/vt/ - Virtual Youtubers

>>	Anonymous Fri Feb 3 06:57:49 2023 No.42291513 [View] File: 1.21 MB, 1024x1024, 00053-1820176989.png [View same] [iqdb] [saucenao] [google] >>42291235 an old one that I made using my first IRyS LoRA a while back.

Anonymous Fri Jan 13 06:42:56 2023 No.40892123 [View]
File: 1.21 MB, 1024x1024, 00053-1820176989.png [View same] [iqdb] [saucenao] [google]

>>40888479
I retrained the previous LoRa using the same dataset but changed some settings.

Training Speed: 5e-5 from 1e-4
Net Dim Size: This has been increased from 128 to 256.
Added text encoder learning rate of 5e-5.
Due to the slower learning rate, I bumped the number of epoch to 12 from 8.
Max bucket resolution changed to 1280 from 960.

Overall it seems to be able to merge itself better into the model rather than maintain the artstyle of the fanart that were used as the dataset?

Advanced search
Text to find
Subject [?]Search by post subject. Leave empty for any.
Username [?]Search for user name. Leave empty for any user name.
Tripcode [?]Search for tripcode. Leave empty for any.
Email [?]Search by email. Leave empty for any.
Filename [?]Search by image filename. Leave empty for any.
From Date [?]Enter what date to start searching from. Format is YYYY-MM-DD
To Date [?]Enter what date to start searching until. Format is YYYY-MM-DD
Image hash
Search in	All Posts OPs Only
Deleted posts	Show all posts Show only deleted posts Only show non-deleted posts
Internal posts	Show all posts Show only internal posts Show only archived posts
Order	New posts first Old posts first
Capcode	All Posts Only by Users Only by Mods Only by Admins Only by Developers
Results	Posts Threads
Action	[ Simple ]

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

/vt/ - Virtual Youtubers

Search: