Model
Trends
.ai
Model
Trends
.ai
les meilleurs modèles d'IA open source

Nœud Video Combine (VideoHelperSuite) dans ComfyUI

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.
Pack de nœuds : ComfyUI-VideoHelperSuite
Catégorie : Vidéo et animation
Cette page n'est pas encore traduite ; elle est affichée en anglais.

Ce que fait Video Combine (VideoHelperSuite)

VideoHelperSuite (VHS) by Kosinkadink provides the loading and saving nodes that video workflows share. Video Combine takes the decoded frames, a frame_rate and a format (image/gif, image/webp, video/h264-mp4, video/h265-mp4, video/webm, video/ProRes and more via ffmpeg), writes the file to the output folder and shows a playable preview in the node. Options add audio from Load Audio, set a CRF quality, pingpong (play forwards then backwards) and save_output off for temporary previews.
The workflow JSON is embedded in the file metadata when the format allows it, so an MP4 can be dragged back into ComfyUI like a PNG. Load Video (Upload) is the matching input node: it decodes a video into frames with frame_load_cap, skip_first_frames and select_every_nth, and can downscale on load.

Entrées

Nom
Type
Rôle
images
IMAGE
The frames in order.
frame_rate
FLOAT
Frames per second (8 for AnimateDiff, 16 for Wan, 24 for Hunyuan/LTX).
loop_count
INT
0 for infinite GIF loop.
filename_prefix
STRING
Output name prefix.
format
COMBO
image/gif, image/webp, video/h264-mp4, video/webm and others.
pingpong / save_output
BOOLEAN
Back-and-forth playback; save to output or temp.
audio
AUDIO
Optional soundtrack.
crf / pix_fmt (per format)
INT / COMBO
Quality (lower is better, 19-23) and pixel format.

Sorties

Nom
Type
Rôle
Filenames
VHS_FILENAMES
Paths of the written files for further nodes.
AD
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.

Comment utiliser Video Combine (VideoHelperSuite)

  1. Install ComfyUI-VideoHelperSuite from Manager; ffmpeg is bundled or found on PATH.
  2. Connect the IMAGE batch from VAE Decode to images.
  3. Set frame_rate to match the model (16 for Wan 2.x), format video/h264-mp4, crf 19.
  4. Queue; the video plays in the node and lands in ComfyUI/output.
  5. Add Load Audio and connect it to audio for a soundtrack, or use pingpong for a seamless loop.

Réglages et conseils

  • h264 with yuv420p is the compatible choice for sharing; webm/vp9 is smaller.
  • For GIFs, keep 512 px and 8-12 fps or the file gets huge.
  • Interpolate frames with RIFE VFI (Frame Interpolation pack) before Video Combine for smooth 24-32 fps.
  • Wan 2.1 outputs 81 frames at 16 fps (5 s); match frame_rate exactly to keep real-time speed.
  • Drag the MP4 into ComfyUI to restore the workflow.

Dépannage de Video Combine (VideoHelperSuite)

Video formats are missing, only gif/webp are listed

Pourquoi cela arrive
ffmpeg was not found; VHS lists video formats only when ffmpeg is available.

Comment le corriger
Install ffmpeg (imageio-ffmpeg pip package or a system binary on PATH) and restart ComfyUI.

Playback is too fast or too slow

Pourquoi cela arrive
frame_rate does not match the frames the model produced.

Comment le corriger
Use the native rate: 8 for AnimateDiff v2, 16 for Wan, 24 for Hunyuan and LTX; interpolate if you want more.

The preview shows one frame or a still image

Pourquoi cela arrive
The IMAGE input is a single frame (batch of 1), for example from a sampler without a video latent.

Comment le corriger
Check the latent node: Empty Hunyuan Latent Video / Wan latents need a length above 1; decode the batch, not a single frame.

Error: height not divisible by 2 (h264)

Pourquoi cela arrive
yuv420p needs even dimensions.

Comment le corriger
Render at even sizes (multiples of 8 or 16), or add an Upscale Image node to an even size before Video Combine.

AD
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.

Questions sur Video Combine (VideoHelperSuite)

Can I save frames as PNG sequence?

Yes, choose image/png or connect the frames to Save Image, which writes numbered PNGs.

How do I add sound?

Load Audio (core) or VHS Load Audio, connected to the audio input. The audio is trimmed to the video length.

Where is the file?

ComfyUI/output with the filename_prefix; save_output off writes to temp.

Nœuds liés

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.
Save Image
ComfyUI core
Save Image writes the IMAGE tensor to ComfyUI/output as a PNG, with the whole workflow embedded in the file metadata so the picture can be dragged back into ComfyUI to restore the graph.
VAE Decode
ComfyUI core
VAE Decode converts the sampled LATENT into a pixel IMAGE with the VAE; VAE Decode (Tiled) does the same in tiles for very large images.
Load Video (Upload) (VideoHelperSuite)
ComfyUI-VideoHelperSuite
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.
AD
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.

Autres nœuds ComfyUI

CLIP Text Encode (Prompt)
ComfyUI core
CLIP Text Encode turns a text prompt into CONDITIONING using the model text encoder. One node holds the positive prompt, a second one the negative prompt.
ComfyUI Manager
ComfyUI-Manager
ComfyUI Manager is the extension that installs, updates and fixes custom node packs and models from inside the interface, resolves missing nodes in imported workflows and snapshots your setup.
KSampler
ComfyUI core
KSampler runs the denoising loop: it takes the model, prompts and a latent and produces the finished latent image, controlled by seed, steps, cfg, sampler, scheduler and denoise.
Load Checkpoint
ComfyUI core
Load Checkpoint (CheckpointLoaderSimple) opens a .safetensors or .ckpt model file and hands out the three parts every workflow needs: the diffusion MODEL, the CLIP text encoder and the VAE.
Empty Latent Image
ComfyUI core
Empty Latent Image creates the blank latent canvas (width, height, batch_size) that text-to-image sampling starts from; dimensions must be multiples of 8 and match the model family.
Load Image
ComfyUI core
Load Image reads a picture from the ComfyUI input folder (or an upload) and outputs an IMAGE tensor plus a MASK taken from the alpha channel, the starting point for img2img, inpainting, ControlNet and IP-Adapter graphs.