Image Generation Skills for Claude Code: NanoBanana & Seedance

As a developer working with Claude Code, you know that visual content creation is essential for modern applications — whether you're building educational tools, poetry generators, or short video creators. But generating high-quality images and converting them to video has traditionally required complex workflows and expensive APIs. Today, I'm excited to introduce the image-generation skill pack for ClickAround Creator Pro — a completely free, open-source solution that brings professional-grade image generation and image-to-video capabilities directly into your Claude Code environment.

What Is Image Generation?

The image-generation skill pack consists of two powerful, complementary capabilities:

• NanoBanana Image Generation: Uses Google's Gemini NanoBanana model to generate stunning AI images in various artistic styles (Ghibli, Educational, etc.)
• Seedance Image-to-Video: Converts static images into beautiful motion clips using Seedance 1.5 Fast model via Atlas Cloud API

Both skills are designed specifically for developers who want to integrate visual content generation into their applications without the complexity of managing multiple APIs or dealing with inconsistent outputs.

How NanoBanana Image Generation Works

The NanoBanana image generation service is built around Google's Gemini SDK and provides a clean TypeScript interface:

class ImageGenerationService {
  async generateImages(
    options: {
      prompt: string;
      numberOfImages: number;
      aspectRatio: string; // "9:16" for portrait
    },
    videoId: string,
    sceneIndex: number
  ): Promise<{ success: boolean; images: Array<{ data: Buffer }> }>;
}

Key features include:

• Automatic style prefixes: The service automatically applies appropriate style prefixes to your prompts (Ghibli, Educational, etc.)
• Optimized for Shorts: Default 9:16 portrait aspect ratio perfect for TikTok, Instagram Reels, and YouTube Shorts
• Character reference mode: Supports consistent character generation across multiple scenes
• Cost-conscious design: Built-in recommendations to minimize API costs by limiting image counts

To use NanoBanana, simply install the package, set your GOOGLE_GEMINI_API_KEY environment variable, and call the generateImages() method with your desired prompt and parameters.

How Seedance Image-to-Video Works

The Seedance image-to-video service converts your generated images into captivating motion clips:

class AtlasCloudClient {
  async generateVideo(options: {
    prompt: string;        // 영상 모션 설명
    image: string;         // base64 또는 URL
    duration: number;      // 초 단위 (5~10)
    orientation: string;   // "portrait" (9:16)
    cameraFixed: boolean;  // true 권장 (할루시네이션 방지)
  }): Promise<{ url: string }>;
}

Key features include:

• Critical cameraFixed parameter: Must be set to true to prevent hallucinations and ensure stable results
• Optimized for vertical content: 9:16 portrait orientation only, perfect for mobile-first applications
• Cost-effective: ~$0.11 per clip, making it significantly more affordable than alternatives like Runway ML
• Fast processing: Results typically ready in 30 seconds to 2 minutes

The Seedance service uses the bytedance/seedance-v1.5-pro/image-to-video-fast model via Atlas Cloud API, which we've verified to be more cost-effective than alternatives like vast.ai.

Getting Started in 3 Steps

Integrating these skills into your project is incredibly simple:

1. Install the marketplace: /plugin marketplace add https://github.com/clickaround/marketplace
2. Install the skill: /plugin install image-generation@clickaround
3. Configure your API keys: Set GOOGLE_GEMINI_API_KEY and ATLAS_CLOUD_API_KEY environment variables

That's it! You're ready to start generating images and converting them to video within your Claude Code environment.

Real-World Use Cases

Developers are already using these skills in production for several compelling applications:

• Educational Tools: Generating custom illustrations for learning materials and textbooks
• Poetry Generators: Creating evocative imagery to accompany poetic content
• Short Video Creation: Building automated pipelines from text → images → video clips
• Marketing Assets: Rapidly prototyping visual concepts for social media campaigns
• Prototyping: Visualizing UI concepts and application flows during development

The beauty of this approach is that you get professional-grade visual generation capabilities without the vendor lock-in or unpredictable pricing models of commercial services.

Why This Approach Beats Commercial Alternatives

Compared to commercial image generation services, the image-generation skill pack offers several distinct advantages:

• 100% Open Source (MIT License): No restrictions on usage, modification, or distribution
• No Vendor Lock-in: You control your API keys and can switch providers as needed
• Cost Predictability: Pay only for what you use through standard API billing
• Developer-Centric Design: Clean TypeScript interfaces and comprehensive documentation
• Production-Ready: Includes error handling, rate limiting, and performance optimizations

We've focused on creating a solution that works reliably in real-world development scenarios, not just theoretical demos.