Like the work I do and want to say thanks? Buy me a coffee or Support me on Patreon for exclusive early access to my models and more!
Meet ProtoVision XL! This model is my "Bob Ross" model, a happy accident that happened when I goofed up some merge settings on my DynaVision XL model and stumbled upon some magic.
So what is ProtoVisionXL? At its core it's a custom built version of NightVision XL, which I then pile multiple fabulous LORAs on top of to create a unique look.
Like all of my other models, merges, embeds and tools, ProtoVisionXL is designed to be easy to use and excels with simple prompts, but is very coherent and can build fabulous scenes with exquisite detail.
ProtoVisionXL is a portrait model, it favors showing human subjects. That's not to say you can't get other art styles, creatures, landscapes and objects out of it, as it's still SDXL at its core and is very capable.
WARNING - DO NOT USE SDXL REFINER WITH PROTOVISION XL
The SDXL refiner is incompatible and you will have reduced quality output if you try to use the base model refiner with ProtoVision XL.
Follow me here by clicking the heart ❤️ and liking the model 👍, and you will be notified of any future versions I release. I also need your help with feedback, please please please post your images and your honest feedback below, I will use your feedback and your output to help guide future revisions!
Patreon coming soon
LORAs used for the initial Alpha version of ProtoVisionXL
add-detail-x
AdvancedEnhancerXL
DetailedEyes_xl_V2
MovieStillXLV7
Neonify
offset_example-lora_1.0
photorealistic_slider_v1-0
Samaritan 3d Cartoon SDXL
dwzstyle-000018
wowifierXL
Description
VERSION 0.4.1.1 RELEASE NOTES
This new version offers much better prompt coherence, less bias, improved female anatomy for NSFW output. This model now offers incredible photorealism, and I have updated the title of the listing accordingly. It still can do eastern style output, but the model does much more than that.
Visually the anime / stylized output has changed slightly, as the model is less biased towards portraits, if you still prefer the more "zoomed in" look, you can use "portrait" or "close up" in your prompt to restore the effect.
CHANGELOG
Partial rebuild to correct color splash issues and update LORA versions
Adjusted Neonify LORA levels
Adjusted SamDoesArts LORA levels
Added New LORAs:
finenude_V02a
DetailedEyes_XL_V2
Removed LORAs
WowifierXL
NightVisionXL 0.5.0 re-merge
Greatly improved prompt coherence
NSFW output has been improved. nudity is much easier to prompt, and female anatomy is overall better. Male anatomy is still a nightmare sadly.
Known Issues
Hands
eyes at a distance can still be weird sometimes
pupils and iris shapes can be off sometimes
male genitalia is pretty much non-existent or reaaaaally wrong
FAQ
Comments (8)
BETA VERSION 0.4.1.1 RELEASE NOTES
This new version offers much better prompt coherence, less bias, improved female anatomy for NSFW output. This model now offers incredible photorealism, and I have updated the title of the listing accordingly. It still can do eastern style output, but the model does much more than that.
Visually the anime / stylized output has changed slightly, as the model is less biased towards portraits, if you still prefer the more "zoomed in" look, you can use "portrait" or "close up" in your prompt to restore the effect.
CHANGELOG
- Partial rebuild to correct color splash issues and update LORA versions
- - Adjusted Neonify LORA levels
- - Adjusted SamDoesArts LORA levels
- Added New LORAs:
- - finenude_V02a
- - DetailedEyes_XL_V2
- Removed LORAs
- - WowifierXL
- NightVisionXL 0.5.0 re-merge
- Greatly improved prompt coherence
- NSFW output has been improved. nudity is much easier to prompt, and female anatomy is overall better. Male anatomy is still a nightmare sadly.
Known Issues
- Hands
- eyes at a distance can still be weird sometimes
- pupils and iris shapes can be off sometimes
- male genitalia is pretty much non-existent or reaaaaally wrong
Great for making porn, and with lots of custom loras
Go go gadget NSFW update 😅😅
Probably the best SDXL model I tested until now for digital illustration. Looks amazing! Thank you!
For me the Hi-Res Fix generates error on Automatik, GTX 1080. can this work with a F16 Vae?
There isn't anything that limits it from working on FP16 VAEs that I'm aware of. Apologies for the late response, if you still need assistance troubleshooting this, come on over to my Discord server (link is in the model comments) and we'll be happy to try to help figure it out.
This has the fixed SDXL 1.0 VAE baked in
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.