Generate images from text prompts using Google's Gemini API.
npx skills add https://github.com/declanshanaghy/fenrir-ledger --skill imagen-declanshanaghy
Please help me install this Agent Skill. Skill: imagen Source: https://github.com/declanshanaghy/fenrir-ledger/tree/main/.claude/skills/imagen Command: npx skills add https://github.com/declanshanaghy/fenrir-ledger --skill imagen-declanshanaghy
Generate images from text prompts using Google's Gemini API to produce visual assets, reducing design turnaround time for concept visuals and assets.
Run the generator with a text prompt or a preset to produce one or more images.
High-intent search queries and answers about installing and using this skill.
To generate images from text prompts using the Gemini API, you need a valid GOOGLE_API_KEY or GEMINI_API_KEY. The tool processes your text input to produce visual assets like logos or posters, saving the output as PNG files.
AI image generation supports multiple aspect ratios including 1:1, 16:9, 9:16, 4:3, and 3:4. The generated visual assets are outputted as PNG files, which are saved to a specified path on your system.
Yes, you need a valid Gemini API key to create AI art and graphics. You must configure either the GOOGLE_API_KEY or GEMINI_API_KEY environment variable to authenticate requests and generate visual assets successfully.
Yes, you can use built-in presets like fenrir-logo, fenrir-icon, norse-badge, and fenrir-medallion to quickly generate logos and icons. These presets allow for rapid visual concept creation without writing complex prompts.
If your text-to-image generation encounters an error, the tool handles it gracefully. Ensure your GOOGLE_API_KEY or GEMINI_API_KEY is valid and check that your specified output path is accessible to resolve common generation failures.
Yes, you can generate multiple images from a single text prompt. The image generation tool supports multiple-image output, allowing you to produce several PNG visual assets simultaneously based on your prompt and aspect ratio settings.
Sampi314Configure GEMINI_API_KEY on Windows and verify it against the stable v1 endpoint.
YSheldonApply resize, crop, filter, and optimization tasks to images via Python or Node.
zaiyemeiyou404Generate knowledge comics with customizable art styles, tones, and layouts.
ash-ai-orgGenerate images from text prompts using the Gemini API.
