RVC voice cloning (2023)
Using my voice I created a data set and trained it on the RVC 2.0 model. I was able to synthesize my voice with Frank Senatras “That's Life”. I can do this with any song and voice.
Image Generation
I took a dataset and trained my face on the stable diffusion XL model. I created a Lora with the Kohya training tools. All using an RTX 3070.ing PLA.
Ai Generated Video 2023
Used Stable Diffusion XL and control net to create this video. I trained a Lora on the character dancing and made several other versions after this.