V4:
18-image Lora that allows you to generate Pseudo-Penises in the style of Pirin-apex.
prompts: by pirin-apex, pseudo-penis, big pseudo-penis, long pseudo-penis, hyaenid genitalia, hyaenid pussy,
negative prompts: futanari, intersex, gynomorph, herm, humanoid penis,
Base model: NoobAI-XL EPS 1.1
Epochs: 10
Repeats: 4
Train Batch Size: 4
Steps: 180
Resolution: 1024
Enable Bucket: On
Shuffle Tags: On
Keep Tokens: 3
Clip Skip: 2
Flip Augmentation: On
Unet LR: 0.0005
Text Encoder LR: 0.00005
LR Scheduler: cosine_with_restarts
LR Scheduler Number: 3
Min-SNR Gamma: 5
Network Dim: 32
Network Alpha: 16
Noise Offset: 0.1
Optimizer: AdamW8bit
V3:
18-image Lora that allows you to generate Pseudo-Penises in the style of Pirin-apex.
prompts: by pirin-apex, pseudo-penis, big pseudo-penis, long pseudo-penis
negative prompts: futanari, intersex, gynomorph, herm
Base model: NoobAI-XL EPS 1.1
Repeats: 6
Steps: 180
Epochs: 10
Unet LR: 0.0001
Text Encoder LR: 0.00001
LR Scheduler: constant
LR Scheduler Number: 1
Min-SNR Gamma: 5
Network Dim: 32
Network Alpha: 16
Train Batch Size: 6
V2:
18-image Lora that allows you to generate Pseudo-Penises in the style of Pirin-apex.
prompts: by pirin-apex, pseudo-penis, big pseudo-penis, long pseudo-penis
negative prompts: futanari, intersex, gynomorph, herm
Base model: NoobAI-XL EPS 1.1
Repeats: 17
Steps: 510
Epochs: 10
Unet LR: 0.0001
Text Encoder LR: 0.00001
LR Scheduler: constant
LR Scheduler Number: 1
Min-SNR Gamma: 5
Network Dim: 48
Network Alpha: 32
Train Batch Size: 6
V1:
10-image Lora that allows you to generate Pseudo-Penises in the style of Pirin-apex.
prompts: by pirin-apex, pseudo-penis, big pseudo-penis, long pseudo-penis
negative prompts: futanari, intersex, gynomorph, herm
Base model: NoobAI-XL EPS 1.1
Repeats: 30
Steps: 500
Epochs: 10
Unet LR: 0.0001
Text Encoder LR: 0.00001
LR Scheduler: constant
LR Scheduler Number: 1
Min-SNR Gamma: 5
Network Dim: 64
Network Alpha: 32
Train Batch Size: 6
Description
The prompts “hyaenid genitalia” and “hyaenid pussy” were added, and the Unet LR and Text Encoder LR values were increased to 0.0005 and 0.00005, respectively.



