Introduction

This LyCORIS is used to generate futanari with hyper penis.

How to use it

I recommand using it in weight 0.6-0.7. If you have other loras used at the same time. Bring it to 0.7-0.8.

This lora has two triggerwords. One is hyper_penis, use to generate penis without cum. The other is hyper_ejaculation. Use it when you need cum in your image.

Why I made these two triggerwords? The answer is that, if your trainset contains both images with and without cum, the concepts will converge and you will get penis with cumdrip randomly. So I divided my trainset into two parts and made two triggerwords.

Training details:

Traingset is of about 400 images. They are mirrored before training. Half of them are chosen as regularization images. Total steps are about 14000.

Regularization = true

resolution=768

batch_size=1

epoch=10

network_dim=32

network_alpha=32

clip_skip=2

Using AdamW8bits as optimizer:

• lr="1e-4"

• unet_lr="1e-4"

• text_encoder_lr="1e-5"

Locon parameters:

• conv_dim=4

• conv_alpha=4

About sample images

I made them with two models: AOM3A3 and AOM3A2. I did too many tries and I cannot remember some lora parameters. Below are all the lora I may used in these samples:

Tattoo at Everywhere | Stable Diffusion LORA | Civitai

photorealistic womb tattoos 逼真私密纹身 | Stable Diffusion LORA | Civitai

Less underwear | Stable Diffusion LORA | Civitai

[LoCon/LoRA] Offset noise | Stable Diffusion LORA | Civitai

epi_noiseoffset | Stable Diffusion LORA | Civitai

I used SwinIR 4X to hires.up the images.