[ 3 / biz / cgl / ck / diy / fa / ic / jp / lit / sci / vr / vt ] [ index / top / reports ] [ become a patron ] [ status ]
2023-11: Warosu is now out of extended maintenance.

/vt/ - Virtual Youtubers

Search:


View post   

>> No.41686382 [View]
File: 319 KB, 3248x257, texture_projection.png [View same] [iqdb] [saucenao] [google]
41686382

>>41686210
There already are models that take depth information from a 3d model as starting image and generates an image over it. Transfer learning on a specific vtuber + this using a posable 3d model could allow very accurate images

Navigation
View posts[+24][+48][+96]