ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified media Safety 4/5

wavespeed-nano-banana-2

Generate and edit images using Google's Nano Banana 2 model via WaveSpeed AI. Supports text-to-image generation and image editing with natural language prompts. Features native 4K resolution, flexible aspect ratios including ultra-narrow (1:8, 8:1), multilingual text rendering, and camera-style controls. Use when the user wants to create images from text or edit existing images.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/chengzeyi/wavespeed-nano-banana-2
Or

What This Skill Does

The wavespeed-nano-banana-2 skill integrates Google's powerful Nano Banana 2 model into the OpenClaw ecosystem, providing advanced image generation and sophisticated editing capabilities. Designed for high-fidelity output, this tool leverages the WaveSpeed AI platform to deliver native 4K resolution, support for exotic aspect ratios like 1:8 and 8:1, and precise multilingual text rendering. Whether you need to generate entirely new visual assets from a text prompt or perform contextual edits on existing images, this model excels in both creative flexibility and technical precision.

Installation

To integrate this model, ensure you have the OpenClaw CLI configured. Run the following command in your terminal: clawhub install openclaw/skills/skills/chengzeyi/wavespeed-nano-banana-2 After installation, you must configure your environment variable: export WAVESPEED_API_KEY="your-api-key". You can obtain this key from the official WaveSpeed portal. Verification of the installation can be confirmed by invoking the model's metadata in your local environment.

Use Cases

  • Professional Design: Quickly generate high-resolution concept art or backgrounds for websites and marketing materials using specific aspect ratios.
  • Content Modification: Use the editing feature to perform complex tasks like replacing backgrounds, changing object colors, or altering environmental lighting in photos.
  • Multilingual Asset Creation: Generate imagery featuring text in diverse languages, making it ideal for international marketing campaigns.
  • Dynamic Layouts: Utilize ultra-narrow ratios for decorative UI elements, banners, or social media headers.

Example Prompts

  1. "Generate a 4K photorealistic image of a sleek minimalist desk setup with a neon-lit keyboard, use a 21:9 aspect ratio."
  2. "Edit this photo to replace the rainy city street background with a sunny beach at dusk while keeping the person in the foreground clear."
  3. "Create a vertical banner, aspect ratio 1:4, featuring futuristic abstract geometry and glowing particles in a 4k png format."

Tips & Limitations

To maximize the quality of your images, be descriptive with lighting and style keywords in your prompt. The editing feature supports up to 14 input images at once; however, complex edits may require clear input photos. Note that very extreme aspect ratios may occasionally introduce distortion at the edges of the frame. Ensure your API key has sufficient usage credits, as high-resolution 4K generation consumes more platform resources than standard 1k exports.

Metadata

Author@chengzeyi
Stars3840
Views0
Updated2026-04-06
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-chengzeyi-wavespeed-nano-banana-2": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#generative-ai#image-editing#4k-graphics#visual-design#api-integration
Safety Score: 4/5

Flags: external-api, file-read

Related Skills

wavespeed-face-swapper

Swap faces in images and videos using WaveSpeed AI. Supports image face swap and video face swap with multi-face targeting. Produces watermark-free results with automatic lighting and skin tone adaptation. Use when the user wants to replace a face in an image or video with another face.

chengzeyi 3840

wavespeed-infinitetalk

Generate talking head videos from a portrait image and audio using WaveSpeed AI's InfiniteTalk model. Produces lip-synced video up to 10 minutes long at 480p or 720p. Supports optional mask images to target specific faces and text prompts for additional guidance. Use when the user wants to animate a face with audio or create talking avatar videos.

chengzeyi 3840

wavespeed-minimax-speech-26

Convert text to speech using MiniMax Speech 2.6 Turbo via WaveSpeed AI. Features ultra-human voice cloning, sub-250ms latency, 40+ languages, emotion control, and 200+ voice presets. Use when the user wants to generate speech audio from text.

chengzeyi 3840

wavespeed-seedream-45

Generate and edit images using ByteDance's Seedream V4.5 model via WaveSpeed AI. Supports text-to-image generation and multi-image editing with custom resolutions up to 4096x4096. Features enhanced typography for posters and logos. Use when the user wants to create or edit images with high-quality text rendering.

chengzeyi 3840

wavespeed-watermark-remover

Remove watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI. Intelligently detects and removes watermarks while preserving texture and background. Supports images and videos up to 10 minutes. Use when the user wants to remove watermarks or text overlays from media.

chengzeyi 3840