What problem does it solve? Creating custom images for blogs, apps, and marketing materials typically requires design skills or stock photo subscriptions. This Skill lets you generate and edit images directly from text prompts using Google's Gemini image models, covering everything from hero images to logos without leaving your workflow. ## Core Features & Use Cases - Text-to-Image Generation: Create photorealistic photos, illustrations, icons, and logos from detailed natural-language prompts. - Image Editing: Modify existing images with instructions like background replacement, style transfer, object addition or removal, and color grading via the --file option. - Prompt Engineering Guidance: Includes a comprehensive prompting guide and categorized example prompts for headers, icons, illustrations, and product photography. - Use Case: You need a 16:9 hero image for a technology blog post. Describe the subject, style, color palette, and exclusions, then generate it with one CLI command and iteratively refine the result. ## Quick Start Ask the AI to generate a wide 16:9 minimalist header image for a technology blog with teal and orange geometric shapes on a white background.
