Infinite Talk – WAN 2.1 Workflow 🎙️🖼️➡️🎬

With this workflow, you can turn any single image into a lip-synced video using your own audio file.

All you need to do is:

. Choose an image with your character.

. Upload any audio file (say whatever you want).

. The workflow syncs the audio with your character and delivers a video output.

✨ Key Feature: Unlimited duration!

If you want a longer video, simply provide a longer audio file and increase the Total Frame value.

📂 Inside the workflow, you’ll find all the instructions you need:

. Download links for the required models

. Correct folder paths to place them

. A clear explanation of how to calculate Total Frame based on the audio length

🎥 In the second part of this video, I explain step by step how to run this workflow on a cloud GPU with RunPod. It’s a complete, beginner-friendly guide with important tips you don’t want to miss — so make sure to watch until the end!

RunPod link : https://runpod.io?ref=zux8tl76

🔗Link for Nunchaco Comfyui and SageAttention : https://github.com/Tavris1/ComfyUI-Easy-Install/tree/Windows

Download the workflow here and get started:

👇👇