diff-svc models that are made/trained/owned by MLo7
project_name: Nehito
tone: Male
step#: 1M
audio data: 6 hours | [4 hours of singing, 2 hours of raw concatenative synth samples]
VP: Ghin K.
Team Title: Archivoice
render and share results: allowed
used for pretraining: allowed
NSFW: allowed
golden.hour.Diff-SVC.demo.render.mov
project_name: Nehito
tone: Male
step#: 1M
audio data: 8 hours | [6 hours of singing, 2 hours of raw concatenative synth samples]
VP: Ghin K.
Team Title: Archivoice
render and share results: allowed
used for pretraining: allowed
NSFW: allowed
##coming soon
project_name: Takuto
tone: Male
step#: 250k | used pretrain
audio data: 2 hour, 18 minutes | [1 hour 22 minutes of raw concatenative synth samples + augmented pitch, 49 minutes of vsynth render]
VP: Taktger
Team Title: Taktger
render and share results: allowed
used for pretraining: not allowed | due to this model was a ported model test
NSFW: allowed
DAWN_demo.mov
project_name: Toshio
tone: Male
step#: TBD | used pretrain
audio data: 3 hour, 51 minutes | [3 hours 13 minutes of raw concatenative synth samples, 38 minutes of singing]
VP: Toshio Sasagawa
Team Title: Toshio
render and share results: allowed
used for pretraining: not allowed | not enough singing data-type
NSFW: allowed
##coming soon