Support the Freedom at https://ko-fi.com/lorian0x7
This model is also available on my kofi page without the need to pay with Yellow Buzz!
🔴 MOSS :SHARP AND UNCENSORED
TIRED OF BLURRY / SOFT OUTPUTS?
MOSS checkpoints are notoriously soft and lack fine detail straight out of the box.
To solve this, I created a dedicated Deblur Workflow that restores crisp skin textures, sharp facial features, and clean edges without altering the generation style.👉 Get the Sharpening Workflow on Ko-fi: https://ko-fi.com/lorian0x7
The workflow it's set to work with an uncensored text encoder to improve prompts without the usual limitation of the default one.
❤️ Support Independent Development
I am passionate about creating open tools, versatile checkpoints, and unrestricted models for the community. If you value this work and want to support independent development, please consider joining my supporters on Ko-fi:
👉 https://ko-fi.com/lorian0x7
🔥 Available on Ko-fi:
Alpaca0x7: New Pony-based checkpoint with high-end anatomy handling.
MOSS Sharpening Workflow: The dedicated setup to eliminate the native blur of MOSS models.
Clothing removal Flux Klein Lora: Made to keep the body proportions and shapes as close to the original image as possible.
Early access to upcoming releases and experimental workflows.
📦 Checkpoints Overview
Resilience (NEW - MOSS): Realistic freedom is back with this amazing MOSS checkpoint, extremely flexible and optimised for NSFW generations. No Turbo LoRA needed.
Omega: The flagship release. It delivers exceptional realism and artistic depth that rivals FLUX, maintaining high visual fidelity across complex scenes.
Ophelia: Focused on natural beauty and refined female anatomy while maintaining strong flexibility for everyday generations.
Aria: Soft aesthetic, exquisite lighting, and optimized for detailed portraits.
Wonderland: A solid, versatile everyday checkpoint with balanced anatomy, expressive faces, and rich lighting.
Alpha: The original SDXL base checkpoint with a cinematic, unrestricted touch.
⚙️ Generation Settings
🔹 Resilience (MOSS)
Steps: 8
CFG: 1
Sampler: Euler
Scheduler: bong_tangent or Beta
Note: Turbo LoRA not needed.
🔹 SDXL Checkpoints (Omega, Ophelia, Aria, Wonderland, Alpha)
Samplers: DPM++ 2M / DPM++ SDE 3M
CFG Scale:
2.0 – 5.0 for short prompts
4.0 – 9.0 for detailed prompts
Disclaimer: The creator holds no liability for any images produced with these models, including their legality, ethical implications, or potential misuse. By using these files, you agree that all responsibility for generated content rests solely with you. Use responsibly and within legal boundaries.
Description
FAQ
Comments (22)
hey,
tell us about your model, what is special what you have trained ? ;)
Right, I probably should add more detail in the description. Starting from a Merge I trained the model with 4000 NSFW onlyfans images, and 1000 cinematic images from netflix series, The results is a model with improved human anatomy, better nudes, better lighting, and better compositions. I also noticed an improvement in details generation
@Lorian 4k onlyfans? LEGEND!
Excellent model for photorealistic pictures.
Does great work with NSFW prompts.
A little bit worse for fantasy paintings, but still very good.
PS Tested it a bit more, paintings turn out good enough.
Sample images are probably the very best from a base SDXL model I've seen
Thank you, I actually didn't put to much efforts in the sample images. I'm sure the community here can do much better then me with this model.
The word "cinematic" and "cinematic lights" is what I this does the trick for most of the images.
@Lorian If you did not put much effort, it means it actually is a really good model. Other SDXL models are not that crisp, neither with complex nor simple prompts. Right now I wouldn't call myself a fan of SDXL, although I yet can't use it on my PC the overall look of generations seems meh to me, but the samples you put here are really good.
Should we still use the SDXL base refiner with this model, or would that interfere with its NSFW capabilities?
I wouldn't if you're planning on doing NSFW stuff. In my experience, the refiner does not like nudity at all.
So far it works fine with NSFW + refiner.
Why do you use BREAK keywords in this prompt that generates big wolf and woman in red dress?
photo of scary huge creature, white wolf, humanoid, night, forest, netflix, cinematic, horror, BREAK girl with red dress, scared, BREAK, fog, smoke, detailed background, intricate forest, mistic lights,otherwise you get a red wolf, search for regional prompts
The BREAK command ends the input line and starts a new one. If you do not put in BREAK it treat it all as a long command which give you very often mixed results... For example you ask for a woman with red hat and a greay wolf. And you end up with a red wolf and a grey hat and things like that. It helps avoid it mixing the imput commends. Also the max order lengt is 75, after that it puts in break there anyway which can lead to unwanted results .
i keep getting this error for img to img <AttributeError: 'ControlNet' object has no attribute 'label_emb'>
what does it mean,how can i fix it? I didn't encounter this bug with any other models.just this one
Hands down best model i ever used for Wild life.
Fantastic model and one of the few that doesn't absolutely overwhelm character LORAs and make them unrecognisable from the source training. Can't wait for future releases!
When will be full ready? no haste but, what is schedule?
Not sure yet, at the moment it's still one of the best model for SDXL, I guess I'll release the next version in few months
sorry, im new to all this. theres a play button next to the download button. it leads to a couple options, one of them being an app called Draw Things for iPad. Is this the same model as the one on that app? its called Realistic Vision on the app...
seriously looking forward to an updated version of this.
hey it's here! xD
fantastic model, I use it for nearly everything. Thank you!






MOSS checkpoints are notoriously soft and lack fine detail straight out of the box.