Sign In

(城ヶ崎 莉嘉) RIKA JOUGASAKI

335
2.8k
756
4
Updated: Oct 5, 2024
character
Verified:
SafeTensor
Type
LoRA
Stats
1,350
625
Reviews
Published
Apr 28, 2023
Base Model
SD 1.5
Training
Steps: 250
Epochs: 12
Trigger Words
/RIKA JOUGASAKI/
1girl
Hash
AutoV2
2BA5A7C8A3

Hello everyone, I decided to train a model at Jougasaki Rika arts.
Used NeverEnding Dream (NED) and Anything-V4.5 to create images.
Recommendations:

  • Keywords: /RIKA JOUGASAKI/, 1girl, 1girl, solo, long hair, blonde hair, hair ornament, green eyes, two side up

  • Use LoRA weight between 0.65-0.85 for versions below 4.0R (there are fewer problems).

About versions:

Version 4 is now available! Perhaps this is the last version of this character.

  • 128 images in various formats and resolutions.

  • Fixed issue with teeth.

  • Simplified input of tags to call. It is enough to enter 2 or one keyword.

  • Like the experimental one, this is a mix of realistic, watercolor, etc. images. More poses like "full body" etc.

  • Most of the example images were created using LoRA weight = 1. But in some cases this does not give the best result.

About versions 1 and 2:

  • The only difference between versions 1 and 2 is the number of epochs. v.1 - 10 x 55 steps, v.2 - 6 x 55 steps. I'll be happy to read your opinion on this.

Version 3 model trained on art with a resolution of 768x768. 🎉🎉🎉

  • Version 4 artmix. (maybe this is not the best idea) 0w0

If you have any tips for training LoRA models, I will be glad to read.