CivArchive
    LipSync w/ FantasyTalking Model - v1.1

    This workflow uses the Wan Fantasy Talking Model for lip syncing.

    NOTE :

    There are sometimes issues with lip syncing... I hope there will be a fix from Alibaba.

    I will update if a fix comes along, meanwhile.. please check MultiTalk, this has no issues with synchronization. This works a lot better at the moment. See link below.

    This is very natural looking lip sync.

    Input: an audio file with a voice, a photo of someone's face (close up is better)

    The workflow will create a video by animating the photo and sync up the voice.

    You may want to upscale the video with your favorite upscaler.

    LIPSYNC using FantasyTalking model (Alibaba)

    Fantasy-AMAP/fantasy-talking: FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis

    wan video model

    -----------------

    https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files/diffusion_models

    Fantasytalking model

    --------------------

    https://huggingface.co/Kijai/WanVideo_comfy/tree/main

    This workflow was tested with 24GB VRAM and 64GB RAM

    100 frames at 512x512 with 15 steps is taking about 9 to 10 minutes.

    Description

    There was an issue the video/audio syncing in version 1.0. Hopefully that is a fixed now. Had to increase the fps, based on feedback from author of model.

    Workflows
    Wan Video 14B i2v 720p

    Details

    Downloads
    168
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    10/5/2025
    Updated
    10/6/2025
    Deleted
    10/5/2025

    Files

    lipsyncW_v11.zip

    Mirrors

    CivitAI (1 mirrors)