[ 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.37007188 [View]
File: 549 KB, 512x768, 08477-4267497106-(masterpiece), best quality, (soft lighting), 1girl, illustration of anya-t4-nai-10000, hololive, brown hair, long hair, wavy ha.png [View same] [iqdb] [saucenao] [google]
37007188

>>37006569
>Do not use the --medvram or --lowvram argument when training! Results will be highly inferior

I made sure I didn't have this on for any of my training. It really was all the same settings and data, just a better graphics card and that resulted in a better embed. Makes me think there's some sort of limiting going on out of sight somewhere, maybe not necessarily in VRAM but it could be in operation speed or simultaneous operations or something.

I guess I may as well check out xformers too if I find the time, always nice to get a look at what all the options are even if it turns out to not be as good

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