{"enrichment":{"faq":[{"a":"Gemini Imagegen uses Google's Gemini image generation model to create visuals from text descriptions. You provide a prompt describing what you want, and the skill generates images at resolutions from 1K to 4K with your chosen aspect ratio. It works seamlessly in Claude Code for programmatic image creation in your workflows.","q":"How do I generate images with Gemini?"},{"a":"Gemini Imagegen excels at logos, product mockups, stylized art, and photorealistic scenes. The skill supports iterative refinement through multi-turn chat, letting you adjust and improve results. You can also compose visuals from multiple reference images to blend concepts and styles into new creations.","q":"What can Gemini Imagegen create?"},{"a":"Yes. Gemini Imagegen integrates directly into Claude Code, giving you access to image generation capabilities within your coding workflows. This lets you create visual content programmatically as part of larger automation scripts or applications without leaving your development environment.","q":"Can I integrate Gemini image generation into Claude Code?"},{"a":"Gemini Imagegen supports multiple resolutions ranging from 1K to 4K, with flexible aspect ratio options. This range covers everything from social media graphics to high-resolution prints, letting you tailor output dimensions to your specific project needs.","q":"What resolutions and aspect ratios does Gemini Imagegen support?"},{"a":"Gemini Imagegen uses multi-turn chat to enable iterative refinement. After generating an initial image, you can describe adjustments, request style changes, or ask for variations. The skill processes your feedback and produces refined versions, making it easy to perfect visuals without starting from scratch.","q":"How does Gemini Imagegen refine images through iteration?"}],"shadow_tags":["image-synthesis","visual-generation","api-integration","ai-art","content-creation"],"summary_rewrite":"This skill harnesses Google's Gemini image generation model to create and modify visuals from text descriptions. It supports multiple resolutions (1K\u20134K), aspect ratios, iterative refinement through multi-turn chat, and composition from multiple reference images. Best for logos, product mockups, stylized art, and photorealistic scenes."},"gist":{"api_url":"https://skillfed.io/api/skills/davekilleen/Dex/gemini-imagegen.json","as_of":"2026-07-27","description":"Gemini Imagegen generates images from text prompts using Google's Gemini API with support for editing. npx skillfed install davekilleen/Dex/gemini-imagegen","install":{"manual":["git clone https://github.com/davekilleen/Dex","cp -r Dex ~/.claude/skills/gemini-imagegen"],"primary":"npx skillfed install davekilleen/Dex/gemini-imagegen","version":"0465807c"},"kind":"skill","mirror_url":"https://skillfed.io/davekilleen/Dex/gemini-imagegen.md","similar":[{"id":"rebyteai-template/rebyte-skills/nano-banana","name":"Nano Banana","publisher":"rebyteai-template/rebyte-skills","url":"https://skillfed.io/rebyteai-template/rebyte-skills/nano-banana"}],"title":"Gemini Imagegen by davekilleen: Generate images using Google Gemini API \u2014 SkillFed","use":{"when":["Gemini Imagegen excels at logos, product mockups, stylized art, and photorealistic scenes.","Yes."]},"what":{"lead":"Gemini Imagegen generates images from text prompts using Google's Gemini API with support for editing, refinement, and multiple aspect ratios.","rest":"This skill harnesses Google's Gemini image generation model to create and modify visuals from text descriptions. It supports multiple resolutions (1K\u20134K), aspect ratios, iterative refinement through multi-turn chat, and composition from multiple reference images. Best for logos, product mockups, stylized art, and photorealistic scenes."}},"id":"davekilleen/Dex/gemini-imagegen","install":{"mode":"external","repo":"https://github.com/davekilleen/Dex"},"links":{"html":"https://skillfed.io/davekilleen/Dex/gemini-imagegen","md":"https://skillfed.io/davekilleen/Dex/gemini-imagegen.md","repo":"https://github.com/davekilleen/Dex"},"meta":{"agents_supported":["claude-code"],"first_seen":"2026-07-28","forks":122,"language":"Python","last_updated":"2026-07-27","license":"NOASSERTION","name":"Gemini Imagegen","publisher":"davekilleen","stars":448},"relations":{"similar":[{"id":"ratacat/claude-skills/gemini-imagegen"},{"id":"drshailesh88/integrated_content_OS/gemini-imagegen"},{"id":"majesticlabs-dev/majestic-marketplace/gemini-image-coder"},{"id":"NikiforovAll/claude-code-rules/nano-banana"},{"id":"hoodini/ai-agents-skills/nano-banana-pro"},{"id":"cnemri/google-genai-skills/nano-banana-build"},{"id":"cnemri/google-genai-skills/speech-build"},{"id":"rebyteai-template/rebyte-skills/nano-banana"},{"id":"wwwzhouhui/skills_collection/xiaohuihui-tech-article"},{"id":"inference-sh/skills/nano-banana"}]},"slug":{"owner":"davekilleen","repo":"Dex","skill":"gemini-imagegen"},"version":"0465807c"}