IffyMix V6
A true continuation from V 5.0 (not the HD versions or Re:mixed)
Better posing
About the same prompt adherence
Ever so slightly more detailed cartoonish look. But not by much
Lora compatibility high (as no LoRA's that interact with visuals are implemented)Notice your prompt used in the cover images? DM me and ill send you buzz
IffyMix Re:Mixed v2.0
A continuation of polishing the Re:Mixed version.
smoother, cleaner look.
wider style shifting.
artist tags work even better.
prompt adherence is low end of top tier.
natural language works when guided with tags.
Lora compatability is very high.IffyMix Re:Mixed v1.0
A complete remerge of the base models.
updated to to be merged with more modern models
Heavier toon look
Hi-Res Fix - No more orange tint
IffyMix V5.0
Its finally here. Iffymix with a base made of V2,3 and HD1
This has a nicer, smoother pastel like effect.
I feel that this mix gives surprisingly creative results.
Euler A, LCM, and UniPC samplers only!
IffyMix HD Remix V2 - EULER / EULER A ONLY
Various EULER A methods work! ( Automatic / SGM / Beta )
The "HD" like remix using IffyMix v2 + Iffmix v3 as the base.
!!!NEW RULE 34 V2 DATASET INCLUDED!!!
Contrast + Brightness precisely fixed.
Solid prompt adherence
This version continues with the vibrant cartoonish aesthetic.
I would say this version is slightly less 2.5D by just a smidge.
Background detail is improved mildlyIffyMix HD Remix V1 - EULER A IS PREFERED.
An "HD" like remake of iffymix (contains v1-v4)
Produces a clean, vivid, and a wonderfully polished cartoon aesthetic with a mild painterly effect.IffyMix V4 - STRICTLY NON DPM++ 2M KARRAS
Launching iffyMix...
Update found. Apply? [y/n]
V4 Released! (Online starting 6/26/25 @ 19:00)!!!! Currently Online !!!!V4 Update + Preview + Suggestions + unreleased goodies
https://civarchive.com/articles/15470/iffymix-v4-suggestions
Click to help shape and polish off Version 4!
V3 released
Some visual refinements made, added some lora's to increase anatomy, pose and dynamic angles. Increased R34 Lora strength. More predictable results, which sadly means some random creativity has been lost. Background detail has improved. Illustrious v2.0 has been merged in so higher quality gens all the way up to 1536x1536 can be done. Mileage may vary as this is experimental.
V2 Released!
This version adds some visual refinements as well as a huge update in tokens. I've merged in R34 tags/database, which was curated by iamddlta, creator of Pornmaster and it's variants.
This not only has wildly increased how good it gens explicit content, but the accuracy of anatomy and prompt adherence have also skyrocketed.
IffyMix - A Revamp of the best version of YiffyMix.........V51
Whats Different about this version besides its V51 + NoobAI?
Unbaked horrendously noisy lightning step before merging.
Completely prunes noisy, signature filled model, ChromaMix and its variants.
Merged with high quality models.
Restored its natural style's cartoonish look.
Parameters:
CFG - 4.5, seems to be the sweet spot.
Steps: 20 -30
Euler A
Tons of artist tags that sucked on NoobAI, do awesome on here. Totally unintentional, but its something I came across.
Quick Start Prompt
POS+
masterpiece,best quality,amazing quality, absurdres, anthroNEG-
bad quality,worst quality,worst detail,sketch,censor, text, ui, signature, patreon,Description
A complete re-merge of the base models.
A complete Re-merge LoRA's
Pruned outdated models
Re-cooked base with modern models
FAQ
Comments (9)
Stop making these foxes so hot I'll cream myself
Yeah, I keep telling myself the same thing. But here I am making more and more of him.
Hm, interesting. The "re:mixed" version seems thus far the best performing model.
What's peculiar and unsurprising is what it prints with no prompt.
I wonder what's up with all the cat collars with little bells on Questionable subjects?
and if you're wondering what "questionable subjects" are, don't worry, if you run the model with no prompt for a hundred images, you'll see what I mean
I use A1111/Civitai generator. So its a bit hard to replicate what you are asking. But sounds odd. Im glad it works good though when used as intended tough lol
Upload a pic of it lol!
@LatteLeopard I'm afraid that posting a picture of "skinny chibi shortstack without the booba, butt, thighs and wide hips features" in explicit positions would be unadviceable. :- )
https://civitai.com/images/108539071
though as you may see, this image features only a negative prompt
(naturally, having no positive prompt, the outputs are very random)
Roughly 1 in 8 of promptless generations feature such peculiar subjects, sometimes with the cat collars, sometimes without. Usually the cat collars are present in 'rougher' compositions. Curious association!
That the mixed datasets contain such things, comes as no surprise to me.
What I find odd is the frequency of such generations, given the lack of actually trying to conjure such subjects.
@VeerGeer Very interesting! I couldnt even begin to explain why or how that happens.
One thing I can say is that IffyMix XL is meant for beginner prompters
If you give basic prompt it will be creative for you. More so than my other models.
@LatteLeopard It's just "contamination" from the various pr0n LoRAs mixed in, where the authors may have trained them on Less Desireable Things without publicly stating it.
(shocked pikachu dot jpeg)
In fact, some less kind types would likely describe the model as "overcooked" as it prints almost exclusively pornographic images, and almost all of them rather pristine-looking rather than a vague jumble in the shape of an image as an "uncooked" model.
(e.g. if I repeat the same test on one of the 'base' models like noobaiXLNAIXL_epsilonPred11, the outputs are wildly varied and mostly a jumble of pixels)
The practical difference is just that the 'uncooked' model has more flexibility in what sort of things it Can depict, while the 'cooked' model mostly stays within its comfort zone.
the actual rubber-meets-the-road difference is that the cooked model actually does what you want it to do, and behaves much more predictably, which is desireable in the context of image creation (e.g. through krita-ai-diffusion) as its limitations can be worked around
@VeerGeer Yeah thats pretty much spot on. Were changing the weights of the original NoobAI/Illustrious to more easily get the prompts to adhere to furry, anime, 2.5d, 3d and ETC.