rinesh/not-real-konsistent

Generate believable consistent character videos

Public

139 runs

Run rinesh/not-real-konsistent 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
input_image	string		Optional: Upload a reference image to maintain character/object consistency in the generated video. The model will preserve the identity and features from this image.
prompt	string		Describe the scene or action you want. If using a reference image, the model will maintain character consistency while applying your description.
duration	None	5	Length of the generated video
resolution	None	1080p	Video quality - choose higher for better detail
aspect_ratio	None	16:9	Video format - use 16:9 for landscape, 9:16 for mobile/portrait

{
  "type": "object",
  "title": "Input",
  "required": [
    "prompt"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "x-order": 1,
      "description": "Describe the scene or action you want. If using a reference image, the model will maintain character consistency while applying your description."
    },
    "duration": {
      "enum": [
        5,
        10
      ],
      "type": "integer",
      "title": "duration",
      "description": "Length of the generated video",
      "default": 5,
      "x-order": 2
    },
    "resolution": {
      "enum": [
        "480p",
        "1080p"
      ],
      "type": "string",
      "title": "resolution",
      "description": "Video quality - choose higher for better detail",
      "default": "1080p",
      "x-order": 3
    },
    "input_image": {
      "type": "string",
      "title": "Input Image",
      "format": "uri",
      "x-order": 0,
      "description": "Optional: Upload a reference image to maintain character/object consistency in the generated video. The model will preserve the identity and features from this image."
    },
    "aspect_ratio": {
      "enum": [
        "1:1",
        "16:9",
        "4:3",
        "3:4",
        "9:16",
        "21:9"
      ],
      "type": "string",
      "title": "aspect_ratio",
      "description": "Video format - use 16:9 for landscape, 9:16 for mobile/portrait",
      "default": "16:9",
      "x-order": 4
    }
  }
}

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/RZMRf7syNp0rDSWSPdBRzOrcPXyPzOdPZvVc3YqcYXOrm7hKA/video_169.mp4'