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)<a target="_blank" rel="ugc" href="https://github.com/Fantasy-AMAP/fantasy-talking">Fantasy-AMAP/fantasy-talking: FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis</a>wan video model-----------------<a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files/diffusion_models">https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files/diffusion_models</a>Fantasytalking model--------------------<a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/WanVideo_comfy/tree/main">https://huggingface.co/Kijai/WanVideo_comfy/tree/main</a>This workflow was tested with 24GB VRAM and 64GB RAM100 frames at 512x512 with 15 steps is taking about 9 to 10 minutes.

LipSync w/ FantasyTalking Model

I had to clean up some things that was causing the video/audio to get out of sync. Fantasy Talking is very sensitive to the configuration. This one seems to produce good results. Please try to stick to the config settings in this workflow. Also , made it easier to do continuation of lipsync for low VRAM.

Files with SHA256: 00f40a203d5e9bffa486b2ad4dd2f1c1e1ddff706c9fa2b7f05c91f5b8a91420