Generate images from text, edit an existing image, or combine up to 14 images into one composition. Choose from three Nano Banana models and specify the output resolution, aspect ratio, and filename.
中文简介正在准备中。当前显示英语简介。
Generate or edit images via Nano Banana image models. Triggers on "generate image", "image generation", "nano banana", "edit image", "nano banana pro", "nano banana 2"
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Image generation script supporting three models. Requires sharp for input image compression (auto-installed on first run).
| Flag | Notes |
|---|---|
--model nano-banana | Default. Fast, good quality. |
--model nano-banana-pro | Highest quality, slower. |
--model nano-banana-2 | Legacy model. |
node {baseDir}/scripts/generate-image.js --prompt "a cat sitting on mars" --filename "cat-on-mars.png"
node {baseDir}/scripts/generate-image.js \
--prompt "make the sky purple" \
--filename "edited.png" \
-i "/path/to/input.png" \
--model nano-banana-pro
node {baseDir}/scripts/generate-image.js \
--prompt "combine these into a collage" \
--filename "collage.png" \
-i img1.png -i img2.png -i img3.png
| Flag | Short | Default | Description |
|---|---|---|---|
--prompt | -p | required | Image description or editing instruction |
--filename | -f | required | Output filename |
--input-image | -i | — | Input image(s), repeatable, max 14 |
--model | — | nano-banana | nano-banana, nano-banana-pro, or nano-banana-2 |
--resolution | -r | 1K | 1K, 2K, or 4K |
--aspect-ratio | — | — | e.g. 1:1, 16:9, 4:3, 3:4, 9:16 |
The API key is pre-configured on this machine. No flags or environment variables needed.
All input images are sent as inline base64. Images over 500 KB are automatically compressed to JPEG and resized to fit under the limit. This keeps requests fast and avoids File API auth issues with the enterprise endpoint.
Relative filenames are saved to $OPENCLAW_STATE_DIR/media/outbound/{slugid}/nano-banana/{filename}. Absolute paths are used as-is. Absolute paths are used as-is. Use timestamps in filenames to avoid overwrites: cat-on-mars-20260304-165000.png.
The script prints a MEDIA: <absolute-path> line on stdout. You MUST include this exact MEDIA: line in your reply text so the image is delivered as an attachment in Discord/Slack/chat.
Example reply:
Here's your image!
MEDIA: /Users/alche/.openclaw/media/outbound/my-bot/nano-banana/cat-on-mars.png
Rules:
MEDIA: line from the script output into your reply verbatim — this is how images get sentMEDIA: line must be on its own line in your response还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Use the ClawHub command-line tool to find and install agent skills, update them to the latest or a specified version, list installed skills, and publish skill folders with version numbers and change notes.
中文简介正在准备中。当前显示英语简介。
Delegate feature development, code refactoring, and pull request reviews to Codex, Claude Code, Pi, or OpenCode. It guides background execution, progress monitoring, and parallel work in separate working directories.
中文简介正在准备中。当前显示英语简介。
Investigate Nexu production issues through the Datadog Logs API. Search crash events, error output, startup activity, and API failures, then summarize findings by time, running instance, and deployed version to help trace related events.
中文简介正在准备中。当前显示英语简介。
Turn a broad research topic into a structured report with traceable sources. The workflow defines questions, prioritizes authoritative material, separates facts from assumptions, compares evidence, and uses an independent agent to check key data and reasoning.
中文简介正在准备中。当前显示英语简介。
Send bug reports, suggestions, or other feedback to the Nexu team using `/feedback`. The submission script automatically includes conversation history and images, then reports whether the feedback was successfully forwarded.
中文简介正在准备中。当前显示英语简介。
Create and manage Feishu Bitable tables for work such as customer tracking. Add, search, update, or delete records, configure columns using 27 field types, filter and sort data, and manage views or batch imports.
中文简介正在准备中。当前显示英语简介。