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
ProtoVision XL Beta Release Notes 08/19/23
This version of ProtoVision has had some additions to add more variety and complexity to scene backgrounds, more facial and skin detail to subjects, better coherence. Eye and hand improvements. PVXL should also be more responsive to cinematic prompts. Facial variety has been improved, and racial biases are less prominent.
Beta 0.5.2.0 Changelog Notes
Updated Merge mix with 0.6.7.1 NightVisionXL
LORAs Added
Teeth_XL
xl_real_beta
Grit-SDXL
MovieStillMasteryV02
LORAs rebalanced
Black_Sa_May
dwzstyle
SamaritanEsdxl
Known Issues
Hands
Signatures and Watermarks (I've identified the issue that is causing this, will be working on the over-abundance of signatures and watermarks in future versions)
nipples can sometimes appear on clothes, though it's rare now
Male genitalia
FAQ
Comments (28)
Beta version 0.5.2.0 Release Notes 08/19/23
This version of ProtoVision has had some additions to add more variety and complexity to scene backgrounds, more facial and skin detail to subjects, better coherence. Eye and hand improvements. PVXL should also be more responsive to cinematic prompts. Facial variety has been improved, and racial biases are less prominent.
Beta 0.5.2.0 Changelog Notes
Updated Merge mix with 0.6.7.1 NightVisionXL
LORAs Added
Teeth_XL
xl_real_beta
Grit-SDXL
MovieStillMasteryV02
LORAs rebalanced
Black_Sa_May
dwzstyle
SamaritanEsdxl
Known Issues
Hands
Signatures and Watermarks (I've identified the issue that is causing this, will be working on the over-abundance of signatures and watermarks in future versions)
nipples can sometimes appear on clothes, though it's rare now
Male genitalia
Thanks for the update!! I love this model!!
you are on first place^^
but at the moment the count also NSFW and not only from one source, like writen in the rules :D
take my lora -> better_faces its is very smooth base one, take a look, at the moment combination with this model is to much ^^
i just think the dimples when laughing are too much in young women...
This is absolutely incredible. Well done. Nothing comes close on Civit at the moment. You deserve to win the competition.
Hey buddy!
Without a doubt, you are number one! Excellent model!
Awesome model, got really satisfying results. Tested it against others and its my favourite so far. Good luck in the competition!
Hello! For some reason, this model does not work for me, it just does not get out of the list of models, I click on it and nothing happens, there is no such thing with other models and in general I meet the problem for the first time, does anyone know what's the matter?
Check its filesize, if its downloaded completely
1024的图提示内存不足，如果渲染小图512的，出来的是色块图，请问是什么原因？在其它模型从来没有过的情况
Excellent model. best results for character design so far. minor extra-limbing where others completely crap the bed ^^
you can fix the extra limbs pretty easily, here is my whole negative prompt:
3d render, cartoon, blurry, low quality, (out of frame, cropped:1.2), (poorly drawn legs, extra legs), liquid hands, fused hands, (poorly drawn hands), (too many digits, extra digits, extra fingers), poorly drawn breasts, deformed, mutated, mutation, poorly drawn feet, extra toes, poorly drawn face, poorly drawn toes, extra toes, rear view, blurry
how is it installed?
It gives me an error, could it be because of the ram memory?
it's installed the same way as other checkpoints and the error could be because of your GPU not having enough vram
Big fan of this model. Is there an inpainting version of it in the works? Are we capable of that with SDXL yet?
Can't wait for the next version of "my favourite checkpoint"!
Not bad, not bad, 5 stars for you! Now, if only you had some milk!
Looks very good however I dont think the sample images look realistic at all, you can still tell its an AI drawing on most of them
The only SDXL that produces good results.
All the rest are wacky at best.
Pls keep working on this, it's great
You work is always top notch, and this model is just the most beautiful thing I have ever seen!
Thanks! I'm excited to see what you can do with this new version 0.6.2.0 I've just dropped, it's a HUGE upgrade over all of my other models and has quickly become my favorite day-to-day.
The only SDXL model that surpasses the best photorealistic SD1.5 models, IMO.
Best settings I've found for near-perfect photorealism without upscaler/refiner:
Positive prompt:
[subject], (raw photo:1.1), 8k uhd, uhd, (natural lighting:1.2), (natural color:0.8), intricate, fine texture
Negative prompt:
anime, 3d, 2d, (sepia:0.9)
with guidance scale 2.75. I've found this works better than bloated negative prompts or stuff like "hyperrealistic"
these are my favorite type of comments on any checkpoint
suggestions on the sampling steps and method?
so SDXL is bad with highres fix ? shame :/ I'm so used to apply it and make images better, one could say its not even needed, but 1.5 stable diffusion models so far are still producing better images imo
The refiner is not the same thing as HRF, and I use HRF constantly - all of my demo images it is enabled, from 1.25 scale up to 4x scale on some.
Can you upload this model on https://pixai.art/ ?
I love the gallery, and it seems that many people are satisfied, but I've tried several setups, and each time, the only result I get is noise?
This is my favorite SD XL model so far! Excellent work thank you for sharing
Details
Files
protovisionXLHighFidelity3D_beta0520Bakedvae.safetensors
Mirrors
protovisionXLHighFidelity3D_beta0520Bakedvae.safetensors
Proto_Vision_XL_High_Fidelity_3D_Photorealism_Anime_hyperrealism_No_Refiner_Needed_Beta_0_5_2_0_Baked_VAE.safetensors
test_model.safetensors
protovisionXLHighFidelity3D_beta0520Bakedvae.safetensors
protovisionXLHighFidelity3D_beta0520Bakedvae.safetensors
protovisionXLHighFidelity3D_beta0520Bakedvae.safetensors
protovisionXLHighFidelity3D_beta0520Bakedvae.safetensors
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.