AIConnect icon

AIConnect

Use OpenAI-compatible API functions
Join our community

Actions7

Overview

The node "AIConnect" provides access to OpenAI-compatible API functions for multiple AI resources, including chat, image, and audio. Specifically, for the Image resource with the Variation operation, it generates variations of a given input image using a selected AI model.

This is useful when you want to create multiple stylistic or content variations of an existing image automatically. For example, designers can generate different versions of a concept art piece, marketers can produce diverse ad visuals from one base image, or developers can experiment with AI-driven image augmentation.

Practical examples:

  • Upload a product photo and generate several stylistic variations for A/B testing.
  • Provide a sketch or base image and get multiple AI-generated interpretations.
  • Create multiple resolution options or styles of an image for different platforms.

Properties

Name Meaning
Model The AI model used for image generation. Options are dynamically loaded via getImageModels.
Image The base image to edit or use as the source for generating variations.
Number of Images How many image variations to generate (1 to 10).
Size The resolution of generated images. Options: "256x256", "512x512", "1024x1024".
Response Format Format of the returned images: either URLs pointing to the images or Base64-encoded JSON strings.
Additional Options Collection of optional parameters:
- Quality: "Standard" or "HD"
- Style: "Vivid" or "Natural"
- User: Unique identifier string representing the end-user.
Simplify Output Whether to return a simplified response containing only essential data instead of full raw output.

Output

The node outputs an array of JSON objects, each representing one generated image variation. The key fields in the json output typically include:

  • If Response Format is "URL": URLs pointing to the generated images.
  • If Response Format is "Base64": Base64-encoded image data strings.

If Simplify Output is enabled, the output is a streamlined version focusing on the core image data rather than verbose metadata.

Binary data is not directly output by this node; images are provided as URLs or Base64 strings depending on configuration.

Dependencies

  • Requires an API key credential for accessing an OpenAI-compatible image generation service.
  • The node dynamically loads available image models via an internal method.
  • Network connectivity to the external AI service endpoint is necessary.
  • No additional environment variables are explicitly required beyond the API credential.

Troubleshooting

  • Common issues:

    • Invalid or missing API credentials will cause authentication failures.
    • Providing an invalid image format or corrupted image string may result in errors.
    • Requesting more images than allowed (above 10) will be rejected.
    • Unsupported model names or unavailable models can cause operation failure.
    • Network timeouts or service unavailability will interrupt execution.

  • Error messages:

    • "The resource \"image\" is not supported!" — indicates a misconfiguration of the resource parameter.
    • API error messages related to quota limits, invalid parameters, or authentication should be checked against the external service documentation.

  • Resolutions:

    • Verify API key validity and permissions.
    • Ensure the input image is correctly formatted and accessible.
    • Use valid model names as listed by the node's model loading method.
    • Reduce the number of requested images if hitting limits.
    • Check network connectivity and retry on transient failures.

Links and References

Discussion