cheribc/continue-video | API reference

Extracts a video frame, uses Claude to enhance prompts, and continues the clip with similar motion, style, and audio across video models like Seedance, Hailuo, Kling, and Veo.

Public

196 runs

Playground API Examples README

Run cheribc/continue-video 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_video	string		None
frame_time	number	5	Time in seconds to extract frame from (e.g., 5.0 for 5 seconds into video)
video_model	None	seedance-pro	Video generation model to use (veo-3 and veo-3-fast generate audio)
base_prompt	string		Base description for the video (leave empty for AI-generated prompt)
camera_motion	None	dynamic	Camera movement style
video_style	None	cinematic	Video style and tone
video_duration	None	5	Duration of generated video in seconds
resolution	None	1080p	Video resolution

{
  "type": "object",
  "title": "Input",
  "required": [
    "input_video"
  ],
  "properties": {
    "frame_time": {
      "type": "number",
      "title": "Frame Time",
      "default": 5,
      "x-order": 1,
      "description": "Time in seconds to extract frame from (e.g., 5.0 for 5 seconds into video)"
    },
    "resolution": {
      "enum": [
        "480p",
        "720p",
        "768p",
        "1080p"
      ],
      "type": "string",
      "title": "resolution",
      "description": "Video resolution",
      "default": "1080p",
      "x-order": 7
    },
    "base_prompt": {
      "type": "string",
      "title": "Base Prompt",
      "default": "",
      "x-order": 3,
      "description": "Base description for the video (leave empty for AI-generated prompt)"
    },
    "input_video": {
      "type": "string",
      "title": "Input Video",
      "format": "uri",
      "x-order": 0
    },
    "video_model": {
      "enum": [
        "seedance-pro",
        "hailuo",
        "kling-v2.1",
        "veo-3-fast",
        "veo-3"
      ],
      "type": "string",
      "title": "video_model",
      "description": "Video generation model to use (veo-3 and veo-3-fast generate audio)",
      "default": "seedance-pro",
      "x-order": 2
    },
    "video_style": {
      "enum": [
        "cinematic",
        "documentary",
        "artistic",
        "commercial",
        "realistic",
        "stylized"
      ],
      "type": "string",
      "title": "video_style",
      "description": "Video style and tone",
      "default": "cinematic",
      "x-order": 5
    },
    "camera_motion": {
      "enum": [
        "static",
        "pan",
        "zoom_in",
        "zoom_out",
        "tracking",
        "dynamic"
      ],
      "type": "string",
      "title": "camera_motion",
      "description": "Camera movement style",
      "default": "dynamic",
      "x-order": 4
    },
    "video_duration": {
      "enum": [
        5,
        6,
        10
      ],
      "type": "integer",
      "title": "video_duration",
      "description": "Duration of generated video in seconds",
      "default": 5,
      "x-order": 6
    }
  }
}

Output schema

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

Schema

{
  "type": "object",
  "title": "Output",
  "required": [
    "extracted_frame",
    "generated_video",
    "prompt_used",
    "camera_motion",
    "style_applied"
  ],
  "properties": {
    "prompt_used": {
      "type": "string",
      "title": "Prompt Used"
    },
    "camera_motion": {
      "type": "string",
      "title": "Camera Motion"
    },
    "style_applied": {
      "type": "string",
      "title": "Style Applied"
    },
    "extracted_frame": {
      "type": "string",
      "title": "Extracted Frame",
      "format": "uri"
    },
    "generated_video": {
      "type": "string",
      "title": "Generated Video",
      "format": "uri"
    }
  }
}

Example API response

View prediction

{'camera_motion': 'pan',
 'extracted_frame': 'https://replicate.delivery/xezq/AZjfK1VcYxW7ByNqKU0rtnwDbNaw2EyLgUJs5yYfmZft7leUB/extracted_frame_5.0.jpg',
 'generated_video': 'https://replicate.delivery/xezq/X9SVdhPFoj5HDh6x4fAOieBM1g58UKltXGs6zv0NfoDs7leUB/tmpcf6uw1bs.mp4',
 'prompt_used': '[Smooth horizontal camera pan] A lone astronaut in a '
                'weathered spacesuit sits contemplatively on the rocky '
                'shoreline of an alien world, gazing at the dramatic cosmic '
                'sky filled with swirling nebulae and a distant moon. The '
                'camera slowly pans right across the desolate landscape, '
                'revealing more of the reflective water surface that mirrors '
                'the brilliant orange and amber light from the towering space '
                'structure in the distance. Steam and atmospheric particles '
                'drift through the air as the astronaut slowly turns their '
                'helmeted head to follow the horizon. The cinematic lighting '
                'emphasizes the contrast between the dark silhouetted figure '
                'and the glowing celestial phenomena above. Gentle lapping of '
                'alien waters against the shore, distant mechanical hums from '
                'the space installation, and the soft whisper of atmospheric '
                "wind through the astronaut's equipment create an otherworldly "
                'soundscape of isolation and wonder.',
 'style_applied': 'cinematic'}