A Workflow That Could Make a Photo Talk With a Perfect Voice Clone and Emotion Match
Free try out link: https://www.runninghub.ai/post/1963995124013387778
All the model details are within the workflow notes.
The video generation is resource-heavy. If your local computer is unable to run this workflow or you just want to see how good the model is and check all the workflow parameter settings before downloading, please open the link above to run it online for free on RTX4090. Just click and run. No brain-racking local setup.
1000 credits upon signing in using the above link(One gen only takes about 10-30 credits), with an extra 100 credits on daily login.
Description
FAQ
Comments (3)
Vibevoice is g-awful with samples Chatterbox handles with ease. And the MS model won't say many words. So if you want "just works" use Chatterbox.
If you are prepared o clean up your samples, put up with censorship and slow generation, and render over and over until you get an output without mistakes, vibevoice is for you.
sorry you got so a so bad experience, for speed, as I mentioned in the workflow note, it will be slow the first time you run it, since it needs to compile the wheels needed. but after that, it should be normal. my RTX 20s card can use it.
vibevoice is the best I've come across, but I will give chatterbox another chance, doubt that it is authentic as vibevoice thoug. talking about the large model of course.