Settyan Flash V2.0.0 Beta.10 AI Content Generator via Replicate - n8n Workflow

Ideal Users

This comprehensive n8n workflow solves the challenge of integrating long-running asynchronous AI models, specifically the Settyan Flash V2.0.0 Beta.10 model hosted on Replicate. Unlike simple APIs that return results instantly, generation models require polling. This particular n8n workflow handles the entire process: triggering the generation, extracting the unique prediction ID, waiting for a set time, and continuously checking the status until the content is successfully created. Utilizing the core http request n8n node alongside logic nodes, this reusable n8n template ensures reliable execution for your AI generation needs, making it an essential tool for sophisticated automation.

This powerful n8n workflow starts with a manual n8n trigger for immediate execution or testing.

1. Initialization: The 'Set API Key' n8n node securely defines your Replicate API key, which is crucial for authentication across subsequent steps.


2. Creation Request: The 'Create Prediction' n8n node sends an authenticated POST request to Replicate, initiating the Flash V2.0.0 Beta.10 generation process with configured input parameters (prompt, seed, dimensions).


3. ID Extraction: The 'Extract Prediction ID' n8n node, a custom code block, immediately captures the newly created prediction ID and the initial polling URL from the response. This ID is vital for monitoring the job.


4. Polling Loop Initiation: The workflow then enters a polling loop, starting with the 'Wait' n8n node, which pauses execution for 2 seconds to allow the remote job to begin processing.


5. Status Check: The 'Check Prediction Status' n8n node makes an authenticated GET request to the polling URL using the extracted prediction ID to retrieve the current status.


6. Conditional Logic: The 'Check If Complete' n8n node uses an IF statement to determine the next step. If the status is 'succeeded', the job is complete, and the n8n workflow proceeds to the result processing step. If the status is anything else (e.g., 'processing'), the n8n workflow loops back to the 'Wait' n8n node to pause and check the status again.


7. Final Processing: Once complete, the 'Process Result' n8n node structures the final output, extracting the generated content URL and associated metadata (metrics, timestamps), ready for use in subsequent n8n nodes.

To deploy and use this n8n workflow template, follow these steps:

1. Import: Copy the provided JSON code and import it directly into your n8n instance via the 'New' menu -> 'Import from JSON'.


2. API Key Configuration: Locate the 'Set API Key' n8n node. Edit the node and replace the placeholder YOURREPLICATEAPI_KEY with your actual Replicate API key. Ensure you secure this credential appropriately.


3. Input Configuration: Modify the JSON body within the 'Create Prediction' n8n node. Update the "prompt": "prompt value" field with the specific text prompt you wish to use for the Settyan Flash V2.0.0 Beta.10 model. Adjust other parameters like width, height, and seed as needed.


4. Test: Use the manual 'On clicking 'execute'' n8n trigger to test the entire n8n workflow. The final output will be available in the 'Process Result' n8n node after the job completes.

This n8n workflow leverages several key n8n nodes for robust asynchronous API integration:

On clicking 'execute' (Manual Trigger): Serves as the starting n8n trigger point for development and manual runs of the n8n template.
Set API Key (Set): Used to inject the secure replicateapikey into the item data stream, making it accessible to subsequent HTTP Request n8n nodes for authentication.
Create Prediction (HTTP Request): Initiates the AI generation on Replicate. Key configuration includes using the Bearer token authorization linked to the API key set in the previous n8n node, and specifying the target model version (8a5e4f716f0a4acfb122d12d120f9c14a0f0addc05dcb264dea657595f39b9bf).
Extract Prediction ID (Code): A critical custom n8n node that scripts the extraction of the prediction ID (id) and constructs the necessary polling URL (predictionUrl) for the monitoring loop.
Wait (Wait): Manages flow control by pausing the n8n workflow for 2 seconds to prevent aggressive polling and conserve API resources while the model runs.
Check Prediction Status (HTTP Request): Performs the polling action, using the dynamic predictionUrl extracted earlier to check the job status.
Check If Complete (IF): The decision-making n8n node. It compares the response status to 'succeeded'. If true, the n8n workflow completes; otherwise, it returns to the 'Wait' n8n node, effectively creating the polling loop.
Process Result (Code): The final custom n8n node that cleans up and formats the successful output data, isolating the resulting AI-generated URL and metadata.