"VCR Head Cleaner" - oh honey, they're just called Poppers (ZIT, FLUX, Pony & SDXL)

🎶 I feel the Rush.. addicted to your touch 🎶... of room deodorizing freshness!

FLUX 2 Klein 9B v2: This pride month, enjoy the new and improved Flux 2 Klein version! Less body horror, more debauchery!

I wanted to see if I could create a self-contained LoRA for this concept which frankly often involves aspects that the base Flux 2 Klein model isn't going to be able to generate normally - without having to resort to anatomy-helper LoRA stacking or using a custom merged checkpoint.

The goal was for the lora understand not only an object, and use of it, but also anatomical and more complex compositional aspects as well. So it knowing the concept involves smelling, not drinking, from the little naughty demon vile, it should also understand how to generate male genitals and compositions involving sexually intimate moments between two, or more, men who love each other's respective genital-ports (butt stuff).

Q: Does the LoRA do all of that? Yes, yes it does. Q: Does it do it perfectly? A: You must be new here. However it is mostly successful if you give it a good prompt and not just phone it in with a few line prompt. Even then it will be successful about more than half the time so either try again with different seeds or make corrections via i2i process. The good news is when it messes up , it doesn't mess up that badly and are generally easy corrections to make.

The image gallery gives example outputs and associated prompts, with base config settings to get you started.

FLUX 1.D Version 2: Based on a much better dataset in quality and quantity with a different captioning strategy - This version is much more flexible and greatly reduces any body horror with complex compositions/scenes than version 1.5, so you won't need to do much, if any, img2img corrections. If you're going to make a nude generation, a peen LoRA or peen-friendly checkpoint is highly recommended. Images in the model example gallery are txt2img examples.

Z-Image Turbo Version: Trained with an upgraded dataset with only HQ images, approx 356 total, with a simplified captioning strategy than what I used for Flux. With Z-Image as the base, the results are very good with prompt adherence and not much in body horror. All the images posted in the model gallery are one-shot txt2img generations without follow-up img2img inpaint or upscaling corrections.

FLUX 1.D Version 1.5: I trained using the same training object-in-context approach with my other recent FLUX LoRAs, but this time testing it out with a smaller dataset to figure a slightly different workflow. LoRA size still an issue but I'm testing a few things out so maybe future versions I'll have it figured out.

Anyway, back to this LoRA: The results were a fairly stable LoRA that plays well with character based LoRAs but results may vary depending on how the character based one was trained; I noticed very few of my character LoRAs did not want to play along w/ this one at all while most other ones were perfectly fine using it. I've included a few in the gallery as examples (btw - the gallery shows 3 for the cfgscale, but I actually used 3.5. For some reason Civi's image edit UI doesn't accept numbers with decimals).

A side 'benefit' is, since about a 3rd of the dataset included men clapping their cheeks, it can sorta generate full on sex scenes but don't expect any one-shots if you want to try to do that. If you do try that out, then a workaround is just correct any body horror from the first shot with an img2img inpaint process using the same or similar image generation parameters. I might work on that issue with later versions, if I grow the dataset. A second alternative workaround is that you can just generate the sex scene without it and then come in afterwards with an inpaint pass using it.

For those of y'all that still have or remember those days of VHS VCR players needing head cleaning to make those films pop.. since the 70s, 80s, 90s and thru today! Sometimes seen used in those trouble room areas of a busy house, like the bath!

--Pony v6--

trigger: poppers, smelling, sniffing, poppers, holding poppers,

label color can be specified and some brand labeling (real and not) exists with Rush being the most consistent.

--Pony v5--

trigger: poppers, smellingpoppers, sniffingpoppers, holding poppers

sniffing should trigger a finger against a nostril .. most of the time at least.

--SDXL v1--

trigger: junglejuice

*IYKYK