Infinite Avatar
A talking avatar image-to-video workflow named "Infinite Avatar" that dynamically generates animated avatars from a still image and audio input, utilizing an LLM for prompt generation. It employs a WanVideo model, multiple LoRAs, and MultiTalk with Wav2Vec models for audio processing and realistic speech synchronization.
Shared by
324 views
88 downloads
Shared 2 months ago
Workflow Properties
Basic information about this workflow
Nodes
69
Connections
85
Version
0.4
Groups
Yes
Workflow Preview
Environment Configuration
This workflow includes pre-configured environment settings
| Setting | Value |
|---|---|
| ComfyUI Version | 4449e147692366ac8b9bd3b8834c771bc81e91ac |
| GPU Type | L40S |
| Python Version | 3.11 |
| Custom Nodes | rgthree's ComfyUI Nodes ComfyUI-WanVideoWrapper ComfyUI-VideoHelperSuite audio-separation-nodes-comfyui ComfyUI LLM Toolkit KJNodes for ComfyUI ComfyUI Frame Interpolation if_chatterbox.git quick-connections ComfyUI-Easy-Use ComfyUI Deploy ComfyUI-MelBandRoFormer |
How to Use
Click "Use This Workflow" to import it into your ComfyDeploy workspace with pre-configured environment settings
Download the JSON file to use in your own ComfyUI instance
Need Help?
Join our vibrant community for support, tips, and workflow sharing
Join Our Discord Community
Free to join • 24/7 community support • 3,000+ members