ComfyUI Tutorial Series Ep 60 Infinite Talk (Audio-Driven Talking AI Characters)
Автор: pixaroma
Загружено: 2025-09-02
Просмотров: 26670
In this episode, we set up the Infinite Talk workflow inside ComfyUI to generate AI-driven talking-head videos from just an image and an audio file. With this setup, you can create realistic lip-synced characters that respond naturally to the timing and pauses in speech.
I’ll walk you through:
Installing the required models (WAN video, Infinite Talk, wav2vec2, Lora, and text encoder).
Setting up the ComfyUI workflow step by step.
Adjusting key parameters for performance (frame window size, motion frames, quantization, and Block Swap for VRAM optimization).
Running single-speaker and multi-speaker workflows.
Testing with different voices, prompts, and image sizes to balance quality and speed.
Whether you want to make AI avatars for videos, audio-driven animations, or talking character content, this guide gives you everything you need to get started.
Get the workflows and instructions from discord for free
Step 1: use this link to join if you didn't join already / discord
Step 2: then access directly this episode using this link: / discord
Check Other Episodes
• ComfyUI Tutorial Series: Mastering Stable ...
Unlock exclusive perks by joining our channel:
/ @pixaroma
Grab your Pixaroma merch from here: / @pixaroma
#comfyui #comfyuitutorial #talkingaiavatar
Доступные форматы для скачивания:
Скачать видео mp4
-
Информация по загрузке:
