Update 19.06.2026. Lustify V9 (Zenith) IS OUT!
This is the absolute final version of Lustify built on the SDXL architecture. You can find the full changelog and a breakdown of the new features there. <----------
Recommended Workflow.
Alternative Access & Support: Outside of CivitAI's Early Access, you can get the model via my Boosty.
Just like last time, after the early access ends, there will be a 1-week period where the model is available for "on-site generation only." After that, it will become available for everyone to download.
Alternatively, you can make a direct Bitcoin (BTC) donation, just make sure to DM me after that: 1CoMZvrXtRXbz7BCzdvxifSjHqhaf1yUZs
LUSTIFY
Lustify is a photoreal checkpoint optimized for creating high-quality imagery of women in explicit/sexual scenarios. The model has been trained on a hybrid dataset, meaning it natively understands both Danbooru tags and natural language prompting.
Note: While it has a strong NSFW bias, if you guide it properly, it is fully capable of generating stunning SFW photography, objects, animals, and fantasy environments.
Crucial Points Before You Download:
NOT Pony or Illustrious-Based: This is a standard SDXL checkpoint. Do not use Pony/Illustrious LoRAs with it; they will not work correctly.
Distant Shots & Anatomy Limitations: Like 99% of SDXL models, distant shots can sometimes suffer from distorted faces or hands. This is an inherent limitation of the base technology (4 channel VAE), not the finetune. It is incredibly easy to fix using Inpainting or ADetailer. Please utilize these tools rather than reporting this as a bug.
Experimental Nature: My training workflow involves a lot of unconventional, high-risk experimentation. Because of this, some prompt combinations that worked perfectly on other checkpoints might behave differently here. If you encounter unexpected behavior, feel free to give feedback so I can look into it.
Recomended parameters:
Sampler: DPM++ 2M SDE/DPM++ 3M SDE,
Scheduler: Exponential/Karras
Steps: 30
Cfg: 2.5-4.5.
Highres.fix: upscale by 1.4-1.5, denoising ~0.4
For the distant shots of people you probably wanna use highres.fix and/or adetailer.
Also, use reasonable positive/negative prompts, shizoprompting does more harm than good (with any SDXL model).
Some tags that have a big visual impact with this model:
Camera type tags: "shot on Polaroid SX-70", "shot on Kodak Funsaver", "shot on GoPro Hero", "shot on Canon EOS 5D", "shot on Leica T".
Photography styles: "analog photo", "glamour photography", "street fashion photography", "candid photo", "amateur photo".
Lighting types: "cinematic lighting", "neon lighting", "soft lighting", "dramatic lighting", "low key lighting", "bright flash photography", "warm golden hour lighting", "radiant god rays".
Film types: "Ilford HP5 Plus", "Lomochrome color film", "Fujicolor Pro".
Photographers: Alessio Albi, Martin Schoeller, Miles Aldridge, Oleg Oprisco, Tim Walker.
Others: "film grain", "bokeh", "dreamy haze", "technicolor", "underexposed", "low quality", "lowres"
Alternatively, you can give a read to this wonderful prompting guide by PromptGeek. It has A LOT of useful tips I didn't know about even after years of using SD.
Description
Even though V8 Apex was trained on 1536 resolution, the inpainting version didn't inherit it that much, use that res on your own risk :P. You can use it for the refinement pass though!
FAQ
Comments (54)
Thank you for all of your hard work
New v8 in fantastic. I have posted some images. Could you pin some plz?
all my dreams came true with this one
absolutely addicted to this checkpoint man
Thank you king! Please this is my first time, Any tutorial to set this up. Does it support videos too?
u can only generate images using this model, then use a image-to-video model to turn the image into a video
That turned out fantastic!
Amazing work with the V8, the higher resolutions result in sharp and addictively fun checkpoint! 🩷
The 1536 x 1536 and other resolution variations allow one to make very high quality images, and upscaling on top of that works also if so wishes.
Prompt adherence is quite good and outdoor images, lighting and whole atmospheres come up just right. I admit i did not truly test NSFW-capabilities, but i assume it's there for those who enjoy it, but this is amazingly good checkpoint even for SFW images.. really incredible as an overall checkpoint due to the quality of the images. ^^
Can make quite long and detailed prompts, understands BREAK function node, so can divide and make long detailed prompts, picks up things on 2, 3 or 4 long BREAK'd prompt segments after testing and blends nicely rendering what one intended:
https://civitai.red/images/128202623
This is the kind of work, the higher resolutions functioning properly are things that SDXL can still improve on, so really thankful for your work on it. Hope this inspires others to keep working on SDXL still.
Honestly, if i was not a permanently broke student, i'd donate all the Buzz to you.. but i can send you all the good karma of the universe, and hope some rich oil sheik or crypto-millionaire donates you lots of buzz/bitcoin for your amazing work (i'll send then them karma also to get even more money from somewhere else, thus a win-win to everyone :P), it would be totally deserved.
A huge thank you from me and the silent lurkers of the community! Much love and warmth to your spring-times! 🌞🩷
* humble cute courtsy bow *
tldr: V8 is currently the best SDXL checkpoint in quality of the images.
Just that you know the result structure of your upscaled result is horror most likely you never saw a correct 7 mpixel digital photo ever to call this quality.
Technically i will only say 2 word "Wavelets/Fractals" ugly result
@alekhammes966 Sorry but that was quite silly thing to say. I do own an actual quality digital camera (used in professional level), but i compare SDXL checkpoint quality against OTHER SDXL checkpoints, not against technology made to dish out quality images from a system level from an actual real life, and not you know from a virtual reality created in seconds lmao. Check out and compare the original SDXL checkpoints, then many of the other creators even new ones maximum potential quality.. then come talk again. Bye. 🤣
Probably a classic skill issue. There are no "wavelets/fractals" for me, only good results in 1536 x 1536 and 2x and 4x upscaled ones. I do images locally with ComfyUI with settings i've used for a while already, did not even had to change anything for this checkpoint, so.. what kind of settings/workflow do you use?
*small edit ^^
@Eclipsia you should not use comfyui if you don't know how diffusion works
anyway i stand by my technical analysis of your result as a engineer you created something which is not worth the bitrate abuse for nothing except artificial data structure nor does it helps your visual cortex or perception in any shape or form it was just a abuse of unnecessary bandwidth.
Unfortunately you see this often from people who want to sell snake oil im used to this since decades of itc work.
and especially at some point all this model variations start to become frustrating and useless as well and have only one goal to keep someone a income nothing more just useless survival instinct that creates more useless data structure and valuable resource waste.
But that will fire back heavily at all of us.
And you wont understand anything of what i said if you do not understand what the VAE is and it's limitations inside the diffusion process.
And if i look at your result here you surely neither have any idea of visual data compression
and for Civitai and users this has direct consequences in the form of resource waste.
And that resource is mostly energy consumption for nothing that should be.
@alekhammes966Â I think you might need to lay off the magical shrooms for less fractals and fewer messages to spam me with, because let's be honest.. who asked?
Also, since you are the master of SDXL, oh please post your images to showcase your ultimate set of skills and technical prowess. I am thrilled to see what you have. Message me when you are done.
PS. I stand by my statement, that this checkpoint is currently the best in quality potential for SDXL. My other top3 favorites currently are HuslyoRealismV2 and ePicRealismXL_PureFix, Huslyo's checkpoint is like i'd say best all-rounder tbh, but that again is user preference.
All i see is a random on the internet telling someone's post is bad and their image is bad and the checkpoint they used is bad and "waste of bitrate" and whatever.. now show me your own images (done with SDXL only, no img2img, just txt2img like me) and what is better checkpoint in quality than this? Again, i am giddy with anticipation while waiting for you to post here and show instead of being big mad in chat. 🤣
@Eclipsia nonsense its not about that it can support this resolution it's about if it makes sense compared to a different path useless to talk to you
@Eclipsia Find my result space on Google "Kosmosx Slushe" all Exclusive handmade prompts my own database of thousands by now.
@alekhammes966
I checked out your images.. actual generic oversaturated slop images in a "3D porn site", yeah there might be "thousands" of them, but sorry to say this: looks like 2023 old checkpoint quality when people used still "skitzo negatives" etc and were still new and learning to prompt, full bokeh slop with bad DoF focusing on random things because most your backgrounds are simplified and not even detailed, and people are full of mutations, errors and poor quality 750 x 750, uncanny & artificial looks etc etc.. and you talk about waste of bitrate? I think your images are mostly waste of space (and my time) having checked them.
And do remember, you came here telling what i said was wrong, that my image is bad and this checkpoint is bad etc, so in return you ought to put on your bigboy-pants and take honest feedback, it's not a shame to take occasional L's.. happens so don't worry. I think most people appreciate this checkpoint and it's qualities based on the feedback here, so maybe one day you can admit to yourself that it might be just a you-issue if could not find what makes this a great checkpoint.
You said it's "useless to talk to you", and i am happy about that so the discussion is now over, nice that we had this chat opportunity and it's now done, i wish you a nice day and rest of life. 🤣
@Eclipsia you just looked at the SD 1.5 results artificial looks is a combined sword if you don't get what you prompt for because you merged the logic to death
@Eclipsia some scenes are 10x more complex from the shoot complexity then anything you see here
@alekhammes966Â Then go back to your 'space with the best complex ai art' and don't waste your time on 'mere low-effort slop'.
I honestly don't know what you're trying to achieve here in the comments.
A) If you were trying to give helpful advice - this isn't it. There has been nothing helpful in your replies so far.
B) If you were just trying to be hateful - that isn't working out either.
I'm sorry you feel the need to act this way. Is this perhaps a result of some past trauma that makes you crave to prove your supremacy and expertise? Because to be honest, that’s exactly what it looks like from the outside
@alekhammes966Â This is free software. And it is undisputably good compared to other SDXL checkpoints. Now, if this is not up to your standards or preferences, do you know what? There are other models. There are digital and analogue cameras. In fact, there is a whole world out there. And you have ONE life as far as we know. Spend your time wisely on things that matter to you for real. I am pretty sure if you stop just 5 minutes and ask yourself "What do I want in this life? What can I do now to get closer to that?" your reply will not be "I want to argue with total strangers on the Internet about a piece of free software they like but I don't."
@coyotte no it just burns me to death seeing how the 500 thousand useless model iteration merged to death comes out without any substantial anything only the purpose of making money and by that wasting resources just to keep a useless machine running.
If you would have just some consistent idea or prove that their is some brain functioning in your model but no worry i will test that.
@coyotte believe it or not but you can merge a model to become dumber
@alekhammes966Â
It's funny how you talk about 'brain functioning' and technical expertise while simultaneously confusing a finetuned model with a merge.
Lustify V8 isn't some 'merged to death' experiment - it’s a checkpoint trained on a curated dataset with months of manual captioning and R&D, hundreds of hours of GPU compute.
If you think training a model on a custom 1536px dataset to push the architecture's limits is 'wasting resources,' then you clearly don't understand how progress in this field happens. Yes, it's still SDXL, but I'm trying to engineer my way around its native limitations.
It wouldn't hurt to learn the basic terminology of the tech you're trying to criticize. You can't tell the difference between a simple merge and a fine-tune, yet you're here talking about 'useless iterations.' You're fighting ghosts.
As for 'brain functioning' - by all means, go ahead and test it. But considering you don't even understand the nature of the model you're testing, I suspect the results won't change your mind anyway. Good luck with your experiments though!
@alekhammes966Â And if you're referring to the older versions from before I started breaking resolution ceilings - your criticism makes even less sense. Lustify has consistently been one of the most popular NSFW SDXL models on the platform; it's far more likely that everyone else was merging my work into theirs, not the other way around.
I can name at least 10 checkpoints that have done so. Even Juggernaut incorporated Lustify, and they explicitly state that on their model page. When the industry leaders are using your model as a component, calling it 'useless' just shows how out of touch you are with the actual state of AI development.
I've always been transparent about the model's lineage: way back in the early stages, there was a small amount of BigASP and NatVis in the DNA. But for a long time now, Lustify has been a pure fine-tune, driven by my own research.
@coyotte simple prompt adherence test full fail 1st generation fails target on seed 1
not even the couch 2 character sex interaction test (in natural language it survived) if it needs a very specific setup its almost garbage.
if it not even understands the relation between penetration couch and african inside a environment target and just shows environment with some sex
@coyotte Industry leaders :D industry leaders that beg every scientist to use their research
Yes i see what you doing the same as subtle shader does who wants extra money for this crap like every cloud service will be happy to see their users going to use these checkpoints so they can charge extra as well ;)
That work was introduced based on SDXL first by OnomaAI (Korean Research Entity) in their illustrious V 1.0 VAE training
Also SubtleShader is a funny guy he uses DMD2 to market his own work funny guy really funny guy that trains with copyrighted material of real humans
@alekhammes966 Wow, that’s a lot of words to say absolutely nothing. You're bringing up Korean research entities, VAE training, and other creators like SubtleShader - none of which have anything to do with me, my work or the technical discussion we were having. It's pure word salad.
Testing a 5-condition prompt and calling it garbage because didn't hit a bullseye on Seed 1 is just peak Dunning-Kruger. That's not how generative AI works, and you know it. You might not even be using the correct prompting method. Are you using the danbooru tags (surely you would know that the CLIP text encoder works best with tags, rather than natural language... right?)
You're moving the goalposts every time I disprove your 'technical' points. First you claimed it was a merge, now it's about some Korean entity or clouds charging extra for compute? It's clear you're not here for a rational discussion - you're just looking for someone to vent your frustrations at.
Discrediting Juggernaut (the most used SDXL model on the site) just to feel superior in an internet argument is a bold move. Bold, but delusional.
At the end of the day, you're clearly just angry that I value my time and effort. If the model is 'garbage' to you, the solution is simple: don't use it, block me so that you never have to land there ever again and move on. I'm done wasting time on this schizoposting. Best of luck ;)
So 100% unique no merge huh who you want to fool here you share the same genetic tree with Pornmaster and Jugernaut you fear i could hurt your income this is why you want to get rid of me now.
@alekhammes966 The idea that a 1-week-old anonymous account could affect me in any way is peak delusion. You're giving yourself way too much credit.
You keep talking about 'genetic trees' and merges while failing to grasp even basic spelling/grammar. It's impossible to have a technical discussion with someone who communicates in a nonsensical stream of consciousness.
Besides, check when the first SDXL Pornmaster was released (Dec 30, 2024) and when the first Lustify version was (Jul 12, 2024). I was first in that 5.5 month window, so nothing you say makes sense.
I'm not 'trying to get rid of you' because I'm afraid - I'm doing it because you're boring and repetitive. Please get some help.
@coyotte search a real job sooner or later you have to
@alekhammes966 somehow I just know you were that pathetic kid everyone at school used to make fun of ðŸ¤
@Eclipsia I'm sorry that this whole mess happened below your really nice comment. Thank you for the feedback and for the positivity!
wow @alekhammes966 Actually still going off big mad.. (i get notifications since started this topic lol) alek you know how the mentioned checkpoints share "genetic tree"? Because those other 2 did dip some of the sweet Lustify in them from an earlier version like a magical spice and it made them better. You are getting it all backwards.
Also, now finally everyone knows why you came here all mad to post at me, you were actually angry because of the Early Access + 1 week cost (just wait 3 weeks, was it really that bad to get your blood pressure up and go this mad over it?) and some other creators wanting to make a few coins/buzz to cover some costs.. so you were big mad, saw me telling that some crypto millionaire should donate for this great work, and rightfully so, good work should be rewarded, since healthy capitalism motivates to innovate and work long hours on something, personally i am grateful and will support when can.. you saw that and got mad at me also.
If i had more time just now, i'd make some image like that meme where a cat puts it's paw on top of a poster's hand and the text says "it's time to stop.." because sometimes someone else has to tell when things not look healthy anymore and should just go do something else.
These type of creations are a work of passion, but there is also the effort and costs. Electricity and pc hardware are not free. Time is money also. I am a poor student, but you don't see me complaining, i am happy we did get this checkpoint for free after a wait. Subtle Shader did also put that Ultra1 version for free, since you mentioned their name. So you get free good stuff, should be happy and not mad.
@coyotte Hih, no worries, it's fine.. 😅 i just get lots of notifications that's all. but i have been happily just using your amazing checkpoint (and couple others) most of the day today again. ^^ I play also some games and in Discord it's sometimes full ping dramas etc, so this is just another normal monday for me. * sips tea happily *
@Eclipsia i would be not mad if they would stop this oh i found a problem oh another release oh i found another problem wait yet another release instead of let me benchmark this first to the teeth before release. No its a job release fast then wait and be happy your community reports bugs and be usable for them again and so in the end you never stop because wow i make money with it.
If you would do it out of fun you would not start earning money with it as soon as you do it becomes a job and you do not cross invest your own resources back you gather them from others.
@alekhammes966Â You're literally describing how modern software and tech development works as if it's a bad thing. I don't release updates because the model was 'broken'; I release them because I've found ways to push the quality even further, integrated new concepts, or improved the dataset. Do you seriously claim I should withhold improvements just because you're tired of seeing updates? That's absurd.
As for 'investing resources' - you keep conveniently ignoring the fact that time is the most valuable resource. Every single release represents 200-400 hours of manual labor: cleaning datasets, hand-refining captions, and writing custom scripts for optimization. That is my personal life and my energy invested back into the project.
You seem to have this naive, adolescent idea that if someone earns money from their work, it's no longer 'for fun' and therefore becomes some kind of exploitation. Newsflash: people in every field (artists, engineers, developers) get paid for their expertise. It’s what allows them to keep creating.
@coyotte bullshit a job allows you to keep creating as well its called cross investment one thing is your job and you finance your hobby with it that you hopefully never made your job.
Don’t feed the troll...Rule number one since the introduction of the Internet...
@Venion Troll when i look at your pictures i wonder who the troll is here
Thank you for your effort! Looking forward to z-image finetuning, it's much needed🤣
I don't mind supporting you with the training,please keep up the good work.
Incredible
Excellente' Works great with https://civitai.red/models/800496/lightninghyper-8step
set lora at .5
Set to 16 steps around 2-3 cfg euler A/SGM uniform
I've tried adding tan lines to the negatives and still get them a ton!
This might be related to your positive prompt rather than the negative one, as there are very few girls with tan lines in my dataset.
What are your prompt and settings?
Nevermind, I've found the examples in the gallery. I see that you're using the dmd2 lora - that means that your negatives don't do much anyway (because of the CFG 1), so it's not really surprising that you can't get rid of the tanlines with negatives.
The LoRA itself is likely what's causing them to appear. I've noticed the same behavior when using DMD2, it tends to bake in certain features.
@coyotte yeah it's a pain... only got 8gb of vram so I got to make things work lol
thanks so much for helping though! Great model as usual!
Probably a troglodyte ahhh question but is it possible to do image2image with this.
Regular img2img - sure.
Image editing like Qwen Edit/Klein Edit - no, not possible with SDXL.
Even though I have no idea if the pictures I uploaded are even visible right now, I’d like to say a big thank you for this amazing model. It’s so beautiful and flexible in every direction—that’s exactly how I like it.
They do! The images you've posted are very aesthetic and beautiful, thank you for sharing. I've pinned one of your posts in the gallery
@coyotte Thanks, there's a lot more to come. I'll always post a picture of my sets, and if a certain threshold is reached, I'll post the rest of the set as well. If it doesn't affect the aesthetics in any way, I'd like to see slightly better-looking vaginas for V9 if you're working on that. Cheers.
do we train a character lora on this model like any other? any recommended settings? :)
Epic Checkpoint, TYSM!

