Type | |
Stats | 255 5,777 3.5k |
Generation | |
Reviews | (55) |
Published | May 22, 2025 |
Base Model | |
Hash | AutoV2 347E65ACAA |
2D Focused Furry Illustrious Model... wowzers.
Illustrious model focused on 2D, traditional, digital- all that stuff, like 90% of other Illustrious models in existence. Not a realism model, can't (-ish) do it, and I don't intend on this model going down that path, that's what this is for.
Model information and details continue below, read before use.
Links are provided below for those who can't run this resource locally.
Version Notes Below:
Version 0.1.5 release.
This version is not 2D focused.
Changes
Improvements
Sharper detail
Less noise at low CFG
More ingrained base style (pseudo-3d porn-slop style), most prompted styles will see some slight adjustment at high CFG but remain mostly intact (except 2D).
Higher detail
Downgrades
Lighting Downgrade, darker images are hard to generate.
Not 2D anymore
Lowered Accuracy
Why the switch from 2D?
It's a temporary change. Future versions will not remain in this style, they will revert towards a more 2D base aesthetic.
Why though?
To fix underlying issues with detail generation and heavy noise on DPM++ 2M at any CFG level. It's mostly fixed, at the cost of 2D style. I do pay attention to complaints. And I'm not going to bulk merge BananaSplitz, IffyMix, Tundra, OAF, or any other decent 2D model by someone else to resolve that. Mainly because it's in bad taste, and also because they're mostly derived from the same few models. Typically, I do not release these model iterations, as I feel they go against the intentions of this specific model. Believe it or not, I do have intentions for every model I post. However, Time Constraints™
This should be a sufficient version improvement until I can properly sit down and work.
For the meanwhile, Porn-Slop Model- release the slop.
<About The Model>
It's an illustrious furry model, designed to output furry content. That's not all it can do but it's where I placed my focus while merging, along with character accuracy. It understands the majority of artists' styles to varying degrees and most concepts. Compatible with all Illustrious Loras and many NoobAI Loras, though use of those aren't necessary unless you're prompting for very specific niche concepts, characters, or certain styles. I don't show much of what I make (if I did, there'd be over 10,000+ images on this model alone), but I have posted some images to reflect some, but not all, of the model's capabilities.
Wish to use this model but don't have the hardware to run locally?
You can run this model for free on the sites linked below (and here):
(Remember to read and follow the ToS of each site.)
SeaArt.AI
https://www.seaart.ai/models/detail/5548eaa0088cef536fb6cacb88cc038a
Tensor.Art
https://tensor.art/models/866189242307482865
PixAI.Art
https://pixai.art/model/1829757967386098908-Illustrious-Lima/1882395076142416453
Yodayo
If there's a model hosting website that I don't know about that you use and wish to generate on, let me know and I'll look into providing the resource on the site.
Resource currently available on this site, future versions will be up to usage discretion on whether demand warrants investment. If a version is unavailable and you wish to use it on-site, let me know.
This resource is also on this site now, and I will look into keeping it available through auction and bids. If you wish to bid to keep this model available for site-use, it would be appreciated.
If you wish to keep a specific version up for generation, please bid. Normally, this is a non-issue, however with CivitAI losing card processors, I can't pay to sustain the buzz necessary for multiple versions being up simultaneously.
<Usage Tips>
CFG: 2 - 9
Steps: 20 - 50
Sampler: DPM or Euler, I recommend DPM++ 2M but Euler A is also perfectly valid.
Scheduler: Karras is recommended,
Resolution Size: 796 - 1,700, the model excels within this range. When exceeding the upper range, prompt intelligently and use the resolution space wisely to avoid image subject deformity at very high resolutions (1,900+).
My Settings
My recommended settings (settings I generally use):
CFG: 2.5 - 5 (Higher chance for monochrome/sketch style at lower CFG's, I would suggest using the negative prompt to counteract this or prompting for style like normal. When it comes to style prompt, [i.e. actual artists] I would recommend CFG's around 2.5 to 3.5, but if you like overbaked images 7.5 is good too.)
Steps: 35 (Sometimes I go higher, sometimes lower. I typically go for 50 on other models because that's just how I gen. That's not needed with this model, 35 is a good baseline)
Sampler: DPM++ 2M
Scheduler: Karras or Automatic
Resolution Size: Angle and pose dependent
Use however you please, feedback is appreciated, crediting is unnecessary.
Feel free to post whatever images created in the gallery below.
I'm not responsible for generations produced with this model, generate responsibly.