V2
Added multiple audio source loading options
Added simple face fixing as alternative to reactor (works much better)
Added a few options to better control the video ref image
Control groups updated with new options
Tested up to 1 min 30 for face sync.
Tested up to 600 frames for video outpaint with 1.3b model
All examples use the 1.3b model as the video model.
V1 - Simple ai talking avatar
Text to speech with chatterbox
Lip Sync with Float
Outpaint with wan Vace. 1.3b or 14b.
optional reactor.
node lip sync
https://github.com/yuvraj108c/ComfyUI-FLOAT
Models
Google drive FLoat model
https://drive.google.com/file/d/1rvWuM12cyvNvBQNCLmG4Fr2L1rpjQBF0/view
git clone these in the ComfyUI/model/float folder (not in custom nodes folder)
https://huggingface.co/facebook/wav2vec2-base-960h
https://huggingface.co/r-f/wav2vec-english-speech-emotion-recognition
Chatterbox tts
Description
FAQ
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.