fusionbrain.ai icon

fusionbrain.ai

fusionbrain.ai Text2Image
Join our community

Overview

This node integrates with the fusionbrain.ai API to generate images from text prompts using AI models. It is designed primarily for the "Generate Image" operation, where users provide a textual description (prompt) and receive AI-generated images based on that input.

Common scenarios include:

  • Creating artistic or illustrative images from descriptive text.
  • Generating concept art or visual ideas quickly without manual drawing.
  • Enhancing creative workflows by automating image generation based on style and model preferences.

For example, a user might input a prompt like "a drawing of nature drawn with a brush and paints, the sea, mountains, pine trees, calm colors" and receive an AI-generated image matching that description.

Properties

Name Meaning
Model Name or ID Select the AI model to use for image generation. Options are loaded dynamically from available models. You can also specify a model ID via expression.
Style Name or ID Choose the style to apply to the generated image. Options are loaded dynamically from available styles. You can also specify a style ID via expression. Default is "DEFAULT".
Prompt The main text description guiding the image generation. For example: "a drawing of nature drawn with a brush and paints, the sea, mountains, pine trees, calm colors".
Negative Prompt Text describing elements to avoid in the generated image, e.g., "worst quality, low res, blurry, watermark, logo". Helps improve output quality by excluding unwanted features.
Width Width of the generated image in pixels. Integer between 1 and 1024. Default is 1024.
Height Height of the generated image in pixels. Integer between 1 and 1024. Default is 1024.

Output

The node outputs one or more items containing:

  • json: An object with metadata about the generated image, including a censored flag indicating if the content was censored.
  • binary.data: The generated image file in JPEG format (image/jpg). This binary data contains the actual image encoded as a buffer.

Each output item corresponds to one generated image. The binary data can be used downstream in n8n workflows for saving files, sending emails, or further processing.

Dependencies

  • Requires an API key credential for authentication with the fusionbrain.ai service.
  • Makes HTTP requests to fusionbrain.ai endpoints for model listing, style listing, image generation, and status polling.
  • Uses multipart/form-data POST requests to submit generation jobs.
  • Polls the job status endpoint repeatedly until the image generation is complete.

Troubleshooting

  • Timeouts or long waits: The node polls the generation status every 2 seconds until completion. Large or complex prompts may take longer. Ensure your workflow timeout settings accommodate this.
  • Authentication errors: Verify that the API key credential is correctly configured and has necessary permissions.
  • Invalid model or style selection: If the selected model or style ID is invalid or unavailable, the API will return an error. Use the "List Models" and "List Styles" operations to verify available options.
  • Image size limits: Width and height must be integers between 1 and 1024. Values outside this range will cause validation errors.
  • API errors: Any API failure will throw an error unless "Continue On Fail" is enabled, in which case the error details are included in the output JSON.

Links and References

Discussion