Fantasy Talking In ComfyUI Locally - Running Next Level Of AI Talking Avatar
Added 2025-04-30 13:01:05 +0000 UTC
Tutorial Video : https://youtu.be/bSssQdqXy9A
Discover Alibaba’s Fantasy Talking AI—the breakthrough in hyper-realistic talking avatars! In this video, we test its lip-syncing accuracy, body movements, and seamless audio integration using WAN 2.1 as the base model. Watch as we compare it to older AI avatars, optimize FPS settings for perfect sync, and even integrate AI-generated voices for next-level content creation. Plus, get a step-by-step guide to running it in ComfyUI—from model setup to workflow tweaks!
Who Is This For?
Content creators wanting AI-powered talking avatars for videos.
ComfyUI users exploring WAN 2.1-based AI tools.
Tech enthusiasts tracking Alibaba’s latest AI innovations.
Marketers and influencers needing customizable digital spokespeople.
Why It Matters:
Fantasy Talking sets a new standard for AI-driven lip-syncing and facial animations, making it ideal for ads, virtual influencers, and dynamic storytelling. While still evolving, its ability to sync fast-paced audio and animate full-body movements makes it a game-changer.
FantasyTalking
https://huggingface.co/acvlab/FantasyTalking
Demo : https://huggingface.co/spaces/acvlab/FantasyTalking
ComfyUI Model Download: https://huggingface.co/Kijai/WanVideo_comfy/blob/main/fantasytalking_fp16.safetensors
Dia TTS : https://github.com/nari-labs/dia
Custom node: https://github.com/nobrainX2/comfyUI-customDia
Demo : https://huggingface.co/spaces/nari-labs/Dia-1.6B
Attached Fantasy Talking ComfyUI workflow here:
