Download
1 variant available
fp16 SafeTensor
Hoshizora_rin_v2.0.safetensors
Half precision, best balance • 36.11 MB
Verified: 3 years ago
Stats
5600 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
80 1 2 3 4 5 6 7 8 9
Reviews
(72)
Published
Mar 1, 2023
Base Model
Training
Steps: 5,000
Hash
AutoV2
B6B4577E9D
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.
Show more

570 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
7190 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
