Real ????? - Lotte

Join our Discord to see more images and upcoming updates!

Real ????? - Lotte v6 XL

V6 was trained on 95 images from spreading / gaping ????? and ??? in close up. All images are hand picked, cropped and improved to get the best results.

Training Resolution

832x1248 (2:3) 100% (Portrait Only)

Model: bigLust_v10

The model itself is already good at generating ????? images. But if you want a specific look you have to use a LoRA. It also helps to get more stable results if you want close up's.

LoRA strenght 0.4-0.6 works best.

Inpainting

If you generate images that have lower resolutions as the training size then the results will look bad. Same applies for the inpainting target and area. If that is too small the result will look weird. It can help to upscale the image before you inpaint the pussy.

Inpainting in SDXL is more difficult because of the lack of a real inpainting model. sd_xl_base_1.0_inpainting_0.1 itself is useless for ????? inpainting. I have tested a few other models that claim to be able to inpaint but none of them was better than the base model which was used for merging. Please proof me wrong if you find one that actually works.

Until then just use the same model bigLust_v10 for inpainting. Lower denoise and higher padding values help.

Tags

Keep in mind: Tags raise the chance to get what you want. But depending on the amount of training images containing this tags some tags might need more luck than others to work.

Main tag

pussy_scale3 - Main tag

View

front view - Most images

close up, extreme close up

dry ?????, wet pussy

Action

showing ?????, spreading ?????, stretching pussy

fingers from the side - For spreading with fingers

Shape

????? having [size] outer ????? and [size] inner ????? - Size: tiny, short, medium

[size] ????? gape with [color] channel - Size: tiny, small, medium, big; Color: pink, dark

????????, [size] ???????? gape with [color] channel - Size: tiny, small, medium; Color: pink, dark

Shaving

shaved vulva, shaved vulva with stubble

Other common tags

woman - All images

photo - All images

peehole - If visible

fingers - If visible

Example prompts

pussy_scale3, extreme close up, photo, woman, spreading ?????, fingers from the side, front view, ????? having short outer ????? and short inner ?????, peehole, small ????? gape with pink channel, dry ?????, shaved vulva with stubble, ????????, fingers

pussy_scale3, extreme close up, photo, woman, showing ?????, front view, ????? having short outer ????? and short inner ?????, peehole, small ????? gape with dark channel, dry ?????, shaved vulva, ????????

pussy_scale3, close up, photo, woman, stretching ?????, fingers from the side, front view, ????? having short outer ????? and short inner ?????, peehole, small ????? gape with pink channel, dry ?????, shaved vulva, ????????, fingers

pussy_scale3, extreme close up, photo, woman, showing ?????, front view, ????? having short outer ????? and short inner ?????, dry ?????, shaved vulva with stubble, tiny ???????? gape with pink channel

Real ????? - Lotte v5n

V5n was trained on 95 images from spreading / gaping ????? and ??? in close up. All images are hand picked, cropped and improved to get the best results out of them.

How to Use

v5n now uses the same tagging technique than Real ????? - Spreading and I consider it as an extension of this LoRA. It can be used standalone or in combination to get more variance. If the total weight of both LoRA is greater than 1.0 you will burn the image!

<lora:Pussy_Spreading_v1c:0.3> <lora:Pussy_Lotte_v5n:0.4> ok

<lora:Pussy_Spreading_v1c:0.3> <lora:Pussy_Lotte_v5n:0.7> ok

<lora:Pussy_Spreading_v1c:0.5> <lora:Pussy_Lotte_v5n:0.3> ok

<lora:Pussy_Spreading_v1c:0.5> <lora:Pussy_Lotte_v5n:0.6> bad

<lora:Pussy_Spreading_v1c:0.8> <lora:Pussy_Lotte_v5n:0.7> very bad

Previous versions

Introduction

This is my secodd release after long testing with LoRA generation. I hope you like her.

I am planing to release other LoRA with similar tags in the future so you can mix different shapes and create new styles. I have already another LoRA in beta phase where this works quite good.

Training Data

This LoRA was trained with close up images of the same ????? to get a consistent look. Lotte has some loose holes which she likes to show.

Image count: 35

Resolution: 512x768

I will probably update her in the future as the poses in the training set are limited.

Model

LazyMix+ (Real Amateur ?????) v2

I might train this LoRA on other models too to see if the results will be better. For now it seems that only this model can be used for generation so don't waste your time with others.

For inpainting use the same model but converted it to an inpaint version with the checkpoint merger of webui. Inpainting this LoRA without an inpainting model will be hard.

Don't forget to switch back to the regular model if you get weird results. Happens to me all the time when I start a new image. The inpaining model can not produce normal images.

Tags

pussy_lotte - Main tag

spreading ????? - ????? will be more open and/or spread with fingers

stretching ????? - Uses fingers to open the pussy

gaping ????? - You can see the black hole

butthole - Changes poses so buttholes are better visible

gaping ???????? - Opens her ???? a little bit more

photo - Training image was a real photo

rendering - Training image was generated with an earlier LoRA version (experimental)

finger nails - Can be used to add fingers to the image or remove them (negative)

How to use

DPM++SDE Karras: More realistic images

Euler a: Smoother images

Use 512x768 for image size and upscale later.

CFG scale depends on the tags you are using. Anywhere in the range from 2 to 6 should work. Lower values are better.

Try to avoid Restore Faces if possible as it will sometimes changes the ????? to some kind of weird face or adds teeth.

For basic close up images just add the LoRA + pussy_lotte tag. For more tags see the LoRA metadata. If you add too much tags the result may get worse.

For body shots you need to lower the LoRA strenght but this will reduce ????? details. I try to use the Regional Prompter extension so I can keep the strenght higher. Fix anything with inpainting that you don't like. Or just create an image without the LoRA and inpaint the ????? with LoRA afterwards.

Also works good to inpaint on real HD images to replace a ?????. This was the primary purpose why I created this LoRA.

The close up sample images are created by txt2img without editing. The full body images are completely inpainted from real images.

Mixing this Lora with Lilly works realy good.

Upscaling

For best results I am using ControlNet with type tile + Ultimate SD upscale to keep the image stable without adding ghost ????? all over the place. Upscale 2-3x works most of the time.