Load Video FFmpeg (Upload) 🎥🅥🅗🅢

Video Helper Suite 🎥🅥🅗🅢

VHS_LoadVideoFFmpeg

Load Video FFmpeg 🎥🅥🅗🅢<div style="font-size: 0.8em"><div id=VHS_shortdesc>Loads a video from the input folder using ffmpeg instead of opencv</div></div><div style="font-size: 0.8em">Provides faster execution speed, transparency support, and allows specifying start time in seconds</div><div style="font-size: 0.8em"><div vhs_title="Inputs" style="display: flex; font-size: 0.8em" class="VHS_collapse"><div style="color: #AAA; height: 1.5em;">[<span style="font-family: monospace">-</span>]</div><div style="width: 100%">Inputs: <div vhs_title="meta_batch" style="display: flex; font-size: 1em" class="VHS_collapse"><div style="color: #AAA; height: 1.5em;">[<span style="font-family: monospace">-</span>]</div><div style="width: 100%">meta_batch: (optional) Connect to a Meta Batch manager to divide extremely long sequences into sub batches. See the documentation for Meta Batch Manager</div></div><div vhs_title="vae" style="display: flex; font-size: 1em" class="VHS_collapse"><div style="color: #AAA; height: 1.5em;">[<span style="font-family: monospace">-</span>]</div><div style="width: 100%">vae: (optional) If provided the node will output latents instead of images. This drastically reduces the required RAM (not VRAM) when working with long (100+ frames) sequences<div style="font-size: 1em">Using this is strongly encouraged unless connecting to a node that requires a blue image connection such as Apply Controllnet</div></div></div></div></div><div vhs_title="Outputs" style="display: flex; font-size: 0.8em" class="VHS_collapse"><div style="color: #AAA; height: 1.5em;">[<span style="font-family: monospace">-</span>]</div><div style="width: 100%">Outputs: <div vhs_title="IMAGE" style="display: flex; font-size: 1em" class="VHS_collapse"><div style="color: #AAA; height: 1.5em;">[<span style="font-family: monospace">-</span>]</div><div style="width: 100%">IMAGE: The loaded images</div></div><div vhs_title="mask" style="display: flex; font-size: 1em" class="VHS_collapse"><div style="color: #AAA; height: 1.5em;">[<span style="font-family: monospace">-</span>]</div><div style="width: 100%">mask: Transparency data from the loaded video</div></div><div vhs_title="audio" style="display: flex; font-size: 1em" class="VHS_collapse"><div style="color: #AAA; height: 1.5em;">[<span style="font-family: monospace">-</span>]</div><div style="width: 100%">audio: The audio from the loaded video</div></div><div vhs_title="video_info" style="display: flex; font-size: 1em" class="VHS_collapse"><div style="color: #AAA; height: 1.5em;">[<span style="font-family: monospace">-</span>]</div><div style="width: 100%">video_info: Exposes additional info about the video such as the source frame rate, or the total length</div></div><div vhs_title="LATENT" style="display: flex; font-size: 1em" class="VHS_collapse"><div style="color: #AAA; height: 1.5em;">[<span style="font-family: monospace">-</span>]</div><div style="width: 100%">LATENT: The loaded images pre-converted to latents. Only available when a vae is connected</div></div></div></div><div vhs_title="Widgets" style="display: flex; font-size: 0.8em" class="VHS_collapse"><div style="color: #AAA; height: 1.5em;">[<span style="font-family: monospace">-</span>]</div><div style="width: 100%">Widgets: <div vhs_title="video" style="display: flex; font-size: 1em" class="VHS_collapse"><div style="color: #AAA; height: 1.5em;">[<span style="font-family: monospace">-</span>]</div><div style="width: 100%">video: The video file to be loaded. Lists all files with a video extension in the ComfyUI/Input folder</div></div><div vhs_title="force_rate" style="display: flex; font-size: 1em" class="VHS_collapse"><div style="color: #AAA; height: 1.5em;">[<span style="font-family: monospace">-</span>]</div><div style="width: 100%">force_rate: Drops or duplicates frames so that the produced output has the target frame rate. Many motion models are trained on videos of a specific frame rate and will give better results if input matches that frame rate. If set to 0, all frames are returned. May give unusual results with inputs that have a variable frame rate like animated gifs. Reducing this value can also greatly reduce the execution time and memory requirements.</div></div><div vhs_title="force_size" style="display: flex; font-size: 1em" class="VHS_collapse"><div style="color: #AAA; height: 1.5em;">[<span style="font-family: monospace">-</span>]</div><div style="width: 100%">force_size: Previously was used to provide suggested resolutions. Instead, custom_width and custom_height can be disabled by setting to 0.</div></div><div vhs_title="custom_width" style="display: flex; font-size: 1em" class="VHS_collapse"><div style="color: #AAA; height: 1.5em;">[<span style="font-family: monospace">-</span>]</div><div style="width: 100%">custom_width: Allows for an arbitrary width to be entered, cropping to maintain aspect ratio if both are set</div></div><div vhs_title="custom_height" style="display: flex; font-size: 1em" class="VHS_collapse"><div style="color: #AAA; height: 1.5em;">[<span style="font-family: monospace">-</span>]</div><div style="width: 100%">custom_height: Allows for an arbitrary height to be entered, cropping to maintain aspect ratio if both are set</div></div><div vhs_title="frame_load_cap" style="display: flex; font-size: 1em" class="VHS_collapse"><div style="color: #AAA; height: 1.5em;">[<span style="font-family: monospace">-</span>]</div><div style="width: 100%">frame_load_cap: The maximum number of frames to load. If 0, all frames are loaded.</div></div><div vhs_title="start_time" style="display: flex; font-size: 1em" class="VHS_collapse"><div style="color: #AAA; height: 1.5em;">[<span style="font-family: monospace">-</span>]</div><div style="width: 100%">start_time: A timestamp, in seconds from the start of the video, to start loading frames from. </div></div><div vhs_title="format" style="display: flex; font-size: 1em" class="VHS_collapse"><div style="color: #AAA; height: 1.5em;">[<span style="font-family: monospace">-</span>]</div><div style="width: 100%">format: Updates other widgets so that only values supported by the given format can be entered and provides recommended defaults.</div></div><div vhs_title="choose video to upload" style="display: flex; font-size: 1em" class="VHS_collapse"><div style="color: #AAA; height: 1.5em;">[<span style="font-family: monospace">-</span>]</div><div style="width: 100%">choose video to upload: An upload button is provided to upload local files to the input folder</div></div><div vhs_title="videopreview" style="display: flex; font-size: 1em" class="VHS_collapse"><div style="color: #AAA; height: 1.5em;">[<span style="font-family: monospace">-</span>]</div><div style="width: 100%">videopreview: Displays a preview for the selected video input. If advanced previews is enabled, this preview will reflect the frame_load_cap, force_rate, skip_first_frames, and select_every_nth values chosen. If the video has audio, it will also be previewed when moused over. Additional preview options can be accessed with right click.</div></div></div></div></div>

Example

JSON Example

{
  "class_type": "VHS_LoadVideoFFmpeg",
  "inputs": {
    "video": "https://example.com/input-video.mp4",
    "force_rate": 0,
    "custom_width": 0,
    "custom_height": 0,
    "frame_load_cap": 0,
    "start_time": 0
  }
}

This example shows required inputs only. Connection values like ["node_id", 0] should reference actual node IDs from your workflow.

Inputs

Name	Type	Status	Constraints	Default
`video`	ENUM 0 options URL: Video	required	-	`-`
`force_rate`	`FLOAT`	required	min: 0, max: 60, step: 1	`0`
`custom_width`	`INT`	required	min: 0, max: 8192	`0`
`custom_height`	`INT`	required	min: 0, max: 8192	`0`
`frame_load_cap`	`INT`	required	min: 0, max: 9.01e+15, step: 1	`0`
`start_time`	`FLOAT`	required	min: 0, max: 9.01e+15, step: 0.001	`0`
`meta_batch`	VHS_BatchManager	optional	-	`-`
`vae`	VAE	optional	-	`-`
`format`	ENUM 7 options `None` `AnimateDiff` `Mochi` `LTXV` `Hunyuan` `Cosmos` `Wan`	optional	-	`"AnimateDiff"`

Outputs

Index	Name	Type	Is List	Connection Reference
`0`	`IMAGE`	IMAGE	No	`["{node_id}", 0]`
`1`	`mask`	MASK	No	`["{node_id}", 1]`
`2`	`audio`	AUDIO	No	`["{node_id}", 2]`
`3`	`video_info`	VHS_VIDEOINFO	No	`["{node_id}", 3]`

How to connect to these outputs

To connect another node's input to an output from this node, use the connection reference format:

["node_id", output_index]

Where node_id is the ID of this VHS_LoadVideoFFmpeg node in your workflow, and output_index is the index from the table above.

Example

If this node has ID "5" in your workflow:

IMAGE (IMAGE): ["5", 0]
mask (MASK): ["5", 1]
audio (AUDIO): ["5", 2]

Package: comfyui-videohelpersuite

Was this page helpful?