Aller au contenu
WorkflowVérifiéExterne
Télécharger

Seamless video join (loop) with Wan 2.1 VACE — video join v1.6

This version outputs joined clip

Sourcecivitai.com/models/2475712
TâcheMultipleCapacitésImage en image · Mise à l'échelleFamilleWanVersionRelease 3085066 — seamlessVideoJoinLoop_videoJoinV16.jsonEstimé VRAMNot yet characterizedUnratedClasse

Profil d'exécution

Accès
Flux de travail externe
Statut
Vérifié
Version
seamlessVideoJoinLoop_videoJoinV16.json
Source
Civitai
Mis à jour
3 nov. 2026

What you need

Model files
1.4 GiB known subtotal

Remaining hardware or download-size estimates are not available yet.

Exigences

Modèles

5

  • umt5-xxl-enc-bf16.safetensors

    Non résolu

    Text encoder · Unknown

  • wan_2.1_vae.safetensors

    Dépôt identifié

    VAE · Unknown

  • Non résolu

    LoRA · Unknown

  • Wan2_1_VACE_1_3B_preview_bf16.safetensors

    Fichier indiqué

    Checkpoint · 1.37 GB · Hugging Face · Kijai/WanVideo_comfy

  • Wan2.1-T2V-1.3B-FP16.safetensors

    Non résolu

    Checkpoint · Unknown

Packs de nœuds

9

  • comfyui_essentials

    Trouvé

    Pack de nœud · Registry

  • comfyui-kjnodes

    Trouvé

    Pack de nœud · Registry

  • Trouvé

    Pack de nœud · Registry

  • comfyui-videohelpersuite

    Trouvé

    Pack de nœud · Registry

  • ComfyUI-WanVideoWrapper

    Trouvé

    Pack de nœud · Registry

  • kijai/ComfyUI-KJNodes

    Trouvé

    Pack de nœud · GitHub · kijai/ComfyUI-KJNodes

  • Label (rgthree)

    Non résolu

    Pack de nœud · Unknown

  • rgthree-comfy

    Trouvé

    Pack de nœud · Registry

  • scale-image-to-total-pixels-advanced

    Non résolu

    Pack de nœud · Registry

Commentaire généré par l’IA

Explication générée par l’IA à partir des détails de la source et de la configuration. Les suggestions sont clairement signalées.

Objectif

  • This workflow joins two video clips or makes a loop from one clip, producing a joined clip.

Flux

  • Its graph includes VHS_LoadVideo and VHS_VideoCombine nodes.

Entrées et sorties

  • Use two clips for a join or one clip for a loop.

    Suggestion · non vérifié

Installation

  • Find video join v1.6 on Civitai, where Brainburns894 is listed as the publisher: https://civitai.com/models/2475712?modelVersionId=3085066.

Dépendances

  • The workflow lists these node dependencies: comfyui_essentials, comfyui-kjnodes, comfyui-logicutils, comfyui-videohelpersuite, and ComfyUI-WanVideoWrapper; kijai/ComfyUI-KJNodes, Label (rgthree), rgthree-comfy, and scale-image-to-total-pixels-advanced.

  • It lists five model files: umt5-xxl-enc-bf16.safetensors, wan_2.1_vae.safetensors, Wan2_1_self_forcing_sid_v2_1_3B_lora_rank_32_fp16.safetensors, Wan2_1_VACE_1_3B_preview_bf16.safetensors, and Wan2.1-T2V-1.3B-FP16.safetensors.

  • Before setup, check whether Label (rgthree) and scale-image-to-total-pixels-advanced are available in your ComfyUI install.

    Suggestion

Configuration

  • The listed base model is Wan Video 2.2 I2V-A14B.

  • comfyui-logicutils is listed at version 1.7.2.

Précautions

  • The title names Wan 2.1 VACE, while the base model is listed as Wan Video 2.2 I2V-A14B; check the listed model files before setup.

    Suggestion

  • No model-use license is listed; check the Civitai page for usage terms before using the workflow.

    Suggestion

Faut-il modifier cela ?

Connectez-vous pour envoyer une demande de modification.

Sources

1 source
CivitaiPrincipalVersion 3085066
civitai.com/models/2475712

Vérifié 3 nov.

Workflow instructions

Author notes from seamlessVideoJoinLoop_videoJoinV16.json · selected release

Calculate how many frames should we skip when extracting middle part

Author notes from seamlessVideoJoinLoop_videoJoinV16.json · selected release

Make number of middle frames Wan-compatible: (x * 4) + 1 where x is integer

Author notes from seamlessVideoJoinLoop_videoJoinV16.json · selected release

Calculate how many frames should we skip when extracting inpaint frames inside middle part

Author notes from seamlessVideoJoinLoop_videoJoinV16.json · selected release

## Model links (for local users) **diffusion_models** - [wan2.1_t2v_1.3B_bf16.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/diffusion_models/wan2.1_t2v_1.3B_bf16.safetensors) - [wan2.1_vace_1.3B_fp16.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/diffusion_models/wan2.1_vace_1.3B_fp16.safetensors) **lora** - [Wan2_1_self_forcing_sid_v2_1_3B_lora_rank_32_fp16.safetensors](https://huggingface.co/Kijai/WanVideo_comfy/blob/main/LoRAs/Wan2_1_self_forcing_1_3B/Wan2_1_self_forcing_sid_v2_1_3B_lora_rank_32_fp16.safetensors) **text_encoders** - [umt5-xxl-enc-bf16.safetensors](https://huggingface.co/Kijai/WanVideo_comfy/blob/main/umt5-xxl-enc-bf16.safetensors) **vae** - [Wan2_1_VAE_bf16.safetensors](https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Wan2_1_VAE_bf16.safetensors) Model Storage Location ``` 📂 ComfyUI/ ├── 📂 models/ │ ├── 📂 diffusion_models/ │ │ └── wan2.1_t2v_1.3B_bf16.safetensors │ │ └── wan2.1_vace_1.3B_fp16.safetensors │ ├── 📂 loras/ │ │ └── Wan2_1_self_forcing_sid_v2_1_3B_lora_rank_32_fp16.safetensors │ ├── 📂 text_encoders/ │ │ └── umt5-xxl-enc-bf16.safetensors │ └── 📂 vae/ │ └── Wan2_1_VAE_bf16.safetensors ```

Download files

Artefacts du modèle

2 artefacts

seamlessVideoJoinLoop_videoJoinV16.json

json · 96,7 KB · SHA-256 8941888ff8ad…3e0f · Civitai

Download file

seamlessVideoJoinLoop_videoJoinV16.json

json · 96,7 KB · SHA-256 8941888ff8ad…3e0f

Download file

Extraits de sources

3 extraits
Note3 nov.civitai.com/models/2475712

Source context: 1122 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B

Note2 oct.civitai.com/models/2475712

Source context: 1021 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B

Note28 juil.civitai.com/models/2475712

Source context: 803 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B