V1 IL/NOOB Version
Suggested weight anywhere from 0.5 to 1
I found pretty good results in the 0.7 to 0.8 range depending on what your doing
Scheduling type depends on base model you use but in most cases Euler a works fine.
this LoRA was 100% made with my own self-made art, I rendered everything in Blender cycles/eevee
I spent a lot of time going through the dataset retagging, removing watermarks, and purging bad data for the lastest version.
enjoy
Description
Better dataset tagging
Expanded training dataset by over 2 times as much from V1
Better style consistency
FAQ
Details
Downloads
1,920
Platform
SeaArt
Platform Status
Available
Created
10/28/2024
Updated
12/31/2024
Deleted
-
Files
Available On (3 platforms)
Same model published on other platforms. May have additional downloads or version variants.







