veo-3-apps/json-prompt-fast

JSON-style prompter for Veo 3 Fast

Public

19 runs

Run veo-3-apps/json-prompt-fast with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field	Type	Default value	Description
subject	string		Describe the main subject (e.g., 'young woman with curly hair', 'elderly man in suit', 'golden retriever dog')
action	string		Describe what the subject is doing (e.g., 'sipping coffee while reading', 'playing guitar on stage', 'walking through falling snow')
dialogue	string		Specific dialogue text (if dialogue_presence is not 'no dialogue')
location	string		Describe the location/setting (e.g., 'cozy coffee shop', 'mountain peak at sunrise', 'busy city intersection')
camera_motion	None	static	Camera movement style
film	None	digital clean	Film grain and texture quality
lighting	None	natural daylight	Lighting type and mood
tone	None	neutral	Overall emotional mood
ambient_audio	None	natural environmental	Background environmental sounds
color_palette	None	natural colors	Color scheme and saturation
image	string		Optional input image to start generating from (ideal: 1280x720)
resolution	None	720p	Video resolution
seed	integer	42	Random seed for reproducible results

{
  "type": "object",
  "title": "Input",
  "required": [
    "subject",
    "action",
    "location"
  ],
  "properties": {
    "film": {
      "enum": [
        "digital clean",
        "iPhone camera",
        "visible 16mm grain",
        "35mm film grain",
        "super 8 grain",
        "Kodak 500T",
        "vintage film stock",
        "high ISO noise"
      ],
      "type": "string",
      "title": "film",
      "description": "Film grain and texture quality",
      "default": "digital clean",
      "x-order": 5
    },
    "seed": {
      "type": "integer",
      "title": "Seed",
      "default": 42,
      "x-order": 12,
      "nullable": true,
      "description": "Random seed for reproducible results"
    },
    "tone": {
      "enum": [
        "gritty",
        "nostalgic",
        "whimsical",
        "intimate",
        "epic",
        "mysterious",
        "cheerful",
        "melancholic",
        "energetic",
        "peaceful",
        "neutral"
      ],
      "type": "string",
      "title": "tone",
      "description": "Overall emotional mood",
      "default": "neutral",
      "x-order": 7
    },
    "image": {
      "type": "string",
      "title": "Image",
      "format": "uri",
      "x-order": 10,
      "nullable": true,
      "description": "Optional input image to start generating from (ideal: 1280x720)"
    },
    "action": {
      "type": "string",
      "title": "Action",
      "x-order": 1,
      "description": "Describe what the subject is doing (e.g., 'sipping coffee while reading', 'playing guitar on stage', 'walking through falling snow')"
    },
    "subject": {
      "type": "string",
      "title": "Subject",
      "x-order": 0,
      "description": "Describe the main subject (e.g., 'young woman with curly hair', 'elderly man in suit', 'golden retriever dog')"
    },
    "dialogue": {
      "type": "string",
      "title": "Dialogue",
      "default": "",
      "x-order": 2,
      "description": "Specific dialogue text (if dialogue_presence is not 'no dialogue')"
    },
    "lighting": {
      "enum": [
        "natural daylight",
        "soft studio lighting",
        "dramatic shadows",
        "neon lighting",
        "candlelight",
        "fluorescent harsh",
        "golden hour warm",
        "blue hour cool",
        "high contrast",
        "low key dark"
      ],
      "type": "string",
      "title": "lighting",
      "description": "Lighting type and mood",
      "default": "natural daylight",
      "x-order": 6
    },
    "location": {
      "type": "string",
      "title": "Location",
      "x-order": 3,
      "description": "Describe the location/setting (e.g., 'cozy coffee shop', 'mountain peak at sunrise', 'busy city intersection')"
    },
    "resolution": {
      "enum": [
        "720p",
        "1080p"
      ],
      "type": "string",
      "title": "resolution",
      "description": "Video resolution",
      "default": "720p",
      "x-order": 11
    },
    "ambient_audio": {
      "enum": [
        "silence",
        "natural environmental",
        "city sounds",
        "nature sounds",
        "indoor ambience",
        "mechanical sounds",
        "crowd noise",
        "wind/weather",
        "echo/reverb",
        "classical orchestral",
        "jazz",
        "rock",
        "electronic",
        "folk acoustic",
        "ambient atmospheric",
        "cinematic score",
        "upbeat pop",
        "dramatic tension"
      ],
      "type": "string",
      "title": "ambient_audio",
      "description": "Background environmental sounds",
      "default": "natural environmental",
      "x-order": 8
    },
    "camera_motion": {
      "enum": [
        "static",
        "fast zoom in",
        "wide shot",
        "slow pan",
        "extreme close-up",
        "fast pan",
        "tilt up",
        "tilt down",
        "dolly in",
        "dolly out",
        "handheld",
        "tracking shot",
        "crane shot",
        "bird's eye view"
      ],
      "type": "string",
      "title": "camera_motion",
      "description": "Camera movement style",
      "default": "static",
      "x-order": 4
    },
    "color_palette": {
      "enum": [
        "natural colors",
        "warm earth tones",
        "cool blues/greens",
        "high contrast B&W",
        "sepia vintage",
        "neon bright",
        "pastel soft",
        "monochromatic",
        "desaturated muted",
        "vibrant saturated"
      ],
      "type": "string",
      "title": "color_palette",
      "description": "Color scheme and saturation",
      "default": "natural colors",
      "x-order": 9
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "string",
  "title": "Output",
  "format": "uri"
}

Example API response

View prediction

'https://replicate.delivery/xezq/77VLgqezbLXuSyNSejkbCtZ8p1cnfztYC3NQ68QjHvBkKQPqA/tmpfdkfwjr1.mp4'