Generate AI videos from text or images with Sora 2/Pro & GPT-5 enhancement
Content & publishing workflow for n8n with 13 active steps. Starts with n8n Form Trigger. Uses OpenAI. Integrations include OpenAI.
What it does
13 active nodes · Starts with n8n Form Trigger.
Steps in the template include:
- Video Input Form (n8n Form Trigger)
- Prompt Refiner (Basic LLM Chain)
- JSON Output Parser (Structured Output Parser)
- Temp Image Upload (HTTP Request)
Nodes and integrations
- n8n Form Trigger
- Basic LLM Chain
- Structured Output Parser
- HTTP Request ×5
- Switch ×2
- Wait
- n8n Form
- OpenAI Chat Model
See the author’s step names
- Video Input Form (n8n Form Trigger)
- Prompt Refiner (Basic LLM Chain)
- JSON Output Parser (Structured Output Parser)
- Temp Image Upload (HTTP Request)
- Text-to-Video Call (HTTP Request)
- Input Mode Router (Switch)
- Image-to-Video Call (HTTP Request)
- Wait 60 Seconds (Wait)
- Status Check (HTTP Request)
- Status Router (Switch)
- Retrieve Video (HTTP Request)
- Video Redirect (n8n Form) — completion
- Refiner Model (OpenAI Chat Model)
Accounts and credentials
- OpenAI access
Credential types in the graph: httpHeaderAuth, openAiApi
Check the HTTP request steps for any additional service accounts or API keys.
AI models and swaps
OpenAI · Chat
gpt-5 in Refiner Model. Potentially swappable with a compatible n8n chat model node. Match structured output before testing.
Inputs and setup options
- Form field: Prompt (required)
- Form field: Aspect Ratio (required)
- Form field: Model (required)
- Form field: Lenght (required)
- Form field: Image
Resource information
- Credit basis
- Author listed by n8n
- Pricing
- Template access shown on n8n
- License
- Not specified
- Last record update
- Nov 5, 2026