It's impressive given the constraints!

Would you consider releasing a more capable version that renders with fewer artifacts (and maybe requires a bit more processing power)?

Chatterbox is my go-to, this could be a nice alternative were it capable of high-fidelity results!

▲

sammyyyyyyy a day ago | parent [-]

This is my side “hobby”. And compute is quite expensive. But if the community’s responsive is good, I will definitely think about it! Btw, chatterbox is a great model and inspiration

▲

bicepjai a day ago | parent | next [-]

Thanks can you share details about compute economics you dealt with ?

	▲	sammyyyyyyy a day ago \| parent [-]
		Yeah sure. The training was about ~250 dollars, which is quite low by today’s standards. And I spent a bit more on ablations and research

▲

littlestymaar a day ago | parent | prev [-]

Very cool work, especially for a hobby project.

Do you have any plans to publish a blog post on how you did that? ?What training data and how much? Your training and ablations methodology, etc.