Video

Real Person Classification

Analyzes video frames using a CLIP model (ViT-L-14) to generate a 'visual realness' score, checking for stylistic coherence and human-like appearance.

5K 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

# detection_threshold number

Probability threshold for marking a person as visually real.. Default: 0.6

Output

{
  "realness_score": 0.85,
  "is_real": true,
  "model": "clip-vit-l-14"
}