The source has no audio track or the format is not decoded by ffmpeg. Verify the file has sound; convert to AAC in an MP4 container.

Trends

.ai

les meilleurs modèles d'IA open source

Nœud Load Video (Upload) (VideoHelperSuite) dans ComfyUI

Q: Out of RAM / the browser tab crashes on load

Too many full-size frames loaded at once. Set frame_load_cap, force_size and select_every_nth; use Meta Batch Manager for long clips.

Load Video (Upload) decodes a video file into an IMAGE batch of frames (with frame cap, skip and every-nth options) plus the audio and frame count, the input node for video-to-video and frame-by-frame processing.

Pack de nœuds : ComfyUI-VideoHelperSuite

Catégorie : Vidéo et animation

Cette page n'est pas encore traduite ; elle est affichée en anglais.

Ce que fait Load Video (Upload) (VideoHelperSuite)

The VHS Load Video nodes (Upload and Path variants) open MP4, MOV, WebM, GIF and more with ffmpeg or OpenCV and output the frames as a single IMAGE batch. force_rate resamples to a target fps, force_size or custom_width/height rescale on load, frame_load_cap limits the number of frames (0 for all), skip_first_frames and select_every_nth pick a range. The audio output can be fed straight into Video Combine so the sound survives the round trip.

Typical graphs: Load Video -> ControlNet preprocessor (Depth, Lineart) -> Apply ControlNet with AnimateDiff for stylised video-to-video; Load Video -> ReActor for face swaps; Load Video -> Wan VACE or Wan Fun control nodes for modern restyling; or Load Video -> RIFE interpolation -> Video Combine for smoothing.

Entrées

Nom	Type	Rôle
video	COMBO/upload	The file from ComfyUI/input.
force_rate	FLOAT	Resample to this fps; 0 keeps the original.
force_size / custom_width / custom_height	COMBO / INT	Resize on load.
frame_load_cap	INT	Maximum frames (0 = all). Keep it small to test.
skip_first_frames / select_every_nth	INT	Start offset and frame stride.

Sorties

Nom	Type	Rôle
IMAGE	IMAGE	The frames as a batch.
frame_count	INT	Number of frames loaded.
audio	AUDIO	The soundtrack (when present).
video_info	VHS_VIDEOINFO	fps, duration and sizes for other VHS nodes.

Oubliez l'installation : des workflows ComfyUI préinstallés sur le cloud

BitVector exécute des workflows ComfyUI prêts à l'emploi sur ses propres GPU. Rien à installer, aucun nœud manquant, aucune case rouge. Ouvrez-le sur votre téléphone ou votre portable et générez en une minute.

Essayer BitVector

Comment utiliser Load Video (Upload) (VideoHelperSuite)

Add Load Video (Upload) and upload a short clip.
Set frame_load_cap to 16-32 while testing, force_rate 8-16 to thin the frames.
Set force_size to a model-friendly resolution (512x768 for SD 1.5, 832x480 for Wan).
Process the IMAGE batch (ControlNet, Wan control nodes, ReActor, upscalers).
Connect the result and the audio output to Video Combine with the same frame rate.

Réglages et conseils

Frames x height x width x 3 floats add up fast: 200 frames at 1080p is 7 GB of RAM. Cap and downscale.
select_every_nth 2 halves the work; interpolate back afterwards.
Use the Path variant for files outside the input folder.
Meta Batch Manager processes long videos in chunks through the same graph.

Dépannage de Load Video (Upload) (VideoHelperSuite)

Out of RAM / the browser tab crashes on load

Pourquoi cela arrive

Too many full-size frames loaded at once.

Comment le corriger

Set frame_load_cap, force_size and select_every_nth; use Meta Batch Manager for long clips.

Error: could not open video / no frames

Pourquoi cela arrive

The codec is not supported by the installed ffmpeg or OpenCV (common with HEVC on some builds).

Comment le corriger

Re-encode the clip to h264 MP4 with ffmpeg or HandBrake and upload again.

Audio output is None

Pourquoi cela arrive

The source has no audio track or the format is not decoded by ffmpeg.

Comment le corriger

Verify the file has sound; convert to AAC in an MP4 container.

Lancez ce workflow depuis votre téléphone

Chaque workflow de cette page est préinstallé sur BitVector, modèles et nœuds personnalisés déjà en place. Choisissez-en un, tapez un prompt, c'est fait. Zéro configuration, rien à télécharger.

Essayer BitVector

Questions sur Load Video (Upload) (VideoHelperSuite)

Is there a core Load Video node?

Recent ComfyUI versions include basic Load Video and Save Video nodes; VHS still offers more controls (cap, stride, resize, audio handling).

Can I load an image sequence?

Yes, Load Images (Path) reads a folder of numbered frames as a batch.

Nœuds liés

Video Combine (VideoHelperSuite)

ComfyUI-VideoHelperSuite

Video Combine turns an IMAGE batch of frames into an MP4, WebM, GIF or image sequence at a chosen frame rate, with optional audio, loop count and ping-pong, the standard output node for every video workflow.

Apply ControlNet

ComfyUI core

Apply ControlNet attaches a guide image and a loaded ControlNet to the positive and negative CONDITIONING with strength and start/end percentages, so the sampler follows edges, depth or pose from the guide.

AnimateDiff Loader (Evolved)

ComfyUI-AnimateDiff-Evolved

AnimateDiff Loader adds a motion module to an SD 1.5 or SDXL model so a batch of latents is rendered as coherent animation frames, the classic route to short clips from text with Stable Diffusion.

WanImageToVideo and Wan 2.x video nodes

ComfyUI core

WanImageToVideo builds the conditioning and the empty video latent for a Wan 2.1/2.2 image-to-video render from a start image, a CLIP Vision embedding and the frame count; the surrounding graph uses Load Diffusion Model, Load CLIP, Load VAE and KSampler.

ReActor Fast Face Swap

ComfyUI-ReActor

ReActor swaps a face from a source photo onto the generated picture with InsightFace, with optional restoration (GFPGAN, CodeFormer) and face boosting, for consistent characters without training a LoRA.

Marre de réparer des nœuds ? Laissez faire le cloud

BitVector garde des centaines de workflows ComfyUI installés, à jour et testés sur des GPU cloud rapides. Pas de Python, pas d'erreurs CUDA, pas de limite de VRAM. Depuis n'importe quel navigateur.

Essayer BitVector