VideoLimited CaptureComfyUI-VideoHelperSuite

Load Video (VHS)

class_type: VHS_LoadVideo

Source repo

Loads a video file and extracts individual frames as an image batch for processing in ComfyUI. Part of the VideoHelperSuite extension, enabling video-to-video workflows.

What It Does

VHS_LoadVideo reads a video file from the input directory and splits it into individual frames that can be processed through the ComfyUI pipeline. This enables video-to-video workflows where each frame is transformed by the diffusion model.

The node supports frame selection (start frame, end frame, frame skip) to process subsets of the video. Like LoadImage, it records only the filename—the actual video content is not preserved in the output metadata.

Inputs

videoSTRING

Video filename from the input directory.

force_rateFLOAToptional

Force a specific frame rate.

force_sizeSTRINGoptional

Force specific dimensions.

frame_load_capINToptional

Maximum frames to load.

skip_first_framesINToptional

Frames to skip at start.

select_every_nthINToptional

Frame selection interval.

Outputs

IMAGEIMAGE

Batch of extracted video frames.

frame_countINT

Number of frames extracted.

What Numonic Captures

  • Source video filename
  • Frame selection parameters

Known Gaps

  • Source video content hash
  • Source video duration and original frame rate
  • Source video codec and quality

Extension Pack: ComfyUI-VideoHelperSuite

This node is not built into ComfyUI. It requires the ComfyUI-VideoHelperSuite custom node package. Numonic detects and extracts metadata from this extension when it appears in workflows.

Related Nodes

Capture ComfyUI metadata automatically

Numonic extracts workflow metadata from every ComfyUI generation — models, samplers, seeds, prompts, and custom nodes. Track provenance, maintain compliance, and never lose a workflow.