Thành viên PixAI
PixAI
PixAI
Generate
Sign in
Trang chủ
Tạo
Mô hình
Studio
NEW
Cuộc thi
Tạo bằng Mio.2

Conversational creation

Hộp công cụ
NEW
Guide

User LoRA

XL
Khác

NAI-Style Inflatables (PonyXL)

#Furry

Công cụ AI

  • OC Maker
  • AI Anime Generator
  • VTuber Maker
  • Sonic OC Maker
  • Hazbin Hotel OC Maker
  • Anime Character Creator
  • AI Figure Generator
  • Genshin OC Maker
  • All AI Tools

Khám phá

  • Thẻ Đang Thịnh Hành
  • Xếp hạng
  • Thị trường Mô hình
  • Cuộc thi
  • Tin tức

Giới thiệu

  • Guide
  • Cách sử dụng PixAI
  • Tsubaki.2
  • Gặp gỡ Mio
  • Quy tắc nội dung

Giá & Trợ giúp

  • Thành viên
  • Gói tín dụng
  • Liên hệ

Ứng dụng di động

  • Tải ứng dụng PixAI
  • App Store
  • Google Play
© 2026 PixAI
  • Điều khoản dịch vụ
  • Chính sách quyền riêng tư
  • Chính sách bản quyền
  • Attributions
  • Luật Giao dịch Thương mại Đặc định
NAI-Style Inflatables (PonyXL) - AI Model cover image
Đã tải lên vào
08:03 28 thg 4, 2025
Lượt sử dụng
11.1k
Đánh giá
Xuất sắc  (1)
Từ khóa

plinflatable

Quyền
  • Allow image generation & sharing
  • Cho phép người dùng tải xuống mô hình của bạn
  • Sử dụng thương mại

Recommended LoRAs

[IL v0.1] Gabriel - Granblue Fantasy | ガブリエル グランブルーファンタージ (3 costumes) - AI Model cover image

User LoRA

[IL v0.1] Gabriel - Granblue Fantasy | ガブリエル グランブルーファンタージ (3 costumes)
12
Mornye (Wuthering Waves) - AI Model cover image

User LoRA

Mornye (Wuthering Waves)
1
Iuno (Wuthering Waves) - AI Model cover image

User LoRA

Iuno (Wuthering Waves)
5
Folded Tentacles View from side - AI Model cover image

User LoRA

Folded Tentacles View from side
0

Mô tả

Version 2.0.0Okay, 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 - plinflatableDegree of realism - realistic, draw over, digital artMaterial - matte, glossy, ultraglossPerspective - low angle view, high angle view, three-quarters view, side view, front view, birdseye view, oblique, tiltedValves - valve on (location) - add "extra valves" to the negative promptPoses - on front, on back, leaning up, laying, standing, sitting, hand(s) on (location)Water - floating, partially submerged, clear waterHandles - 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 detailsSide view handles tend to get mangled more often than notCreatures that are often depicted with jagged mouths have less consistent open smiles and permagrins"realistic" tends to have a blue tintNOTE: the previously unmentioned "no valves" tag in 1.0.0 is not present in 2.0.0 - additional negative prompting is requiredIllustrious version when?When everything stops being tinted green. Things aren't tinted green. Some are blue, apparentlyAs usual, reach out if you find any glaring issues I missed.Version 1.0.0After 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 - plinflatableDegree of realism - realistic, draw over, digital artMaterial - matte, glossy, ultraglossPerspective - low angle view, high angle view, three-quarters view, side view, front view, birsdeye view, oblique, tiltedValves - valve on (location) - add "extra valves" to the negative promptPoses - on front, on back, leaning up, laying, standing, sitting, hand(s) on (location)Water - floating, partially submerged, clear waterWhat's new:Now fairly cooperative with portraits, not just full body imagesDramatically improved material tagsShape tags - "slim," "toy proportions," and "thin arms" can help achieve (or discourage) a certain form factorKnown issues:Does not play nicely with handles - tries to make them into valvesLake backgrounds confuse the skyline with another waterlineClose-up backgrounds for realistic and draw overs are grainyOther notable tags used in training:Species - mizutsune, wickerbeast, dragon, moth, lycanroc, dialga, wolf, espeon, (alolan) vulpix, lion, kobold, dragonite, absol, lugiaCloud cover - partly cloudy, overcast, storm cloudsLocales - beach, lake, ocean, river, mountainsVersion 0.6.1Many, many changes. Most for the better, some not so much.What's the same:Trigger word: plinflatableTrained on: SFW NAI outputs of inflatables (but more this time)Degree of realism/style: realistic, drawoverWhat's different:More consistent generalizationValve location tags - "valve on thigh" is now "valve on hip"Perspective tags - now uses "X view" rather than "X angle" to hopefully improve consistencyImproved valve placement - more receptive to locations other than "hip"Known issues:Struggles with "zoroark" and "absol"Still struggles with valve placement consistency, duplication, etcBackgrounds are often muted and require some promptingThe usual culprits (limbs, etc)Beach/lake backgrounds HEAVILY biased towards realismWater can come out murkyNotable tags used in training:Realism: realistic, photo, drawover, digital artPerspective: high angle view, side view, three-quarters view, low angle view, birdseye view, oblique, tiltedLocales: lake, beach, ocean, riverPoses: laying, standing, on front, on side, on back, leaning up, sitting, hand(s) on cheek/chest/belly/etcProps: leaning against rocks, lounge chairCloud Cover: partly cloudy, overcast, storm cloudsMaterial Finish: matte, glossy, ultraglossValves: no valve, valve on thigh/shoulder/tail/hand/bellyOriginal 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: plinflatablePrimarily uses tags. Should have decent understanding of the following:Species: mizutsune, wickerbeast, dragon, moth, koi (somewhat)Degree of Realism: realistic, drawover - biased towards realismShould have vague understanding of the following:Certain Pokemon: vulpix, lugia, lycanroc, dragonite, absol, a few othersValve locations: Belly, thigh, shoulder, tail, no valves - it's fairly stubborn, thoughHas frequent problems with the following:The Classics: paws, feet, wings, etcValve Duplication: "extra valves"/"multiple valves" in negative helps somewhatHandles: (the training set only had a few images with handles on thighs)Color Bias: Red and purple are frequent culpritsI'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.

Bình luận