š Nanobanana Pro Fallback OpenClaw Plugin & Skill | ClawHub
Looking to integrate Nanobanana Pro Fallback into your AI workflows? This free OpenClaw plugin from ClawHub helps you automate image & video generation tasks instantly, without having to write custom tools from scratch.
What this skill does
Nano Banana Pro with auto model fallback ā generate/edit images via Gemini Image API. Run via: uv run {baseDir}/scripts/generate_image.py --prompt 'desc' --filename 'out.png' [--resolution 1K|2K|4K] [-i input.png]. Supports text-to-image + image-to-image (up to 14); 1K/2K/4K. Fallback chain: gemini-2.5-flash-image ā gemini-2.0-flash-exp. MUST use uv run, not python3.
Install
openclaw skills install @yazelin/nanobanana-pro-fallbacknpx clawhub@latest install nanobanana-pro-fallbackFull SKILL.md
Open original| name | version | description | license | homepage |
|---|---|---|---|---|
| nanobanana-pro-fallback | 0.4.4 | Nano Banana Pro with auto model fallback ā generate/edit images via Gemini Image API. Run via: uv run {baseDir}/scripts/generate_image.py --prompt 'desc' --filename 'out.png' [--resolution 1K|2K|4K] [-i input.png]. Supports text-to-image + image-to-image (up to 14); 1K/2K/4K. Fallback chain: gemini-2.5-flash-image ā gemini-2.0-flash-exp. MUST use uv run, not python3. | MIT | https://github.com/yazelin/nanobanana-pro |
SKILL.md content below is scrollable.
Nano Banana Pro with Fallback
Use the bundled script to generate or edit images. Automatically falls back through multiple Gemini models if one fails.
ā ļø IMPORTANT: MUST use uv run or the generate wrapper. Do NOT use python3 directly ā dependencies won't be available.
Generate (option A: wrapper script)
{baseDir}/scripts/generate --prompt "your image description" --filename "output.png" --resolution 1K
Generate (option B: uv run)
uv run {baseDir}/scripts/generate_image.py --prompt "your image description" --filename "output.png" --resolution 1K
Edit (single image)
uv run {baseDir}/scripts/generate_image.py --prompt "edit instructions" --filename "output.png" -i "/path/in.png" --resolution 2K
Multi-image composition (up to 14 images)
uv run {baseDir}/scripts/generate_image.py --prompt "combine these into one scene" --filename "output.png" -i img1.png -i img2.png -i img3.png
API key
GEMINI_API_KEYenv var- Or set
skills."nanobanana-pro-fallback".apiKey/skills."nanobanana-pro-fallback".env.GEMINI_API_KEYin~/.openclaw/openclaw.json
Notes
- Resolutions:
1K(default),2K,4K. - Models tried in order:
gemini-2.5-flash-imageāgemini-2.0-flash-exp-image-generation(configurable viaNANOBANANA_FALLBACK_MODELSenv var). - Use timestamps in filenames:
yyyy-mm-dd-hh-mm-ss-name.png. - The script prints a
MEDIA:line for OpenClaw to auto-attach on supported chat providers. - Do not read the image back; report the saved path only.