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
Remaster of Vantablack and XXX-tended v2 then merged with IVFF GRAYED and Nova18
great backgrounds, expressive close ups, pretty solid prompt adherence. Glossy fur is now maintined with fuzzy fur for more realistic look.
FAQ
Comments (8)
Hey, glad to see you still working on improving the model, another one to test :)
Can I ask for some advice? Using my regional prompter workflow to render complex scenes one of the character often defaults to a completely different species one. I suspect that the prompt I use is too complicated. Should I use simplified character description tags? (You can see examples on my page for the character prompts that I use in different scenes, and after a download the whole prompt visible, the site was not able to read it correctly)
Ive nver used regional prompter. Only used comfyui a handful of times. BUT! I do recommened trying not to have your regional tags overlap in the other boxes. I usually accomplish duo or trip descriptions like this
(fox, male, green eyes, orange fur, blue hat, smirking)
(wolf, masculine, male, muscular, grey fur, yellow eyes, hugging from behind)
encapsulating the entire character and its features can tend to group them together better, it adds wieght to the entire list of tags, so it knows to focus on two characters. but I cant gaurentee it works all the time. lol.
@LatteLeopard Yeah, that was the approach I tried to use in Forge and in early days switching to Comfy, but I had heavy prompt bleeding so I had to figure out a way to counter that (resulted in the aforementioned workflow). Anyway, thanks for the reply, my question based on the fact that with a duo scene where a female cow is present, that side often fails to render incorrectly. Since I tested almost every variable, my last idea is the prompt itself (or the dataset, but I doubt that).
Looking good!! Would you ever consider doing an Anima fine tune with your Yiff In Hell models, or object to someone doing it?
Im working to train e621 tags into anima. at the moment Anima just copies the style furry model or lora but lacks enough knowledge of tags and artists.
Anima is currently missing 866GB worth of data from e621, in which Illustrious has. So theres a HUGE disconnect.
You will see a proper furry models for anima, but first I have to continue the training on my own. Sort of like how NoobAI added the furry content that illustrious was missing.
Finetuning vs Merging are two extremely different processes. Finetuning is also very expensive as I need to use 196GB of VRAM minimum to effieciently traing nearly a TB of data.
@LatteLeopard Yes, I was looking at doing a proper furry Anima finetune, but the storage costs killed me. Anima is already pretty good, and certain models are excellent; just imagine how good they could be with a proper merge or even a finetune!
I'm still learning Metallic Tetra's quirks but some initial thoughts. A unique aesthetic. Much more willing to let in the mid-tones, lower contrast, more "natural" shading and more detail compared to other YIH versions. Lighting is more realistic and complements the shading. Posing is more dynamic with some quite inventive posing of characters. Overall less "artificial" in feel.
Personally I still find myself warming up other versions of YIH for the rubbery, wet, hyper, 2.5D look I'm addicted to, but I feel like in terms of appeal Metallic Tetra has its' own.
If it were me I'd take the philosophical direction of Metallic Tetra and go one way as more "artistic refined natural" and take YIH its' own way for "maximalist AI visualistic style".
why cant we use the old one -_- the new one is so cleaned up, it loses its soul.
the XXX model was better. is that still selectable?