Lovelive -- Hoshizora Rin
My first Lora Model, which might still have some problem. I will keep tring to optimize and perfect this model.
Description
New version trained by 50 pictures, which include 20 3d-model pictures. With simple background, weight 0.6-0.8 will be fine (or using hoshizora_rin tag together with weight 0.4-0.6). With complex background, I recommand 0.4-0.6. Never use more than 0.8 weight which will cause terrible image. Next step I will try to use more transparent background picture to make this Lora more general.
Details
Downloads
535
Platform
CivitAI
Platform Status
Available
Created
3/1/2023
Updated
9/27/2025
Deleted
-
Files
Hoshizora_rin_v2.0.safetensors
Mirrors
CivitAI (1 mirrors)