It is important to read the description of each version please!! -->

Being my first trained LoRA model, I didn't really know what I was doing very well and I don't know how versatile the model can be. So below I leave you some recommendations for use, the result of the tests I did.

- The recommended weight is between 0.1 - 0.3
To use it together with character LoRAs I recommend a range between 0.2 - 0.3

(Creating images with this model and without some LoRA character model to accompany it does not give me good results... Maybe it's just me that this happens to me...)

- Mandatory trigger words: wind lift, wind lifted skirt,

- You can use or ignore the following prompts, BUT I recommend that if you want to prevent your results from deviating from what you are looking for, you add SOME prompts you don't want to the negative prompts (see the "!" symbol in my example images): showing her ass, from behind, leaning forward, bent over, all fours, cameltoe, thigh gap, cowboy shot, from front, from below, looking back, looking at viewer, ass, panties, no panties, ?????, ????, close up,

(The "close up" tag can change the result quite a bit. Keep this in mind when generating your images.)

- The model often tends to dress the subject in a "school uniform", so add it to the negative instructions if it is not what you are looking for.

Help for "all fours"

- Describing the background/location can help improve image generation: on floor, on grass, on bed, wood floor, indoors, outdoors, etc, etc...

- Adding tags of different positions to the negative prompts also helps: standing, lying, sitting, etc.

Help for "leaning forward/bend over"

- Likewise, add descriptions of the environment to help generate the image (for example, if you intend to obtain a view from below, use "blue sky, clouds, etc" for a low angle) or add labels such as "balcony or table" to help the "bent over" tag.

Help for "from front"

-The "from front" doesn't work very well xD

But after a few tries you may get good results.

Help for "close up" images

It is quite difficult to obtain those types of images, but after several attempts with different combinations and simple prompts you can get good images.

Clarification:

1. The force range I used, with the character LoRAs, in all the example images in this post was always the force recommended by their respective creators.

2. Highres fix on all sample images: 4x-UltraSharp

3. Yeah, Yeah... I know that "by knowing well what you are doing, you can achieve the same or better results without the need for a LoRA", but as I said before, MAYBE it will help someone (even with errors in the LoRA).

4. Yeah, Yeah... I also know that the concept of LoRA is sometimes wrong and that such and such is not considered such and that blah, blah, blah... Shh! Don't ask! Just enjoy! (If the model works for you xD)