[ 3 / biz / cgl / ck / diy / fa / ic / jp / lit / sci / vr / vt ] [ index / top / reports ] [ become a patron ] [ status ]

/vt/ - Virtual Youtubers

Search:


View post   

>> No.72340422 [View]
File: 1.29 MB, 928x1232, Gawr Gura --sref flat white (Niji 6 Raw).png [View same] [iqdb] [saucenao] [google]
72340422

>>72338796
Midjourney! They added both Character Reference and Style Reference pretty recently. All I need is a reference image of a style and I can render stuff in that style!

Style References work better with characters that Midjourney knows natively though, from my experience. Niji Journey "knows" the same VTubers from the NovelAI leak. The more reference images in its training, the more you can abstract them while still keeping small details on model.

>Style Reference:https://doodles.google/doodle/celebrating-the-flat-white/

>> No.71104524 [View]
File: 1.29 MB, 928x1232, Gawr Gura --sref Niji 6 Raw 4.png [View same] [iqdb] [saucenao] [google]
71104524

oh and uhh here's a Glorbo in the style of today’s Google Doodle!

>Style Reference: https://www.google.com/logos/doodles/2024/celebrating-the-flat-white-6753651837110463.2-la202124.gif

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