Video

XceptionNet Deepfake Detector

Detects manipulated facial regions using a CNN trained on the FaceForensics++ dataset.

340K runs

Note: This playground provides simulated output to showcase functionality. No input data is processed or stored on our servers. Use this demo to explore the feature extractor's capabilities before integrating it into your application.

Input

File URL string

Enter a URL to a video file

Upload video

Drag and drop a video file here, or click to browse

Select File

# model_variant string

Choose the variant of Xception to use.. Default: xception-small

# detection_threshold number

Probability threshold for marking a face as fake.. Default: 0.5

Output

{
  "face_boxes": [
    {
      "x": 0.22,
      "y": 0.33,
      "width": 0.15,
      "height": 0.18
    }
  ],
  "manipulation_scores": [
    0.78
  ],
  "embeddings": [
    [
      0.123,
      -0.045,
      "...",
      0.089
    ]
  ],
  "model": "xception-small"
}