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
videoSTRINGVideo filename from the input directory.
force_rateFLOAToptionalForce a specific frame rate.
force_sizeSTRINGoptionalForce specific dimensions.
frame_load_capINToptionalMaximum frames to load.
skip_first_framesINToptionalFrames to skip at start.
select_every_nthINToptionalFrame selection interval.
Outputs
IMAGEIMAGEBatch of extracted video frames.
frame_countINTNumber 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.