Please read the entire post for instructions on how to use the lora

The model is trained using a new dedicated dataset, focusing on sheer pantyhose (tan color or black). The first aim was to improve the appearance of transparent tights for the Realistic Vision model, where legwears have often an opaque appearance (see picture above), and most of the times with artifacts (random horizontal dark bands etc.).

This Lora, based on SD 1.5, is optimized for Realistic Vision (checked also with 3.0) but also gives good results with other models, by changing the weight of the model or the weight of the trigger word.

Activating Lora:

<lora:RealPantyhose:1.0>

Trigger word:

RealPantyhose

for tan pantyhose use: tan color RealPantyhose

for black pantyhose use: black color RealPantyhose

Sampling steps recommended: 25-40

CFG Scale: 7

CHECKPOINTS TESTED

Model and trigger word weight

REALISTIC VISION V2.0, V3.0 and V4.0 (new!!!!):

weight model suggested: 1

trigger word weight: 1 for tan color, 1-1.2 for black color.

REV_ANIMATED:

weight model suggested: 1.1-1.3

trigger word weight: 0.8-0.9

XXMix_9realistic:

weight model suggested: 0.9-1

trigger word weight: 1

DELIBERATE_V2:

weight model suggested: 1 for tan color, 1.2 for black color.

trigger word weight: 1.2

DREAMSHAPER_V6.31:

weight model suggested: 1.

trigger word weight: 1 for tan color, 1.2 for black color (sometime may be more effective the use of expression ((black color:1.2) RealPantyhose:1.0) ).

CHILLOUTMIX:

weight model suggested: 1.

trigger word weight: 1 for tan color, 1.2 for black color (sometime may be more effective the use of expression ((black color:1.2) RealPantyhose:1.0) ).

If prompt is very long and structured, inpainting is suggested to obtain a more effective result.

Effectiveness on more checkpoints will be tested.

On Realistic vision this Lora is compatible with Opentoe heels/sandals with legwears. The use of Opentoe lora is reccomended with inpainting algorithm.

Possible future release may include white sheer pantyhose color.

Feedbacks well accepted.

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.