Update June 28th, added V3+VAE, pruned and fp16 versions also added.
V3
More training added to supplement some things I feel are missing in current models. Skin textures, darker lighting and more variety in race in people.
V2
After weeks in the making, I have a much improved model. No longer a merge, but additional training added to supplement some things I feel are missing in current models. Lots of new training for skin textures, lighting and non-asian faces to balance out the asian dominance in models. If you create a generic prompt, you'll get a greater variety of races and faces now. Skin textures are increased by a large amount, if that's not your thing, you can put detailed skin in the negative prompt and get back that airbrushed look if you like.
A photorealistic model I've been using for a little bit. I hate smooth airbrushed skin so I refined this model to be very realistic with great skin texture and details. There are 2 models, a standard and an ultra.
The Ultra model is nearly 3 times as large, but it's not 3 times as good. It is better though with a broader knowledge. You can even generate 1024x1024 in many cases. The config file is required for the Ultra model, be sure to download that too.
So I recommend using the normal version unless you have the need or vram to run the Ultra model. If you'd like to run the Ultra model with modest vram, try --medvram or --lowvram in your auto1111 startup script.
A side-by-side comparison. Link to see full-size samples with metadata. Like I said, the Ultra model isn't 3 times as good, but it is better across multiple subjects, not all. The pruned version of the Ultra model is debatable, might be better to use the normal V1 model in some cases. But all have been provided so you can make the choice yourself. For me, I use the Ultra model in every case.
Do you have requests? I've been putting in many more hours lately with this. That's my problem, not yours. But if you'd like to tip me, buy me a beer. Beer encourages me to ignore work and make AI models instead. Tip and make a request. I'll give it a shot if I can. Here at Ko-Fi
Description
FAQ
Comments (34)
Thank you very much! your model is the best by far, and I tested all of them...
I'm in debt with you
thanks
I see a V1 Ultra, but not a V2 Ultra...is the V2 by default the ULTRA model?
Yes!
@Zovya I didn't find a config file for the V2 full version, or can I just rename the aZovyaPhotoreal_v1Ultra.yaml to the aZovyaPhotoreal_v2.yaml?
@1240632494418 the V2 model doesn't need a config file. ONLY the V1 Ultra needs one.
@Zovya thx! I use v1 ultra full version a lot,you do the always best!
Genial!! ya me estaba aburriendo de caras asiáticas, muy buen modelo!!!! gracias, este modelo debería ser de pago.
haha, gracias
Hey there. I'd love to Dreambooth train based on this model, but all of the collabs use huggingface. How can I train with this?
I thought some collabs were intergrating civitai recently. you could upload any model to your own huggingface though
Thanks for the response. I switched collabs and used Huggingface and it went off perfect!
What is difference between 5GB model and the 2GB model?
some things are pruned out to make the size smaller. some would say no difference. others would argue there's a big difference. maybe the 2gb is good enough for you. only you can decide.
@Zovya ok thanks
I would guess the 5GB would make better results. Size matters, dont let the talking heads tell you different.
5GB version often used for training, pruned for generate result
is there no "ultra" version of V2? which is better, V2 or V1 Ultra?
try them both for your particular prompt
Tutorial for this model A-Zovya Photoreal easy and fast
With a baked in VAE like in V2 inprinting, do you still set the VAE in Stable Diffusion/AUTOMATIC1111 or do you set the "global" one to None?
set to "automatic"
@Zovya thx :)
Is this coming to SDXL? I want it so bad
indeed. but it will take time
@Zovya the best things do.
how long till SDXL model by you? @Zovya
Please start creating XL models.
How do I add the checkpoint to the huggingface stable diffusion model?
Probably the best realistic model out here for SD1.5 - kudos!
it does people very well, but does not draw any animals from my lora... only people...
When I try put on automatic1111 Stable difussion checkpoint at top it revers back to my previous one so i cannot use?
hi may I ask if there is a way to use this in a paid app/service?
when the sdxl update coming with turbo , lcm or lightning