Sign In

BlackRealFishnetsP for SDXL – Thin mesh black fishnet pantyhose

124
1.6k
41
Verified:
SafeTensor
Type
LoRA
Stats
1,635
Reviews
Published
Jan 27, 2024
Base Model
SDXL 1.0
Trigger Words
BlackRealFishnetsP
Hash
AutoV2
825533D4AF

The Lora model is specifically trained to render Black Fishnet pantyhose (thin mesh) for SDXL.

There are more Loras related to pantyhose theme:

-          for regular sheer pantyhose for SDXL (also SD1.5 available, follow link) , you can download RealPantyhose for SDXL

-          for nylon feet for SDXL (also SD1.5 available, follow link)  you can download Nylonfeet for SDXL

-          for opentoe heels with nylon for SDXL (also SD1.5 available, follow link)  you can download Opentoe heels with legwear for SDXL

 

A native 1024x1024 BlackRealFishnetsP set was selected to train an XL Lora, with reliable thin mesh fishnet layout.

If you like this Lora, please REVIEW IT, use it and SHARE PICTURES.

For a great output please read the following instructions.

Rendering the thin mesh pantyhose pattern details is a very challenging issue, due to the maximum allowed dimensions of the training set (1024x1024) that is barely enough to train a model for a very thin pattern. Results are definitely better than base image without Lora, but some tricks for best results are explained in the following.

Triggering prompt keyword:

BlackRealFishnetsP 

Lora weight:

A value of 0.6 or 0.8 is highly recommended. Higher values can trigger artifacts.

So a good activation keyword for lora is:

<lora: BlackRealFishnetsP_XL:0.6>

This Lora could be used both with realistic or manga checkpoints. Concerning realistic checkpoint Formula XL was used to generate the demo gallery.

Sampling steps:

About 40-60 sampling steps, with Euler A for first generation and DPM ++ SDE for inpaint.

DPM ++ SDE seems to have more realistic output for mesh patterns.

 

WARNING: Fine details of this Lora require in most of cases to use the inpaint algorithm only on legs, to improve the fishnet pattern  with a very specific prompt like the following.

Raw Photo, BlackRealFishnetsP, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3

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.