Create Images from Text Prompts using Lumi and Replicate

This n8n workflow demonstrates how to generate images from text prompts using a combination of external APIs, specifically hinting at services like Lumi and Replicate (based on the directory name, though the JSON itself doesn't explicitly name them). It provides a foundational structure for interacting with image generation models, handling asynchronous operations, and retrieving results.

What it does

This workflow outlines the following steps:

1. Manual Trigger: The workflow is initiated manually, allowing for on-demand image generation.
2. Edit Fields (Set): This node is typically used to prepare or transform data. In this context, it would likely be used to define the text prompt for image generation, or other parameters required by the image generation API.
3. HTTP Request (Image Generation): This node sends an HTTP request to an external API (e.g., Replicate, Lumi) to initiate the image generation process based on the provided text prompt. It's expected to receive a response that includes a job ID or a URL to check the status.
4. If (Check for Image URL): This conditional node checks the response from the image generation API. It likely verifies if an immediate image URL is available or if the process is asynchronous and requires polling.
5. Code (Extract Image URL - True Branch): If an image URL is directly available (the "True" branch of the If node), this Code node would extract and process that URL.
6. Wait (Asynchronous Process - False Branch): If the image generation is an asynchronous process (the "False" branch of the If node), this node introduces a delay, allowing time for the image generation to complete.
7. HTTP Request (Get Image Status/Result): After the wait, this HTTP Request node would poll the external API using the job ID obtained earlier to retrieve the final image URL or status.
8. Sticky Note: A sticky note is present, likely for documentation or to provide instructions within the workflow itself.

Prerequisites/Requirements

To use this workflow, you will need:

• An n8n instance.
• Access to an image generation API (e.g., Replicate, Lumi, or a similar service) that can generate images from text prompts.
• API credentials (API Key, access token, etc.) for your chosen image generation service. These will need to be configured in the "HTTP Request" nodes.

Setup/Usage

1. Import the Workflow: Download the provided JSON and import it into your n8n instance.
2. Configure Credentials:
   • Locate the "HTTP Request" nodes.
   • Edit these nodes to include your API endpoint URLs and authentication details (e.g., API keys in headers or body).
3. Define Prompts:
   • Modify the "Edit Fields (Set)" node to define the text prompt you want to use for image generation. You can also extend this to accept dynamic prompts.
4. Adjust Wait Time:
   • If the image generation process is consistently taking longer or shorter, adjust the duration in the "Wait" node as needed.
5. Execute Workflow: Click the "Execute Workflow" button to run the workflow manually and generate an image.

This workflow provides a robust starting point for integrating AI image generation into your automated processes.