more specific tool can handle the request - The user needs general-purpose assistance without domain expertise ## How It Works The difference between an AI image and a real photo lies in the imperceptible details: the slight grain from a cell phone camera, the imperfect lighting, the slightly off-center framing, the depth of field characteristic of a small lens. skill systematically injects these qualities into every generation. ## AI Studio Image : Expert in Humanized Images An image-generation skill via Google AI Studio that transforms any prompt into photos with a genuinely human look. Each generated image looks as if it were taken by a real person with their cell phone:not by AI. ## 1. Set Up API Key The user needs a Google AI Studio API key: - Go to https://aistudio.google.com/apikey - Create or copy your API key - Set it as an environment variable: ``bash ## 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 `bash pip install -r C:\Users\renat\skills\ai-studio-image\scripts\requirements.txt ` ## 3. Gerar Sua Primeira Imagem `bash 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: | Modo | Quando Usar | Caracteristicas | |------|-------------|-----------------| | **influencer** | Posts de redes sociais, lifestyle, branding pessoal | Estetica atraente mas natural, cores vibrantes sem saturacao excessiva, composicao que prende atencao | | **educacional** | Material de curso, tutorial, apresentacao, infografico | Visual 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 | Formato | Aspect Ratio | Uso Ideal | |---------|-------------|-----------| | square | 1:1 | Feed Instagram, Facebook, perfis | | portrait | 3:4 | Instagram portrait, Pinterest | | landscape | 16:9 | YouTube thumbnails, banners, desktop | | stories | 9:16 | Instagram/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: `bash python C:\Users\renat\skills\ai-studio-image\scripts\prompt_engine.py --prompt "prompt do usuario" --mode influencer `` The humanization engine adds layers of realism: Layer 1 : Device and Technique: - Photographed with a smartphone (iPhone / Samsung Galaxy) - Cell phone lens with pro

// original public source
sickn33/antigravity-awesome-skills
/skills/ai-studio-image/SKILL.md
License: MIT License
Independent project, not affiliated with Anthropic. This skill remains the property of its original author.
// install this skill
Paste this command in your terminal at the root of your project:
mkdir -p .claude/commands && curl -o ".claude/commands/SKILL.md" "https://raw.githubusercontent.com/sickn33/antigravity-awesome-skills/main/skills/ai-studio-image/SKILL.md"
Then in Claude Code, type /SKILL to activate it.
open_in_newOpen original source
// save
Save available after sign in.
loginSign in to save
// information
Creatorsickn33
Stars★ 48.5k
LicenseMIT License
UpdatedMay 22, 2026
Format.md
AccessFree
HiggsfieldSponsored

One video, ten variants, zero reshoots

With Genjutsu, take an existing video and swap the character, the product or the set while keeping the motion and the edit. Perfect to scale an ad that works or adapt it to each market.

Discover Genjutsu
// similar

Skills Image generation

View allarrow_forward