Version 2.0.0

Okay, first off - a huge thank you to everyone who poked around with previous versions. I had zero intention of continuing to work on this LoRA outside of any critical adjustments, but as time went on it sunk in that this was no longer just a personal project.

Weeks turned into months, dataset tweaks turned into entire overhauls, and eventually I finally managed to cobble together what I think is a worthy successor to 1.0.0...

Almost.

The core additions are there, but there's still a lot of fine tuning to go. The dataset needs a decent chunk of balancing yet, but it should still be serviceable enough to get some use out of.

There were two main things I wanted to try and add here - handles and mouths. The permagrin is a signature element of the pooltoy look, and 1.0.0 just... couldn't. Things have dramatically improved here, but the finer details are still a bit of a crapshoot (as always). Next, handles - the other main pooltoy-ish thing 1.0.0 just never did.

Again, 2.0.0 isn't nearly as final as 1.0.0 - please bear with me as I continue ironing things out.

Enough rambling.

Quickstart Tags:

• Trigger word - plinflatable

• Degree of realism - realistic, draw over, digital art

• Material - matte, glossy, ultragloss

• Perspective - low angle view, high angle view, three-quarters view, side view, front view, birdseye view, oblique, tilted

• Valves - valve on (location) - add "extra valves" to the negative prompt

• Poses - on front, on back, leaning up, laying, standing, sitting, hand(s) on (location)

• Water - floating, partially submerged, clear water

• Handles - handles on hips, handles on shoulders (best with front/three-quarters views)

• Expressions - closed smile, open smile, permagrin, pl_sawgrin (jagged teeth)

Known Issues:

• Forest backgrounds are rough and tend to decrease consistency of other details

• Side view handles tend to get mangled more often than not

• Creatures that are often depicted with jagged mouths have less consistent open smiles and permagrins

• "realistic" tends to have a blue tint

NOTE: the previously unmentioned "no valves" tag in 1.0.0 is not present in 2.0.0 - additional negative prompting is required

Version 2.2.2 Addendum: Consistency should be slightly improved, plus a mostly functional Illustrious version.

As usual, reach out if you find any glaring issues I missed.

Version 1.0.0

After a lot of learning (and trial and error), this finally has reached a point where it has a decent grip on everything I originally aimed for. Hopefully others can get some mileage out of this too.

If you find any notable weaknesses or issues you'd like me to try and correct, feel free to reach out - but I can't promise anything.

Quickstart Tags:

• Trigger word - plinflatable

• Degree of realism - realistic, draw over, digital art

• Material - matte, glossy, ultragloss

• Perspective - low angle view, high angle view, three-quarters view, side view, front view, birsdeye view, oblique, tilted

• Valves - valve on (location) - add "extra valves" to the negative prompt

• Poses - on front, on back, leaning up, laying, standing, sitting, hand(s) on (location)

• Water - floating, partially submerged, clear water

What's new:

• Now fairly cooperative with portraits, not just full body images

• Dramatically improved material tags

• Shape tags - "slim," "toy proportions," and "thin arms" can help achieve (or discourage) a certain form factor

Known issues:

• Does not play nicely with handles - tries to make them into valves

• Lake backgrounds confuse the skyline with another waterline

• Close-up backgrounds for realistic and draw overs are grainy

Other notable tags used in training:

• Species - mizutsune, wickerbeast, dragon, moth, lycanroc, dialga, wolf, espeon, (alolan) vulpix, lion, kobold, dragonite, absol, lugia

• Cloud cover - partly cloudy, overcast, storm clouds

• Locales - beach, lake, ocean, river, mountains

Version 0.6.1

Many, many changes. Most for the better, some not so much.

What's the same:

• Trigger word: plinflatable

• Trained on: SFW NAI outputs of inflatables (but more this time)

• Degree of realism/style: realistic, drawover

What's different:

• More consistent generalization

• Valve location tags - "valve on thigh" is now "valve on hip"

• Perspective tags - now uses "X view" rather than "X angle" to hopefully improve consistency

• Improved valve placement - more receptive to locations other than "hip"

Known issues:

• Struggles with "zoroark" and "absol"

• Still struggles with valve placement consistency, duplication, etc

• Backgrounds are often muted and require some prompting

• The usual culprits (limbs, etc)

• Beach/lake backgrounds HEAVILY biased towards realism

• Water can come out murky

Notable tags used in training:

Realism: realistic, photo, drawover, digital art

Perspective: high angle view, side view, three-quarters view, low angle view, birdseye view, oblique, tilted

Locales: lake, beach, ocean, river

Poses: laying, standing, on front, on side, on back, leaning up, sitting, hand(s) on cheek/chest/belly/etc

Props: leaning against rocks, lounge chair

Cloud Cover: partly cloudy, overcast, storm clouds

Material Finish: matte, glossy, ultragloss

Valves: no valve, valve on thigh/shoulder/tail/hand/belly

Original Description (v0.2)

A LoRA trained on SFW NAI outputs of inflatables (~75, x2 including mirrored versions). I'm new to this training thing, so don't expect much.

Generally has a lapped-seam-pooltoy look. Mostly trained on feral subjects.

Trigger word: plinflatable
Primarily uses tags. Should have decent understanding of the following:

Species: mizutsune, wickerbeast, dragon, moth, koi (somewhat)

Degree of Realism: realistic, drawover - biased towards realism

Should have vague understanding of the following:

Certain Pokemon: vulpix, lugia, lycanroc, dragonite, absol, a few others

Valve locations: Belly, thigh, shoulder, tail, no valves - it's fairly stubborn, though

Has frequent problems with the following:

The Classics: paws, feet, wings, etc

Valve Duplication: "extra valves"/"multiple valves" in negative helps somewhat

Handles: (the training set only had a few images with handles on thighs)

Color Bias: Red and purple are frequent culprits

I'm sure I'm missing something, but this will do for now.
Seems to work decently well with the couple other PXL inflatable LoRAs that I tried. May be worth experimenting with.