Text-to-image and image editing with Google Gemini 3.1 Flash, supporting up to 14 input images and real-time search grounding. Generates single or multiple images with customizable aspect ratios (1:1, 16:9, 9:16, 4:3, 3:4) and resolutions up to 4K Edits existing images by accepting up to 14 input images (JPEG, PNG, WebP) alongside a text prompt Enables Google Search grounding to incorporate real-time information like weather and news into generated imagery Accessible via inference.sh CLI ( infsh ) with Python SDK support for streaming live progress updates
Install
Add to Contextium Workspace
Sign up free to add this skill to your workspace and sync it across Claude, Cursor, VS Code, and more.
Install via CLI
Run this command to install directly into your Contextium workspace.
contextium skill get inferen-sh-nano-banana-2
New to the CLI? npm install -g @contextium/[email protected] then contextium login
Is this yours?
This listing was imported from skills.sh under the handle @@inferen-sh. If you created this, you can claim it and take ownership of the listing.