Regolo AI icon

Regolo AI

Use Regolo AI (OpenAI-compatible)
Join our community

Actions3

Overview

The node enables generating images based on textual descriptions using an AI image generation model. Users provide a prompt describing the desired image, select or specify a model to generate it, and configure output format and additional options like image resolution and number of images.

This node is beneficial for creative workflows such as:

  • Generating concept art or illustrations from text prompts.
  • Creating unique images for marketing, social media, or presentations.
  • Rapid prototyping of visual ideas without manual graphic design.

For example, a user can input "A cat sitting on the Colosseum steps at sunset" as a prompt, choose a preferred AI model, and receive one or multiple generated images in either binary file format or as URLs.

Properties

Name Meaning
Prompt Text description of the desired image(s).
Model Model to use for image generation. Options include dynamically loaded models filtered to those supporting image generation, plus a "Custom (Type Manually)" option.
Custom Model When "Custom (Type Manually)" is selected as Model, this string specifies the custom model name.
Response Format Format in which to return the image(s): either as a binary file or as an image URL.
Options Additional options:
- Number of Images How many images to generate (1 to 10).
- Resolution Image resolution: 256x256, 512x512, or 1024x1024 pixels.

Output

The node outputs the generated images in the specified format:

  • If Binary File is selected, the images are returned as binary data suitable for further processing or saving.
  • If Image Url is selected, the output contains URLs pointing to the generated images.

The exact JSON structure depends on the response format but generally includes the image data or URLs corresponding to each generated image.

Dependencies

  • Requires an API key credential for authenticating with the Regolo AI service.
  • The node makes HTTP requests to the configured base URL (from credentials) to perform image generation.
  • Dynamically loads available image generation models via a GET request to /model/info endpoint, filtering for models that support image generation.

Troubleshooting

  • Common issues:

    • Invalid or missing API credentials will cause authentication failures.
    • Selecting a model not supporting image generation may result in errors or empty responses.
    • Requesting too many images or unsupported resolutions might be rejected by the API.
    • Network connectivity problems can prevent successful API calls.

  • Error messages:

    • Authentication errors: Verify that the API key credential is correctly configured.
    • Model not found or unsupported: Ensure the chosen model supports image generation or specify a valid custom model name.
    • Rate limits or quota exceeded: Check API usage limits and adjust request frequency accordingly.

Links and References

  • Regolo AI Documentation (hypothetical link)
  • OpenAI DALL·E or similar image generation API references for conceptual understanding.

Discussion