AI Video Generator workflow blueprint

Inputs for the AI Video Generator workflow

Provide the following information when starting this workflow. Required inputs are validated before the first workflow stage runs.

• Prompt

  Required

  Description of the video to generate (idea, story beat, or shot list)

  Type: String

• Target Duration

  Optional

  Target length in seconds (default 8; values are clamped to 4-144). Durations above 8 require background/async execution.

  Type: Number

• Storage Id

  Optional

  Workspace storage to write outputs (default: 'default')

  Type: String

• Aspect Ratio

  Optional

  16:9 (landscape) or 9:16 (portrait). Default 16:9.

  Type: String

• Resolution

  Optional

  720p or 1080p. Default 720p.

  Type: String

• Style

  Optional

  NanoBanana keyframe style: realistic, anime, 3d, pixel-art. Default realistic.

  Type: String

• Reference Image Path

  Optional

  Optional storage path to an existing character image. When set, the same person is used in every scene; otherwise a fresh avatar is generated.

  Type: String

Input template

This request shape is generated from the blueprint's input schema. Angle-bracket values are placeholders; defaults and examples appear only when the source blueprint defines them.

{
  "prompt": "<required string>",
  "target_duration": "<optional number>",
  "storage_id": "<optional string>",
  "aspect_ratio": "<optional string>",
  "resolution": "<optional string>",
  "style": "<optional string>",
  "reference_image_path": "<optional string>"
}

How the AI Video Generator AI workflow works

This content & writing blueprint uses a sequential workflow with 1 agent, 1 function, and 0 MCP servers. Open it in GraphN to customize the resources, inputs, and workflow behavior for your use case.

1. 1

   Plan

   Agent using Scene Director

2. 2

   Generate

   Function using Generate Video

Blueprint resources and prerequisites

These are the actual agents, functions, and MCP servers declared by the blueprint. If an MCP server connects to an external system, configure the required connection and credentials in your GraphN workspace before running the workflow.

Workflow output contract

The completed workflow makes the following output available to downstream steps, applications, or API clients: