Generate and edit images with Gemini

Creates images from text prompts or edits existing images using Google's Gemini 3 Pro and 2.5 Flash models. Works with batch processing and multi-image inputs.

Best for: Designers and founders who need quick visual assets without leaving Claude.

Design / craft-polishatomicfor-designersneeds-integrationfrom-text

Source

Creator's repository · inference-sh/skills

View on GitHub