Regen Video Upscaler

Enhance and upscale your videos up to 4K with our powerful AI video upscaler.

The endpoint is available at https://api.regen.video/v1/upscale.

Examples

curl -X POST https://api.regen.video/v1/upscale \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "file=@path/to/your/video.mp4" \
  -F "target_fps=60" \
  -F "engine=regen-4x"

async function upscale() {
  const url = 'https://api.regen.video/v1/upscale';
  const formData = new FormData();
  formData.append('file', new File([''], 'video.mp4', { type: 'video/mp4' }));
  formData.append('target_fps', '60'); // Optional: specify target framerate
  formData.append('engine', 'regen-4x'); // Optional: specify engine
 
  try {
    const response = await fetch(url, {
      method: 'POST',
      headers: {
        'Authorization': 'Bearer YOUR_API_KEY'
      },
      body: formData
    });
 
    if (!response.ok) {
      throw new Error(`HTTP error! status: ${response.status}`);
    }
 
    const result = await response.json();
    console.log('Upscale job created:', result);
  } catch (error) {
    console.error('Error creating upscale job:', error.message);
  }
}
 
upscale();

import requests
 
def upscale():
    url = 'https://api.regen.video/v1/upscale'
    headers = {
        'Authorization': 'Bearer YOUR_API_KEY'
    }
    files = {
        'file': ('video.mp4', open('path/to/your/video.mp4', 'rb'), 'video/mp4')
    }
    data = {
        'target_fps': 60,  # Optional: specify target framerate
        'engine': 'regen-4x'  # Optional: specify engine
    }
 
    try:
        response = requests.post(url, headers=headers, files=files, data=data)
        response.raise_for_status()
        print('Upscale job created:', response.json())
    except requests.exceptions.RequestException as e:
        print('Error creating upscale job:', e)
 
upscale()

Make sure to replace YOUR_API_KEY with your actual API key, and provide the correct path to your video file.

Parameters

Engines

The API offers two upscaling engines:

• regen-4x-lite (default): A fast and cost-effective upscaler, which is suitable for most use cases.
• regen-4x: A premium upscaler that can handle more complex scenes.

Both engines provide 4x upscaling (meaning the output video will have 4 times the resolution of the input video in each dimension), but with different quality-cost tradeoffs.

Response

The API will respond with a JSON object containing information about the upscaling process, including a unique identifier for the render job.

{
  "render": {
    "id": "abc123",
    "userId": "xyz789",
    "status": "queued",
    "createdAt": "2023-04-01T12:34:56.789Z",
    "queuePosition": 8
  }
}

Response Properties

render.status can have the following values:

• queued: The job is queued for processing
• pending: The job is being initialized for processing
• processing: The job is being processed
• completed: The job is completed
• failed: The job failed

Errors

If an error occurs, the API will respond with a JSON object containing an array of error messages:

{
  "errors": [
    {
      "message": "File not found"
    }
  ]
}

Common Errors

• 404 Not Found: The specified file does not exist in your user’s upload directory.
• 500 Internal Server Error: An unexpected error occurred while processing the request.

Notes

• The upscale factor is fixed at 4x, which means the output video will have 4 times the resolution of the input video in each dimension.

• The cost of the upscale operation is calculated based on the output gigapixels (width * height * duration * framerate) and an engine multiplier:

  • regen-4x-lite: 1x cost multiplier (default)
  • regen-4x: 2x cost multiplier

• After successful submission, your job will be queued for processing. You can check the status of your render job using the returned render.id.

• Target framerate must not be greater than 120 FPS.