ComfyUI Tutorial Series Ep 60 Infinite Talk (Audio-Driven Talking AI Characters)

Sobre esta lección

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 https://discord.gg/gggpkVgBf3 Step 2: then access directly this episode using this link: https://discord.com/channels/1245221993746399232/1410879622832324618/1410880021299462165 Check Other Episodes https://www.youtube.com/playlist?list=PL-pohOSaL8P9kLZP8tQ1K1QWdZEgwiBM0 Unlock exclusive perks by joining our channel: https://www.youtube.com/channel/UCmMbwA-s3GZDKVzGZ-kPwaQ/join Grab your Pixaroma merch from here: https://www.youtube.com/@pixaroma/store #comfyui #comfyuitutorial #talkingaiavatar