Reality Bound XL
Details
Download Files
About this version
Model description
This series is focused on women and the female body, in every kind of setting or style. It can do fine art, social media style, surrealism, cinematic, and pornographic very well. The main goal is to have as much diversity as possible in an SDXL checkpoint. Diversity in ethnicity, body type, faces, posing, personality, and locations.
The VAE is baked in. No loras were used for the sample images. Only Hi-res fix and Adetailer, on some images.
If you like it post your creations!
General Series Details
Using natural language works best. Be descriptive in your prompts. Pony/Danbooru tags aren't generally as effective.
v8 faceSmash
Since the Long Clip series seems to be popular I have created 2 versions of v8 with both fp16 & fp32 clips swapped with the dull built-in SDXL clips.
fp16 version is using the Simulacrum text encoders
fp32 version is using Long Clip Distilled encoders
Simulacrum also has very well trained encoders that perform noticeably better than the standard.
Very responsive to quality tags:
8k uhd, high quality, masterpiece, vivid | deep | vibrant colors, sharp details, cinematic composition, soft glow, creative shadows | lighting
My tests:
Eular a for artistic gens
Eular a SGMUnifom for detailed soft skin (soft: obvious goosebumps)
DPM++ SDE for extra crisp details (lower steps/CFG) (crispy: intricate skin details)
DPM++ 2s a for dramatic skin texture and details (Hyper-realism)
Using a different scheduler for generation and a different scheduler for Hi-res fix can give beautiful results. Try a crispy start with a soft finish.
Pushing my models to reach "overwhelmingly positive" status one day.
/model/1044804/clip-l-and-clip-g-full-fp32-zer0int-and-simulacrum
/model/1805024/long-clip-distilled
v7 gutPunch
v7 is an entirely different beast than what came before.
Female anatomy is indistinguishable from real life
Groups & multiple people are easier to gen
Improved photography & lighting variation, Vivid colors
Added cinematic composition, decades, styles & genres
Great Diversity: people, body, ethnicities, pose (lewd)
Very responsive to quality tags:
8k uhd, high quality, masterpiece, vivid | deep | vibrant colors, sharp details, cinematic composition, soft glow, creative shadows | lighting
Natural language works best in short prompts
Danbooru tags work best in Long prompts
Gen settings do have a sweet spot depending on the image type. Test out different schedulers and other settings for best results.
My tests:
Eular a for artistic gens
Eular a SGMUnifom for touchable soft skin
DPM++ SDE for extra crisp details (lower steps/CFG)
DPM++ 2s a for dramatic skin texture and details (Hyper-realism)
Using different schedulers for generation and Hi-res fix can give beautiful results. Try a crispy start with a soft finish.
Both versions of v7 have the HDR VAE baked in.
V4.0 fullybound
I don't like making grand definitive statements on things that are subject to diverse opinions. So I won't tell you this version will knock your socks off. That would be presumptive.
Strong points include:
Creativity is through the roof
Background details are amazing
Realism & Hyper-realism is excellent, semi-realism is also easy to generate
Diversity is still very strong
It can handle many different styles and themes
Dynamic poses are especially dynamic
Clothing prompts work very well & very detailed
Expressions have really improved
Good skin details, eyes are better than the previous versions
Prompt adherence is good for simple prompts and sfw prompts, but may need a neg prompt
Bondage prompts...you'll see, it will not disappoint ;)
Weak points:
Some sex actions are hard to prompt for if given a lot of specifics
Fantasy creatures are ok, however fairies are very good
Hands are pretty good, but still has typical XL behavior
Multi-person images are better than most XL models, but the hands become harder to get right
Prompt adherence can go from excellent to "where did that come from?"
V3.0
Maintaining the diversity of this series is my main focus. This version is very creative and has additional social media style and amateur style capabilities. The poses are very dynamic and facial expressions are more expressive than most realistic models when you specifically prompt for them.
If you're having issues with skin or eye details, add weighted text describing what you want. It is noticeably responsive to detailed prompts.
Strong points include:
Impressive ethnic diversity
NSFW images are easy to prompt without using a lora in the prompt
Realistic anatomy (woman focused, but men too)
Beautiful women, handsome men, both with a very wide range of features
Prompt adherence is good for long prompts, and great for short prompts
Stronger ability to generate dynamic and artistic images
Photography: art, glamour, erotic, pornographic, social media, professional, amateur
Lighting: creative, dynamic, stylized
Poses: dynamic, sexually explicit, casual, unique, action
Better at handling Danbooru tags
Uncensored and very horny (post images responsibly, please!)
Weak points:
Some lewd acts are hard to prompt for but will then appear unprompted at times
Difficult to keep her clothes on...but it is possible with a detailed description of clothes
Distant faces need aDetailer
Eyes usually need to be described in the prompt or they default to dull or ugly
Hi-res fix is essential for complicated imagery (pretty standard, yes?)
ribaldVassalage V2.0
Maintaining the diversity of this series is my main focus. This version is very creative and has additional social media style and amateur style capabilities. The poses are very dynamic and facial expressions are more expressive than most realistic models when you specifically prompt for them.
If you're having issues with skin or eye details, add weighted text describing what you want. It is noticeably responsive to detailed prompts.
Strong points include:
Impressive ethnic diversity
NSFW images are easy to prompt without using a lora in the prompt
Realistic anatomy (woman focused, but men too)
Beautiful women, handsome men, both with a very wide range of features
Prompt adherence is good for long prompts, and great for short prompts
Stronger ability to generate social media-style selfies to epic cinematic images
Photography: art, glamour, erotic, pornographic, social media, professional, amateur
Lighting: creative, dynamic, stylized
Poses: dynamic, sexually explicit, casual, unique, action
Better at handling Danbooru tags
Uncensored and very horny (post images responsibly, please!)
Weak points:
Some lewd acts are hard to prompt for but will then appear unprompted at times
Difficult to keep her clothes on...but it is possible with a negative prompt and a detailed description of clothes in positive prompt
Cloned faces in a crowd
Distant faces need aDetailer
Eyes usually need to be described in the prompt or they default to dull or ugly
Hi-res fix is essential for complicated imagery (pretty standard, yes?)
Suggested Resources:
Refiner text encoders from Huggingface will bring out the best in any SDXL model:
https://huggingface.co/refiners/sdxl.autoencoder/tree/main
https://huggingface.co/refiners/sdxl.text_encoder/tree/main
https://huggingface.co/ekhalavyan/sdxl-refiner-encoder-2/tree/main
I use these in ForgeUI. The listed refiner models are great at interpretive prompts, wonderfully detailed without changing aesthetics entirely, and are just better in my opinion.
V1.0 / V1.1
V1.1 is the reduced size of version 1.0. Re-merged with the original base model (16GB) using several methods. I managed to get it practically identical to V1.0. Only minor aesthetic variation in seed reproducibility.
Strong points include:
Impressive ethnic diversity
NSFW images are easy to prompt without a lora
Realistic anatomy (woman focused, but men too)
Beautiful women
Prompt adherence is great for long and short prompts
Ability to generate influencer-style selfies to epic cinematic images
Fine art and glamour/erotic/amateur photography
Uncensored (generate responsibly, please!)
Weak points:
Some lewd acts are hard to prompt for but will then appear unprompted at times
Cloned faces in a crowd
Eyes usually need to be described in the prompt or they default to dull or ugly
V1.0 InvokeAI reads as a lora network, rather than a base model (fixed in v1.1)
Suggested Resources:
Refiner text encoders from Huggingface will bring out the best in any SDXL model:
https://huggingface.co/refiners/sdxl.autoencoder/tree/main
https://huggingface.co/refiners/sdxl.text_encoder/tree/main
https://huggingface.co/ekhalavyan/sdxl-refiner-encoder-2/tree/main
I use these in ForgeUI. I've tried many new trained encoders from Zeroint and others. One thing I noticed is that they drastically change the image output in a way that I don't really like. From prompts being interpreted too literally, guiding aesthetic details to be overly polished and even losing any unique characteristic that the base model is capable of.
The listed refiner models are great at interpretive prompts, wonderfully detailed without changing aesthetics entirely, and are just better in my opinion.
Details about me and my process
Motivation
I love creating fun artistic tools and exploring new technology. And above all, I love the incredible art that the human body can make. Text2Image technology is allowing me to smash all of that together in a stellar way.