Replicate Digitalhera Heranathalie Image Generation Poller - n8n Workflow

AI artists and developers needing automated generation pipelines.
Users looking for advanced n8n workflow polling examples.
Engineers integrating digital image generation into larger applications or web services.
Anyone seeking reusable n8n templates for asynchronous API interaction.

This sophisticated n8n workflow provides a reliable method for leveraging external AI models that require asynchronous processing, specifically the Digitalhera/Heranathalie model on Replicate. Since complex image generation often takes time, the initial request returns a pending status. This n8n node architecture addresses this challenge by implementing a precise polling loop. This solution ensures your main n8n workflow execution doesn't time out while waiting, offering a robust and reusable component for any time-intensive external API call. Using these specialized n8n templates means you can easily customize the image generation prompt and model parameters directly within the n8n node settings.

The execution of this n8n workflow begins with the Manual Trigger n8n trigger, allowing immediate testing. The first critical step is the "Set API Key" n8n node, which securely passes your Replicate credentials. Next, the "Create Prediction" HTTP Request n8n node sends the initial image generation request to the Replicate API, providing the required prompt and model parameters. The response, containing the prediction ID and status, is immediately processed by the "Extract Prediction ID" code n8n node. This ID is essential for monitoring the task status. The core logic then enters a polling loop, starting with a 2-second "Wait" n8n node to manage request frequency and prevent hitting API rate limits. The "Check Prediction Status" HTTP Request n8n node continuously queries Replicate using the prediction URL derived from the ID. The "Check If Complete" n8n node evaluates the status; if the status is "succeeded," the n8n workflow exits the loop and the "Process Result" n8n node extracts the final generated image URL and metadata. Otherwise, the n8n workflow loops back to the "Wait" n8n node, continuing the polling cycle until completion. This asynchronous design makes this a highly effective n8n workflow.

1. Import: Copy the provided JSON code and import it into your self-hosted or cloud n8n instance using the 'New' menu -> 'Import from JSON'.


2. API Key Setup: Locate the "Set API Key" n8n node. Replace the placeholder YOURREPLICATEAPI_KEY with your actual Replicate API key.


3. Prompt Configuration: Locate the "Create Prediction" HTTP Request n8n node. Edit the JSON body to customize the prompt value and adjust input parameters like seed, width, and height as needed for the Digitalhera Heranathalie model.


4. Activation: Ensure all credentials are set up correctly. Activate the n8n workflow and execute the Manual Trigger n8n trigger to begin image generation.

On clicking 'execute' (Manual Trigger): Serves as the starting n8n trigger point for this asynchronous n8n workflow, ideal for testing and manual initiation.
Set API Key (Set n8n node): Defines the replicateapikey variable. Function: Ensures the API key is dynamically available as a Bearer token header for authentication in the HTTP Request n8n node steps.
Create Prediction (HTTP Request n8n node): Initiates the image generation request to the Replicate API. Key Configuration: Uses POST method, Generic HTTP Header authentication, and specifies the digitalhera/heranathalie model version.
Extract Prediction ID (Code n8n node): A critical flow control n8n node. Function: Parses the initial prediction response to obtain the unique predictionId and constructs the polling URL necessary for subsequent status checks.
Wait (Wait n8n node): Implements a fixed 2-second delay between status checks, preventing resource overuse and handling API rate limits during the polling phase of the n8n workflow.
Check Prediction Status (HTTP Request n8n node): This core polling n8n node repeatedly queries Replicate using the derived prediction URL.
Check If Complete (If n8n node): Determines the next step in the n8n workflow. Key Configuration: Checks if the incoming status is exactly equal to "succeeded." If true, the flow progresses; otherwise, it loops back to the Wait n8n node.
Process Result (Code n8n node): The final processing n8n node. Function: Cleans up and extracts essential data from the successful response, including the final image URL (output) and generation metrics.