Some cover images are prompts created by you guys and alot from @GayPurpleSkunk (A pro at genning with furry models) If you notice you're prompt DM me for compensation!
WOW! You guys got both XXX-tended editions online from bidding! Y'all really like that series, eh?
Version VANTABLACK (READ ME)
Updated to MegaCock V2 and REED_FURRY_MIX
Color, vibrancy, and contrast are adjusted.
Prompt adherence is more sensitive
Clean, crisp, HQ output.
any blotchyness or blur removed.
Version XXX-TENDED v2.0 (READ ME)
This version uses an entirely different base model known as "Mega Cock"
it is appearently a checkpoint trained model focused on delivering highly detailed, cinematic, and creativity for NSFW, Fantasy and anime content. Still delivers that glossy, shiny, 2.5D look, but with more detail and better posing.
Anatomy & Poses - 9/10
Seems to get creative with poses, dynamic angles, shockingly good at getting full body or 3/4th body shots with good eyes.
Also appears to do duo very well with eyes, and full body.
fingers, mostly gives furries 4 or 5 fingers. Mostly 5, but here and there 4 fingers in springled in. Chance of finger failure is pretty low.
Prompt Adherence - 7/10
Great adherence, can get good results with a basic detailed prompt, but detailed prompting results in a finer tuned result.
Version XXX-TENDED (READ ME)
Base aesthetic cleaned up.
Better anatomy,
Less male gender bias.
I know you guys love using Yiff in Hell for the huge glossy boobs.
and this model amplifies that affect.For my gay bros, thick shiny asses and glossy thick cocks are locked and loaded.
Clean, Smooth, Glossy, as ever.
Awesome NSFW knowledge.
High Customizable via LoRA's for NSFW concepts
Backgrounds are about the same as V3/V4 ish.
Further Improved chances of perfect outcome without inpainting
Extremely strong prompt adherence
This means more detailed the prompt, the better the outcome
This almost understands natural language in a scary accurate way sometimes.
No need for prompt strenghts of (1.3) or higher. Recognized tags are already potent
You can choose to extend the power of each of these baked in LoRA's to finetune your results.
Rule34 V2
Pornmaster add detail
Gay Porn Extender
Gay Painterly Mix (Bara/Kemono)
All of these work harmonously if you dont want to add more of them to the model, and wont affect other lora's you choose.
Try out these embeddings too if you hate writing quality tags!
Recommended Settings
Steps: 24
Resolution: Portrait(832x1216), Square(1024x1024) Landscape(1216x832)
HiRes Multiplier: 1, 1.2, 1.5(best on A1111 and its forks)
Hires fix steps: 12
Sampler: Euler A(Auto, Beta, SGM Uniform), LCM,
CFG 2 - 4
Supports 512~1536 resolutions from its Illustrious 2.0 base
Recommended Positive Prompts
2.5D Photorealistic / Fuller Realism
masterpiece, ultra-HD, photorealistic, impressionism, high detail, depth of field, dynamic lighting, best quality, very aesthetic, 8k, best quality, realistic, muted colors palette. anthro
2.5D Semi-Realism with impressionism(painterly)
masterpiece, ultra-HD, impressionism, high detail, depth of field, dynamic lighting, best quality, very aesthetic, 8k, best quality, anthro,2.5D-3D (Ultra Quality)
masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, 32k, UHD, absurdres, newest, scenery, furry, anthro2.5D Semi-Realism (High Quality)
masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, furry, anthro,2.5D (Simple Quality)
masterpiece, best quality, newest, absurdres, highres, anthro,__________________________________________________________________________________________________
Version 4
Total modification of base aesthetic.
YES - the rule 34 v2 is still in this.
Suprisingly creative, good dynamic poses
Cleaner, Smoother, AND GLOSSY
Background details are slightly decreased
Backgrounds are more coherent and fitting.
Prompt Adherence is pretty solid.
__________________________________________________________________________________________________
Version 3
Big imporovements on base aesthetic.
Increased creativity and poses
Cleaner, smoother, 2.5D look
More detailed backgrounds
__________________________________________________________________________________________________
Version 2
One of the big things I wanted to announce with this version, is the addition of the all new Rule 34 dataset V2.
This will greatly improve prompt adherence, aesthetic and NSFW knowledge.
ALSO IF YOU NOTICE YOUR PROMPT USED IN THE COVER IMAGES DM ME FOR COMPENSATION.
READ ME!
Includes rule 34 dataset
Includes training data from top rated furry images on Civitai and e6ai.
Highly detailed backgrounds
Has really good knowledge of sex acts and positions.
Can do 2.5D all the way up to semi-realism.
Recommended Settings
Steps: 30
Hires fix steps: 15
Sampler: Euler A(Auto), DPM++ 2M(karras), DPM++ 2M SDE (Karras)
CFG 4.5
Resolution: supports 512~1536 resolutions
__________________________________________________________________________________________________
Description
Basic Recipe List.
Base Model Re-Mixed Recipe
Yiff in Hell V1
Yiff in Hell V2
Nova Furry 12
Supporting Models
Yiff in Hell V3
Hyphoria
Plant Milk - Flax
CiviFur Lora
Rule34 V2 Lora
Goal: A rebalance of glossy 2.5D and flat 2.5D while maintaining clean, smooth, gens
Control your level of realism by how many quality tags you use and which ones.
FAQ
Comments (28)
v3 is a masterpiece. A goat for me. And I don't gen furry. I believe this is the focus of YiffInHell, but even tough the main focus is furry this model is incredible versatile to gen pokemon, human characters, and very aesthetic backgrounds. This is my go-to model, the top 5 in this site. Really interested in this v4 to see what's new. Really excited to try.
Whoever is not using this model, is living wrongly haha
Oh damn i need to get on it then :x
Oh yeah, it can gen humans and anime stuff easily.
these models really function as "anime" models but with better
capabilities for furry tags/concepts/knowledge.
So you should be able to do anything with it.
@LatteLeopard <3
@Fleshcraftergo. is the goat
One of the most stable model for furry and none-furry image generation. Love every update and Version 4 is a masterpiece. With or without LORAs or embeddings, you get what you want. Great work!
awwwww yeah buddy,TY! Glad to hear youre lovin' this model!
Does V4 have a bias to males? Despite not changing my prompts from V3, I'm getting very small breasts/outright males fairly frequently.
While the yiff in hell models are still female baised, they are tuned to dilute the effect as much as possible. but creating female charcters I found easier during testing. I actually ran into the issue you are describing, but with male characters becoming female.
Maybe change around the prompting a bit. The text encoder for V4 might like more detail about gender specific traits.
@LatteLeopard So upon further experimentation, it seems to dislike the word 'gigantic' - I swapped back to huge (look my gals' proportions tend to grow over time and then I scale back again, it's a thing :V) and suddenly working fine every time, no misfire tiny tits/males. Very odd.
Yiff in Hell really is my go-to model; very stable and versatile. I'm a huge fan overall, and so far the results of the V4 version are excellent, even better than the already fantastic V3.
tyvm! I really cooked hard for V4 to make it as kick ass as possible
(Also posting the comment I made on YiffyMix here since it also applies for this model and might be useful for some people):
To anyone who used this model to gen NSFW for free with blue buzz and are now shafted because of Civitai's new policy: you can still gen NSFW with this model for free on Yodayo. Just make an account there (it mentions phone number or Google login but you only really need to give your e-mail address) and fill in your (optionally fake) date of birth and change the content settings in your profile. It only mentions up to R+ rating but the generator doesn't block X or XXX content (you just can't post it). You get 50 free "YoBeans" daily which you can gen pictures with, which cost 4 credits minimum. They don't stack, so you'll have to use them daily so they don't expire. It's not much, but it's better than nothing.
@LatteLeopard That is called SD WEBUI, A1111 was a person, not a program
@2P2 Yeah that's true, but A1111 is a more familiar term related to SD web ui.
Even on this site they tag A1111, when external generator is detected.
Just didnt want to confuse anyone, not everyone knows that fact.
@LatteLeopard I considered vast.ai, but they only allow crypto payments through services that require extensive KYC, and I don't want to attach my personal identity to my smut (and definitely not through sites like Coinbase or Crypto.com, which both have been breached before).
I'll probably buy a second-hand 3090 one of these days. I've just been putting off local generation because the case of the system I had prepared for it is too small, so I'll need to create a new one which is a bit of work. I was only using Civitai because it was convenient and good enough for my needs (and also free, of course) but that's obviously in the past. ¯\_(ツ)_/¯
@odol You can pay with debit/credit cards.
But its up to you if you rather pay in crypto
or just not use the service at all, for the reasons you stated.
Im not sure if your country blocks payment via bank card.
but for anyone else interested. it does accept normal card payments.
@LatteLeopard I cloned Stable-diffusion but i got a lot artifacts (like signal glitches not multiple hands, but looking past glitches it is +/- I asked for) Do you have any tips how to use your model locally? i run iris graphic and relay don't mind waiting hour or so for result.
Please do not try to troubleshoot it as maybe you just have howto somewhere and I'm lit blind for that.
@wytrzeszcz Im sorrry, I dont really understand the question.
I love this checkpoint, but I'm not a furry. I would love to see a human version, so I don't need to go so heavy with the negatives.
thank you!
You might have an easier time with humans if use it like a species tag.
example: (quality tags), 1girl, female, human, green eyes, brown skin
Its also recommended to through anthro and furry into the negatives.
Ill have to test it out more, I might make a LoRA to humanize it more.
@LatteLeopard Thanks! If you are willing to train a human LoRA for this checkpoint, I can offer you some buzz to cover the expenses, and maybe generate some images for the dataset.
@OptimalOyster You gave me a good idea. Maybe I should make model page with different styles for these models.
This already does non furry stuff amazingly well too. This is my fav for both human and furry stuff.
It should be criminal to make a model this good. I only need to use LoRAs for super niche things otherwise this model does everything I've asked with absolutely stellar results. Yiff in Hell and Banana Splitz XL are definitely some of the best furry models I've used; they both do SFW and NSFW generations extremely well.
Awww damn bro, that makes me so happy to hear.
With a comment that powerfully kind I gotta give props to my peeps who helped build the foundation for my creation YiH V4
@Crody - Nova v12, guides on merging, guides on weighted block merging(advanced)
@Mol_Keun -DeepNavy V3 /DeepBlue V2
@ecaj - Hyphoria
@Ocean3 - Plant Milk - Flax/Oat
@iamddtla - Rule34 V2 and V1 special mix.
@someyoungguy69 - KSM Styled Lora
And interestingly, furry models are always the best for general stuff including humans. I almost only use furry models like this one and 3wolfsmondai for whatever I do.