Summary
A single Python entrypoint for Gemini's image generation models with clean alias support for the three tiers: the fast default, the preview model with 512px and 2K sizes, and the pro reasoning variant. The workflow is sensible: check the model constraints doc, run generate or batch, add dry-run when you're testing payload shape. Multiple input images work for edits or multi-reference prompts, and custom base URL support means you can point it at a self-hosted gateway. The auth-mode auto flag sends both bearer and API key headers to maximize compatibility. It's the kind of wrapper that saves you from re-reading model docs every time you switch tiers.
Install to Claude Code
npx -y skills add gargantuax/openskills --skill nanobanana --agent claude-codeInstalls into .claude/skills of the current project.
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Files
SKILL.md
Select a file.
Featured
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
