[ 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   
  [?]In ghost mode, only threads with non-archived posts will be shown
>> No.48010124 [View]
File: 2.55 MB, 1728x865, AB.png [View same] [iqdb] [saucenao] [google]
48010124

the more i try to add specifics, especially for scenes, the worse the accuracy of the figure becomes. is that normal? do i just need to gitgud with putting prompts into weighted blocks etc?

ie. if i just ask for Mumei and let the AI do its thing i get something decent, if i try to make a scene like "exploring a large underground train tunnel" i get digital soup.

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