Skip to content
WorkflowListedExternal
Open source

Change a video background using wan, vace and insprynet rembg (Workflow) — v1.0

Seamless Video Background Change: WAN + VACE + Masking in ComfyUI

Sourcecivitai.com/models/1976318
TaskMultiCapabilitiesImage to image · UpscalingFamilyWanEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access
External workflow
Status
Listed
Source
Civitai
Updated
Oct 2, 2026

Source excerpt

Seamless Video Background Change: WAN + VACE + Masking in ComfyUI

What you need

Model files
0.1 GiB known subtotal

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

Requirements

Models

6

Node packs

4

  • comfyui-depthanythingv2

    Found

    Node pack · Registry

  • comfyui-kjnodes

    Found

    Node pack · Registry

  • comfyui-videohelpersuite

    Found

    Node pack · Registry

  • ComfyUI-WanVideoWrapper

    Found

    Node pack · Registry

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

Purpose

  • This ComfyUI workflow changes a video's background with WAN, VACE, and masking; it takes video and image paths and lists video-combination, image-preview, and image-saving outputs.

Flow

  • The listed flow covers video loading, mask growth and preview, masked-image compositing, and video combination.

  • It lists DepthAnything_V2, InspyrenetRembg, ReActorFaceSwap, ReActorRestoreFace, and RIFE VFI nodes.

Inputs and outputs

  • VHS_LoadVideoPath and VHS_LoadImagePath are listed for video-path and image-path inputs.

  • VHS_VideoCombine is listed for video combination, while PreviewImage and SaveImage are listed for image preview and saving.

Setup

  • The listed base model is Wan Video 14B t2v, and the publisher is Lordcaocao2025.

Dependencies

  • The workflow lists these node packs: ComfyUI-WanVideoWrapper, comfyui-kjnodes, comfyui-depthanythingv2, and comfyui-videohelpersuite.

  • It lists these model items: wan_2.1_vae.safetensors, microsoft/Florence-2-base, and Wan21_CausVid_bidirect2_T2V_1_3B_lora_rank32.safetensors.

  • It also lists wan2_1-VACE_module_1_3B_fb16.safetensors, depth_anything_v2_vitl_fp16.safetensors, and wan2.1_t2v_1.3B_fp16.safetensors.

Configuration

  • The workflow includes WanVideoModelLoader, WanVideoSampler, WanVideoTextEncode, and WanVideoVACEModelSelect nodes.

  • It also includes WanVideoLoraSelect, WanVideoTeaCache, WanVideoBlockSwap, and WanVideoTorchCompileSettings nodes.

Cautions

  • Before use, verify that wan_2.1_vae.safetensors, Wan21_CausVid_bidirect2_T2V_1_3B_lora_rank32.safetensors, wan2_1-VACE_module_1_3B_fb16.safetensors, depth_anything_v2_vitl_fp16.safetensors, and wan2.1_t2v_1.3B_fp16.safetensors are available.

    Suggestion · not verified

  • No license is listed for this workflow.

Does this need to be edited?

Sign in to send an edit request.

Sources

1 source
CivitaiSource
civitai.com/models/1976318

Verified Jul 19

Source excerpts

1 excerpt
NoteJul 19civitai.com/models/1976318

Source context: 646 downloads · Type Workflows · Base model Wan Video 14B t2v