Image generation and editing based on Google Gemini native image generation (Nano Banana).
设计与多媒体
Nano Img CLI
试用Drives the local nano-img Gemini image CLI for image generation, model selection, saved defaults, reference-image workflows, and output sizing or format conv...
它能做什么
Drives the local nano-img Gemini image CLI for image generation, model selection, saved defaults, reference-image workflows, and output sizing or format conv...
技能文档
Nano Img CLI
When To Use
Use this skill when the task is specifically about the local nano-img or nano-image CLI in this repository or its home-directory defaults under ~/.nano-img.
Package naming note:
- npm package:
nanobana - installed commands:
nano-img,nano-image
Typical triggers:
- "generate an image with nano-img"
- "set the nano-img model"
- "save images to a default folder"
- "use the refs from ~/.nano-img/assets"
- "show what nano-img supports"
- "fix or inspect nano-img config"
Do not use this skill for general Gemini API design discussions that are not tied to this CLI.
Execution Mode
Prefer the installed binaries when available:
nano-imgnano-image
If you are working inside this repo and do not want to depend on a global link, use:
npm run dev --npm run nano-img --
Core Workflow
- Start by checking the exact command surface instead of assuming flags.
Use
nano-img helpfor global help ornano-img --helpfor command help. - If the task is generation, inspect saved defaults first when they matter.
Run
nano-img config --json. - If the task depends on a saved model or output directory, prefer the dedicated commands over editing config by hand:
nano-img model ...nano-img save-dir ...
- If the task depends on reusable prompts or style, use the home-directory files:
~/.nano-img/INSTRUCTION.md~/.nano-img/STYLE.md~/.nano-image/STYLE.md
- If the task uses default reference images, inspect
~/.nano-img/assetsand verify withnano-img refs --json. - After changing behavior, validate with one concrete CLI command and capture the resulting output path or config state.
Generate Images
For generation details and command recipes, read references/command-reference.md.
Key rules:
- Use
generateexplicitly unless the user clearly wants the shorthand prompt form. - Respect saved defaults from
~/.nano-img/config.json. - If the user passes
--save-toor--output, that overrides the saved default output directory. - Width-only or height-only requests preserve aspect ratio during local resize.
- Width plus height forces the final image to the exact requested dimensions.
- Format defaults to
png;jpg,jpeg, andwebpare supported through local conversion.
Configure Defaults
For persistent settings and file layout, read references/defaults-and-files.md.
Prefer command-driven config changes:
- Save model:
nano-img model - Pick model interactively:
nano-img models - Save default output dir:
nano-img save-dir --set "" - Clear saved output dir:
nano-img save-dir --clear-save-dir
Avoid editing ~/.nano-img/config.json directly unless the user explicitly asks for a manual file edit.
Troubleshooting
Read references/troubleshooting.md when:
- generation fails
- models do not list
- the picker or config looks wrong
- output paths or refs are not being used
Validation
After making changes or guiding usage:
- run one obvious command that should succeed
- use
--jsonwhen you need machine-readable confirmation - report the exact saved model, output directory, or generated file path when relevant
相关技能
Generate and edit images with Nano Banana through RunAPI. Use when the user asks an agent to create, edit, or transform images with Nano Banana. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend.
Generate images through the Nano Banana REST API and help agents integrate or operate the service safely. Use when a task involves text-to-image, image-to-im...
Use when tasks need the NanoGPT API for text, image, or video generation through the local `nano-gpt` CLI and bundled wrapper scripts for OpenClaw or ClawHub...
Use APIDot for Nano Banana 2 API workflows, including Gemini 3.1 Flash Image API, nano-banana-2, nano-banana-2-edit, text-to-image API, image editing API, re...
AI multi-image generation powered by CellCog via Nano Banana. 10-20 coherent images in one prompt, character consistency across scenes, production-grade composition. Nano Banana AI, Nano Banana Pro, Gemini image generation.