CivArchive
    Video Subject Inpaint (WAN2.2 KJversion+Fun) - v1.0

    Fed up?
    Models too big filling up your storage, nodes a nightmare to install with constant errors, GPU RAM always running out and crashing halfway? RunningHub solves it all! With RTX 4090 24G VRAM in the cloud, all models and nodes pre-integrated, just sign up with Gmail to get 1000 free credits and run your workflow instantly — smooth, fast, and hassle-free!

    Workflow Link:https://www.runninghub.ai/workflow/1969075794129678337?inviteCode=rh-v1153

    Use the VACE node released by the FUN team to perform subject replacement. It is recommended to read the NOTE section for better results.
    If you don’t want to use a reference image, you can disconnect the Ref_image input on the VACE node and control the generation solely with text.

    Kj version Fun vace:

    https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/tree/main/VACE

    Wan2.1-T2V-14B-StepDistill-CfgDistil lora

    https://huggingface.co/lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill-Lightx2v/tree/main/loras

    WAN2.2 FUN Reward:(not necessary)

    https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Wan22_FunReward/Wan2.2-Fun-A14B-InP-LOW-HPS2.1_resized_dynamic_avg_rank_15_bf16.safetensors

    Description

    Workflows
    Wan Video 2.2 T2V-A14B

    Details

    Downloads
    68
    Platform
    CivitAI
    Platform Status
    Available
    Created
    9/19/2025
    Updated
    9/27/2025
    Deleted
    -

    Files

    videoSubjectInpaintWAN2_v10.zip

    Mirrors