chigozienri / posy-motion-extraction

Extracts motion from video

  • Public
  • 187 runs
  • CPU
  • GitHub
  • Paper

Input

*file

Input video

integer

Frames to offset video by for motion extraction. Don't see any motion? Try increasing the number of frames.

Default: 2

boolean

Enable fixed mode. Will ignore frames_offset, and use comparison_frame instead

Default: false

integer

Frame number to compare to for fixed_mode. Note that this is 1-indexed, so the first frame is 1, not 0.

Default: 1

boolean

Enable color delay mode. Will ignore frames_offset and comparison_frame, and use red_offset, green_offset, and blue_offset instead

Default: false

integer

Number of frames to delay red channel for color_delay_mode

Default: 0

integer

Number of frames to delay green channel for color_delay_mode

Default: 5

integer

Number of frames to delay blue channel for color_delay_mode

Default: 10

Output

Generated in

This output was created using a different version of the model, chigozienri/posy-motion-extraction:8499ec8f.

Run time and cost

This model costs approximately $0.0052 to run on Replicate, or 192 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on CPU hardware. Predictions typically complete within 52 seconds. The predict time for this model varies significantly based on the inputs.