Generate and edit images via the Gemini API from text prompts.
npx skills add https://github.com/sidsarasvati/dotfiles --skill gemini-imagegen
Please help me install this Agent Skill. Skill: gemini-imagegen Source: https://github.com/sidsarasvati/dotfiles/tree/main/claude/skills/gemini-imagegen Command: npx skills add https://github.com/sidsarasvati/dotfiles --skill gemini-imagegen
This skill provides a powerful, flexible interface to Google's Gemini API for all image generation and manipulation needs. It simplifies complex tasks like creating images from text, editing existing visuals, applying style transfers, or composing multiple images, saving designers and content creators significant time and effort.
Generate an image of "A cat wearing a wizard hat" and save it as output.png.
High-intent search queries and answers about installing and using this skill.
Text-to-image generation with Gemini API converts written descriptions into high-quality images by calling the gemini-2.5-flash-image or gemini-3-pro-image-preview models with your prompt. Set response_modalities to TEXT and IMAGE, configure aspect_ratio and image_size in image_config, and the API returns both visual output and descriptive text in a single response.
Yes, this skill supports iterative image editing through multi-turn chat. After generating an initial image, send follow-up prompts describing refinements—such as style changes, color adjustments, or composition tweaks—and the Gemini API modifies the image based on your conversational instructions across multiple turns.
Gemini image generation supports resolutions up to 4K and customizable aspect ratios configured through image_config parameters. The skill uses the Pillow library to handle image processing and composition, supporting standard image formats for both input reference images and output visuals.
Advanced composition merges up to 14 reference images into one coherent visual by passing them as inputs to the Gemini API alongside a composition prompt. This is ideal for product mockups, group scenes, or complex layouts where you want to blend multiple source images into a unified result.
Yes, you must provide a GEMINI_API_KEY environment variable to authenticate with Google's Gemini API. The skill passes this key when calling gemini-2.5-flash-image or gemini-3-pro-image-preview models, so valid credentials are a prerequisite for all image generation and editing operations.
While Gemini excels at creating logos and mockups from text prompts, results depend on prompt clarity and model interpretation. Complex brand requirements, precise text rendering, or highly specific design constraints may require iterative refinement through multi-turn chat rather than single-pass generation.
resultanyildiziGenerate and edit images via Google's Gemini 3 Pro Image API.
SJTU-IPADSAutomate deterministic image editing tasks on image collections with Pillow.
michaelvolzGenerate and edit images from text prompts via Gemini API endpoints.
EveryIncGenerate and edit images via the Gemini API with multi-turn refinement.
