Original link: https://v3u.cn/a_id_313
With the help of So-vits, we can train a variety of timbre models by ourselves, and then reproduce any song we want to enjoy, realizing the freedom of ordering songs, but sometimes we always feel that something is missing, that’s right, the picture is missing, and we can only smell it This time we let AI Trump’s singing voice and his stalwart image appear at the same time, and based on PaddleGAN, we built the “Knowing King” with “beautiful voice and beautiful image”. PaddlePaddle is Baidu’s open source deep learning framework. Its functions are all-encompassing, covering a total of 40 models in the three major fields of text, image, and video. It can be said that it can see everything in the field of deep learning. Wav2lip, a sub-module in the PaddleGAN visual effect model, is the secondary packaging and optimization of the open source library Wav2lip. It realizes the synchronization of the character’s mouth shape and the input lyrics. It sounded like it was singing. …
This article is transferred from: https://v3u.cn/a_id_313
This site is only for collection, and the copyright belongs to the original author.