generate-image

To generate AI art from text prompts using Gemini, provide a descriptive text prompt and the skill automatically rewrites it for clarity before executing the Gemini 3 Pro image generation API call to produce the visual output.

Yes, you can create image variations from an existing image using the img2img capability, which applies prompt rewriting and optional style library adherence to generate modified visual outputs via the Gemini API.

Yes, this image generation approach supports creating banners, logos, and illustrations by rewriting your initial text prompt for clarity and applying optional style references through the Gemini 3 Pro API.

To apply specific visual styles to AI-generated images, select a desired option from the style library, and the skill will use prompt hints and tile references to guide style adherence during the Gemini image generation process.

Prompt rewriting is the process of refining your initial text input for clarity and detail before API execution, which improves image generation by ensuring the Gemini model receives a well-structured prompt for better visual results.

Yes, you can generate social share images and OG images by providing text prompts that describe the desired output, leveraging the prompt rewriting and Gemini 3 Pro integration to create compliant visual assets.