Summary
Generates images through Google's Gemini native image models using the inference.sh CLI. You get access to both Gemini 3 Pro Image for quality and Gemini 2.5 Flash Image for speed, with support for text-to-image, image editing, and multi-image inputs. The real differentiator here is Google Search grounding, which lets you incorporate real-time web data into prompts. Works through the belt CLI with straightforward JSON inputs for aspect ratios, resolution up to 4K, and batch generation. Solid option if you're already in the inference.sh ecosystem and want Google's models without hitting their APIs directly.
Install to Claude Code
npx -y skills add inference-sh/skills --skill nano-banana --agent claude-codeInstalls into .claude/skills of the current project.
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
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
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →First SeenJun 3, 2026
