← All models
Scene Finder
scene-finder
Visionby infery
Search any video with a text prompt - Scene Finder locates the matching moments and returns their time segments and extracted frames.
Details
- Accepts
- video
Pricing
- Price
- 0.525 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| promptrequired | string | Text description of the event or scene to find in the video. |
| video_urlrequired | string | URL of the video to search through. |
| frame_selection | stringenum: mid, start, end, all | Which frame(s) to extract from each detected segment. 'mid' returns the midpoint frame, 'start' the first frame, 'end' the last frame, 'all' returns start + mid + end. |
| frames_per_second | integer | Frames per second to sample from the video. Higher values give more precision but use more memory. |
Output
| Field | Type | Description |
|---|---|---|
| images | array | Extracted frames from each detected segment based on frame_selection. |
| segments | array | Detected event time segments. |