Generate UGC product video ads from a reference image with OpenAI and Kie.ai
Ready for 3.0What this workflow does
This AI workflow has 27 nodes and runs manually, when you click “Execute workflow”. Along the way it connects OpenAI, OpenAI Chat Model, Box and Google Drive and 1 more. It also calls api.kie.ai over HTTP.
How it runs
Trigger: Manually, when you click “Execute workflow”.
- Video script (Edit Fields (Set)): sets 1 field: Script
- Setup (Image & Video settings) (Edit Fields (Set)): sets 6 fields: googledrive link reference image, how many videos?, dialouge…
- Analyze image (OpenAI): analyze (image)
- Generate UGC prompts with AI agent (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 1 tool (Validate prompt generation); output parser: Structured Output Parser
- Process image prompts (Split Out): splits a list into separate items
- Call image generation API (HTTP Request): calls api.kie.ai (POST)
- Wait: pauses before continuing
- Retrieve generated image (HTTP Request): calls api.kie.ai
- Check if image is ready (If): checks a condition and branches into true / false
- Call video generation API (HTTP Request): calls api.kie.ai (POST)
…plus 13 more steps. See the full node list below.
Services it uses
HTTP calls to: api.kie.ai
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (16)
- Manual Trigger
n8n-nodes-base.manualTrigger - OpenAI
@n8n/n8n-nodes-langchain.openAi - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Box
n8n-nodes-base.box - Google Drive
n8n-nodes-base.googleDrive - Think Tool
@n8n/n8n-nodes-langchain.toolThink - Edit Fields (Set)
n8n-nodes-base.set - AI Agent
@n8n/n8n-nodes-langchain.agent - Split Out
n8n-nodes-base.splitOut - HTTP Request
n8n-nodes-base.httpRequest - Wait
n8n-nodes-base.wait - If
n8n-nodes-base.if - Aggregate
n8n-nodes-base.aggregate - Google Sheets
n8n-nodes-base.googleSheets - Switch
n8n-nodes-base.switch
From the author
How it works - Analyzes a reference product image using AI vision to extract brand elements, colors, and design - Generates UGC-style prompts for image and video creation based on your specifications - Calls external APIs to generate product images and videos…