video-trim — Traditional AI Model
Video Trim cuts one long source into a list of clips, one per timecoded segment, carrying each segment's title, hook and score forward so later steps can caption and rank without re-deriving anything. CPU.
Details
- CategoryTraditional
- Year-1
- License
Inputs & Outputs
- VideoInputvideo
Source video to cut into clips
- SegmentsInputsegments
Timecoded highlight segments from the Video Analysis node
- ClipsOutputlist:video
One trimmed clip per segment
Parameters
- max_clipsintegerdefault 20range 1–50
Maximum number of clips to produce.
- pre_roll_secintegerdefault 0range 0–10advanced
Seconds of padding added before each clip's start.
- post_roll_secintegerdefault 0range 0–10advanced
Seconds of padding added after each clip's end.
- min_clip_secintegerdefault 0range 0–30advanced
Skip clips shorter than this many seconds (0 = keep all).
Tags
Alternatives in Selection & Extraction
- Color Pick by Class
Extract a segmentation class by name.
- Color Pick by RGB Value
Extract segmentation regions by exact RGB color.
- Image Collect
Gather separately made images into one image list, in port order.
- Image Crop by Class
Crop detected objects by class name.
- Image Crop by Coord
Crop a region from explicit bounding-box coordinates.
- Image Crop Each by Class
Crop every detected object into its own image.
- Image Gate by Text
Pass or block an image based on text match.
- Image Selector
Pick first non-empty image from inputs (fallback).