UGC Video Generation via Replicate API Polling - n8n Workflow

• Marketing agencies and content creators needing to scale video content production quickly.


• Developers looking for a reliable n8n template for asynchronous API polling.


• Businesses seeking to turn static product images into dynamic, user-generated content (UGC)-style videos.


• Users familiar with n8n and external AI services like Replicate.

Generating high-fidelity videos using AI models like Wan 2.5 is often an asynchronous process, requiring status checks (polling) until the output is ready. This efficient n8n workflow solves this complexity entirely. It manages the entire process: taking a seed image and detailed prompt, initiating the video creation via the Replicate API, and implementing a robust checking loop. By using this n8n template, you eliminate the need to manually monitor API calls. The workflow handles success, failure, and the necessary waiting periods, returning a clean JSON object containing the final video URL or detailed error messages. This is an essential n8n workflow for scaling AI-driven media creation.

This powerful n8n workflow begins when the 'Manual Trigger' n8n trigger is activated.

1. Configuration: The workflow first runs the 'Set API Token' n8n node to securely define the Replicate API key. Next, the 'Add Seed Image and Prompt' n8n node sets the critical inputs—the input image URL and the motion prompt—required for the AI model.


2. Request Initiation: The 'Create Video' HTTP Request n8n node sends a POST request to the Replicate wan-video/wan-2.5-i2v model endpoint. This initial request starts the video generation and returns a unique prediction ID.


3. Logging: The 'Log Request' n8n node records the prediction ID for monitoring and debugging purposes.


4. Polling Loop Initialization: The workflow immediately executes a short 'Wait 5s' n8n node, followed by the 'Check Status' HTTP Request n8n node, which uses the received prediction ID to check the status on the Replicate platform.


5. Status Check: The 'Is Complete?' IF n8n node evaluates the API response status. If the status is 'succeeded', the workflow proceeds to 'Success Response'.


6. Failure and Polling: If not successful, the 'Has Failed?' IF n8n node checks for a 'failed' status. If failed, it routes to 'Error Response'. If neither succeeded nor failed (meaning it's still running, like 'processing' or 'starting'), the workflow routes to 'Wait 90s' before looping back to 'Check Status', implementing a sophisticated polling mechanism.


7. Final Output: Both 'Success Response' and 'Error Response' n8n nodes format the final result into a clean, structured JSON object, which is then passed to the 'Display Result' n8n node for the user to consume.

To use this video generation n8n workflow, follow these setup steps:

1. Import the n8n Workflow: Copy the provided JSON code and paste it into your n8n instance using the 'New' -> 'Import from JSON' option.


2. Acquire Replicate API Key: Sign up or log in to Replicate and obtain your API token from your account settings.


3. Configure API Credentials:

1. Define Inputs:

1. Execution: Click on the 'Manual Trigger' n8n trigger and execute the full n8n workflow to initiate video generation.

Manual Trigger (n8n trigger): Starts the execution of this specific n8n workflow, ideal for testing and single-run generations.
Set API Token (n8n node): Essential configuration node for storing the Replicate API key, used dynamically by subsequent HTTP Request nodes.
Add Seed Image and Prompt (n8n node): A Set node used to define the core inputs (Seed_image URL and detailed Prompt) that drive the AI video generation.
Create Video (HTTP Request n8n node): Sends the initial generation request to wan-video/wan-2.5-i2v. Key configuration includes setting the Authorization header using the API token and specifying the input image and prompt in the JSON body.
Check Status (HTTP Request n8n node): Polls the Replicate API using prediction ID interpolation: https://api.replicate.com/v1/predictions/{{ $('Create Video').item.json.id }}. It is crucial for retrieving the video output status.
Is Complete? (IF n8n node): Core flow control logic. Checks if $json.status equals 'succeeded' to determine if the video is ready.
Has Failed? (IF n8n node): Checks if $json.status equals 'failed', directing the n8n workflow to error handling if the generation failed.
Wait 90s (n8n node): Implements the necessary delay in the polling loop when the video is still processing, preventing excessive API calls.

• Success Response / Error Response (Set n8n nodes): Formats the final results. The 'Success Response' n8n node specifically extracts the final video URL from the $json.output field.