Du hast einen ComfyUI-Workflow? Erstelle direkt im Browser eine verständliche Workflow-Dokumentation.Workflow verständlich machen.Jetzt ausprobieren ↗
Support me by watching the video and gave like and comment This is far from perfect, but you can start experiment from here if you use non causvid model/lora, it acutally not going to be saturated, but you trade off...
Laufzeitprofil
Quellenbeschreibung
Support me by watching the video and gave like and comment This is far from perfect, but you can start experiment from here if you use non causvid model/lora, it acutally not going to be saturated, but you trade off quality with time
Geschätzter VRAM Bedarf
Schätzung nicht verfügbar
Die Modell-Dateigrößen sind noch nicht vollständig genug, um diese Anforderung zu berechnen.
Anforderungen
8 AnforderungenKI-generierter Kommentar
KI-generierte Erklärung auf Grundlage von Quellen- und Konfigurationsdetails. Vorschläge sind klar gekennzeichnet.
This ComfyUI workflow is for experimenting with longer video sequences using Wan 2.1; it can take an image, image path, or video path as source media and includes image-to-video processing and video output.
The graph includes WanImageToVideo, KSampler, VAEDecode, and VHS_VideoCombine.
Source media can be selected through LoadImage, VHS_LoadImagePath, or VHS_LoadVideoPath.
Use an image, image path, or video path as the source through LoadImage, VHS_LoadImagePath, or VHS_LoadVideoPath.
WanImageToVideo is listed for image-to-video processing, and VHS_VideoCombine is listed for video output.
The listed base model is Wan Video 14B i2v 480p.
The workflow is published on Civitai by Lordcaocao2025.
The listed model files are clip_vision_h.safetensors, umt5_xxl_fp8_e4m3fn_scaled.safetensors, wan_2.1_vae.safetensors, and wan21Lightspeed_lightspeedI2v14B480p.safetensors.
The listed node packs are comfyui-custom-scripts, comfyui-image-saver, comfyui-kjnodes, and comfyui-videohelpersuite.
To choose source media, review LoadImage, VHS_LoadImagePath, and VHS_LoadVideoPath.
Vorschlag · nicht geprüft
For image-to-video processing and video output, review WanImageToVideo and VHS_VideoCombine.
Vorschlag · nicht geprüft
Verify that the four model files are available and match the listed filenames; no source URL is listed for them.
Vorschlag · nicht geprüft
If you use a non causvid model or LoRA, review the stated quality-versus-time tradeoff for your setup.
Vorschlag · nicht geprüft
Muss das bearbeitet werden?
Melden Sie sich an, um eine Änderungsanfrage zu senden.
Quellen
1 QuelleQuellenauszüge
1 AuszugSource context: 346 downloads · Type Workflows · Base model Wan Video 14B i2v 480p
Vision model · Unknown
umt5_xxl_fp8_e4m3fn_scaled.safetensors
Datei ungeprüftText encoder · SAFETENSORS · Unknown
VAE · Unknown
wan21Lightspeed_lightspeedI2v14B480p.safetensors
Nicht aufgelöstCheckpoint · Unknown
Knotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
