How to Use Google’s Nano Banana FREE with n8n (No-Code Tutorial)

AI WorkshopAbout 4 min readAug 29, 2025Watch original
THE SUMMARYAI-generated

Key Concepts

  • Google Gemini 2.5 Flash (Nano Banana): A new image generation model by Google.
  • Open Router: A platform providing access to various AI models, including Gemini 2.5 Flash.
  • Naden: A workflow automation platform used to integrate and utilize AI models.
  • HTTP Request Node: A Naden node used to make API calls to external services like Open Router.
  • Base64 String: A text representation of binary data, used for encoding images.
  • POV Videos: Point-of-view videos, often animated, simulating a first-person perspective.
  • RunwayML: A platform for AI-powered video editing and animation.
  • AI Agency: A business model focused on providing AI-related services to clients.
  • Retail AI: A voice AI platform.

Google Gemini 2.5 Flash (Nano Banana) Image Model

  • Introduction: Google has released Gemini 2.5 Flash, an image model that the speaker claims outperforms existing models, including GPT image generation.
  • Performance: According to TechCrunch, Gemini 2.5 Flash (referred to as "Nano Banana") surpasses other models in image generation quality.
  • Key Features: The model excels in editing features, character consistency, and overall image quality.
  • Free Access via Open Router: The video emphasizes that Gemini 2.5 Flash is currently available for free through Open Router. The speaker notes that this free access might be temporary.
  • Cost: Open Router currently lists the model as "$0 per input token and $0 per output token." The speaker confirms this through personal testing.

Utilizing Gemini 2.5 Flash in Naden

  • Workflow Overview: The video demonstrates how to integrate Gemini 2.5 Flash into a Naden workflow for automated image generation.
  • Naden Form Trigger: The workflow starts with a Naden form trigger, allowing users to input a text description for the desired image.
  • Prompt Generation: An AI prompt is used to transform the user's short description into a detailed, hyperrealistic cinematic image prompt. The AI is instructed to output the prompt as a single JSON.
  • HTTP Request Node Configuration:
    • Purpose: To communicate with the Open Router API.
    • Method: POST request.
    • URL: openrouter.ai/api/v1/chat/completions (This is the base URL, the model needs to be specified in the body).
    • Authentication: Uses Open Router API key, stored as a credential in Naden.
    • Headers:
      • Content-Type: application/json
    • Body: Specifies the model, role, and content for the image generation request.
      • model: "google/gemini-2.5-flash-image-preview-free" (Important to write this correctly)
      • modalities: "image, text"
      • role: "user"
      • content: The generated image prompt from the previous step.
  • Response Processing: The API returns a JSON response containing a URL for the image data (in Base64 format).
  • Data Extraction: The "Edit Fields" node extracts the image URL from the JSON response.
  • Base64 to File Conversion: The "Convert to File" node converts the Base64 string into an image file.
  • Example: The speaker demonstrates generating an image of "a large monkey holding a banana," showcasing the model's speed and high image quality.

Creating POV Videos and Baby Podcasts with Gemini 2.5 Flash

  • POV Video Workflow: The video demonstrates how to adapt an existing POV video workflow to use Gemini 2.5 Flash instead of other image generation models.
    • The original workflow used Flux AI for image generation.
    • The speaker replaces the Flux AI node with the Gemini 2.5 Flash workflow described earlier.
    • The generated image is then passed to RunwayML for animation.
  • Baby Podcast Workflow: The video shows how to integrate Gemini 2.5 Flash into a "baby podcast" workflow.
    • The original workflow used OpenAI's image generation, which is costly.
    • The speaker replaces the OpenAI image generation node with the Gemini 2.5 Flash workflow, resulting in better quality images for free.
    • The workflow involves selecting the baby's ethnicity and topic of discussion, then generating an image of the baby podcasting.

Community and Monetization Opportunities

  • Community Invitation: The speaker encourages viewers to join their community for tutorials, resources, and tech support.
  • AI Agency: The community offers guidance on monetizing AI skills and building an AI agency.
  • Voice AI Course and Retail AI Partnership: The speaker highlights a voice AI course in partnership with Retail AI, offering certification for those who complete the training. This certification allows individuals to sell voice AI services to clients.

Conclusion

The video provides a practical guide to using Google's Gemini 2.5 Flash image model for free through Open Router and Naden. It demonstrates how to integrate the model into automated workflows for image generation, POV video creation, and other applications. The speaker emphasizes the model's high quality, speed, and the potential for monetization through AI-related services. The call to action encourages viewers to join the community for further learning and support.

AI summaries can miss context or contain errors. Check important details against the original video.

Go a little deeper.

Have a question about this video? Load its transcript to open the video chat.