Skip to main content

Generate Videos

Generates videos from text prompts using Google's Veo models.

Common Properties​

  • Name - The custom name of the node.
  • Color - The custom color of the node.
  • Delay Before (sec) - Waits in seconds before executing the node.
  • Delay After (sec) - Waits in seconds after executing node.
  • Continue On Error - Automation will continue regardless of any error. The default value is false.
info

If the ContinueOnError property is true, no error is caught when the project is executed, even if a Catch node is used.

Inputs​

  • Connection Id - The connection ID obtained from the Connect node.
  • Video Prompt - Describe the video you want to generate (subject, action, style, camera positioning).
  • Negative Prompt - Optional: Elements to avoid in the video.
  • Reference Image Path - Optional reference image for image-to-video generation (Veo 2 only).

Options​

  • Model - The Veo model to use for video generation. Options include:
    • Veo 3 (Preview - with Audio)
    • Veo 2 (Stable)
    • Custom Model
  • Custom Model - Custom model name when "Custom Model" is selected.
  • Aspect Ratio - Video aspect ratio (720p at 24fps). Options are:
    • Landscape (16:9)
    • Portrait (9:16)
  • Person Generation - Controls the generation of people in videos. Options are:
    • Allow All
    • Allow Adult
    • Don't Allow
  • Timeout (seconds) - Request timeout in seconds (default: 360 - up to 6 minutes).

Output​

  • Generated Videos - The generated videos with file paths and metadata.

How It Works​

The Generate Videos node creates videos from text prompts using Google's Veo models. When executed, the node:

  1. Validates the provided connection ID and video prompt
  2. Configures the selected model with all specified parameters
  3. Sets up generation parameters including aspect ratio and person generation settings
  4. Handles reference image input for image-to-video generation (Veo 2 only)
  5. Sends a video generation request to the Veo API
  6. Polls for completion status until the operation finishes
  7. Saves the generated videos to a temporary directory
  8. Returns structured information about the generated videos including file paths and metadata

Requirements​

  • A valid Google Gemini API key
  • Connection ID from a successful Connect node execution
  • Valid text prompt describing the desired video
  • Reference image file (for image-to-video generation with Veo 2)

Error Handling​

The node will return specific errors in the following cases:

  • Empty or invalid Connection ID
  • Empty Video Prompt
  • Video prompt too long (maximum 2000 characters)
  • Negative prompt too long (maximum 2000 characters)
  • Reference image file not found
  • Invalid custom model name
  • Veo 3 does not support image-to-video generation
  • API errors from Google's Veo service
  • Video generation operation failures
  • Timeout during video generation

Usage Notes​

  • The maximum length for video prompts and negative prompts is 2000 characters
  • Videos are 8 seconds long at 720p resolution and 24fps
  • Veo 3 has native audio support and SynthID watermarking
  • Veo 2 supports image-to-video generation with reference images
  • Videos are saved to a temporary directory with unique names
  • The default timeout is 360 seconds (6 minutes) which can be adjusted
  • The default aspect ratio is 16:9 (landscape)
  • Person generation settings control content filtering for human subjects
  • The node returns file paths to the generated videos, which can be used by other nodes