nano-banana-cog
par nitishgargiitd
Coding Agents & IDEsRésumé
Nano Banana × CellCog.
Description
Ce que fait ce skill
Wraps Nano Banana image generation through CellCog's execution layer. Supports text-to-image, character-consistent series, multi-image composition, and photo editing at 1K–4K resolution. Any OpenClaw agent can invoke it with a single prompt.
Exposes Nano Banana's character consistency and multi-resolution output inside any OpenClaw agent without a separate image API integration.
Quand l'utiliser
- Generating product shots for e-commerce listings
- Creating a brand mascot in multiple poses and contexts
- Building a visual story sequence with a consistent character
- Transforming photos with style transfer or background swaps
- Producing photorealistic marketing scenes from text descriptions
Exemple de workflow
User asks: Create a tech entrepreneur character, then show them presenting on stage and working at a laptop
- 1
Calls CellCog client with chat_mode set to 'agent'
- 2
Sends detailed character description including age, style, and lighting for the initial portrait
- 3
Receives first image with character identity established
- 4
Sends follow-up prompts referencing 'the same character' for the stage and laptop scenes
- 5
Returns all three images with consistent character appearance
Three photorealistic images of the same character across different professional contexts
Installation
clawhub install nitishgargiitd/nano-banana-cogExécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.