PonyRealNylonFeets - Feet in nylon for Pony Diffusion

The Lora model is specifically trained to show nyloned feet, with different nylon clothes (pantyhose, stockings), and colors (black, tan, white).

The native 1024x1024 was specifically selected to train a performing Pony diffusion Lora, with reliable layout.

An SD 1.5 Lora  is available here.

An SD XL Lora is available here.

ISTRUCTIONS FOR USE (use example image to retrieve an istance prompt)

To obtain best results please read the following istructions (moreover reviews are very welcome!!!)

Lora activation and weight:

A value of 0.6 or 0.7 is highly recommended. Higher values can trigger artifacts.

So a good activation keyword for lora is:

<lora:PonyRealNylonFeets:0.7>

This Lora is specifically trained for manga/cartoon/draw images using PonyDiffusion. Concerning realistic images the other versions of this Lora (for SD XL and SD1.5) are more performing.

Sampling steps:

About 50-70 sampling steps.

Clip skip:

Remember to set clip skip to 2

Additional istructions

-          The triggering keyword should be preceded by a color. Lora was trained with black, tan and white colors, but a good prompt should render also many other colors.

Black RealNylonFeets

Tan RealNylonFeets

White RealNylonFeets

-          There are some different particulars than can be rendered, like a reinforced toe nylon or painted toenails, that can be triggered by using the following tokens:

RealNylonFeets reinforced toes

Painted toenails

-          Moreover is better to specify what kind of nylonwear is requested (Pantyhose, Stockings) adding a specific tokens:

pantyhose

stocking

For this aim specific Loras can be added to the prompt, like:

PonyRealPantyhose

PonyBlackRealStockings

WARNING: The details level of this Lora could drop in case of full body portraits (very little feet) or in case of many different Lora used together. Details can be rescued using inpaint algorithm only on feet, with a very specific prompt focused only on RealNylonFeets triggering words.

Image dimensions

Better result are obtained with a base image of about 1200 px dimension on the long image side with an image width/length ratio of  1.5. After the base generation upscaling is a good practice.

USE DEMO IMAGES PROMPTS AS REFERENCE

Final statements:

1. You are solely responsible for any creative work using this model.

2. You cannot use this model to intentionally produce or share illegal images or content.

3. Furthermore can't use this model for malicious, hurtful, defamatory, fraudulent or political purposes.