- Jan 24, 2020
- 1,401
- 3,793
Thanks guys. Though.. A blonde bombshell with huge boobas .. And everyone is like.. Hey look at the water.. And the lovely tile work, must have been expensive.. Those guys building it, how talented.. 
- Dec 31, 2016
- 316
- 708
Been doing some testing to how training on different models affect the end result. Thanks to an update that added 3 hours to my already long training time it took a lot longer than hoped...
(each image is marked with the model used to generate the image)
Train on deliberate v2:
Trained on dreamshaper v6:
Trained on sd 1.5:
All training is done with the same settings, same dataset, captions etc
The one trained on and generated with sd1.5 is definitely the one closest to the dataset and overall it seems to give the "best" result.
Doesn't come as a completely surprise but i'm rather surprised at the amount of aging/wrinkling (and size/weightloss) in the others. I guess it can be used if people are trying to create that effect considering how bad the AI is at generating "middle aged" at times, it's either 20 or 80.
Not sure how helpful (or informative) this is to anyone else, but as i'd done it i thought i'd share just in case.
(each image is marked with the model used to generate the image)
Train on deliberate v2:
Trained on dreamshaper v6:
Trained on sd 1.5:
All training is done with the same settings, same dataset, captions etc
The one trained on and generated with sd1.5 is definitely the one closest to the dataset and overall it seems to give the "best" result.
Doesn't come as a completely surprise but i'm rather surprised at the amount of aging/wrinkling (and size/weightloss) in the others. I guess it can be used if people are trying to create that effect considering how bad the AI is at generating "middle aged" at times, it's either 20 or 80.
Not sure how helpful (or informative) this is to anyone else, but as i'd done it i thought i'd share just in case.
Hi, just getting my feet wet with stable diffusion after trying it out once months ago, does anyone know what are the most photorealistic checkpoints now? gonna bother Mr-Fox as well
PS nice blondie, but not as nice as the water
PPS send help for my poor 8gb 1070 Ti, she's screaming in pain
PS nice blondie, but not as nice as the water
PPS send help for my poor 8gb 1070 Ti, she's screaming in pain
- Sep 15, 2021
- 903
- 3,341
I've found the most versatile photorealistic checkpoint to be CyberRealisticv3.0Hi, just getting my feet wet with stable diffusion after trying it out once months ago, does anyone know what are the most photorealistic checkpoints now? gonna bother Mr-Fox as well
PS nice blondie, but not as nice as the water
PPS send help for my poor 8gb 1070 Ti, she's screaming in pain
There are many others, but this seems the best all-rounder.
It's also particularly good at portraying celebrities realistically.
- Dec 21, 2020
- 1,528
- 3,598
Also, my $0.02 is that the sampler matters a lot. I.e. Heun does result in great images, pretty much regardless of a model you use:Hi, just getting my feet wet with stable diffusion after trying it out once months ago, does anyone know what are the most photorealistic checkpoints now? gonna bother Mr-Fox as well
PS nice blondie, but not as nice as the water
PPS send help for my poor 8gb 1070 Ti, she's screaming in pain
You don't have permission to view the spoiler content.
Log in or register now.
- Dec 31, 2016
- 316
- 708
Adding to the two posters above, going with the more commonly downloaded "realistic" models will keep you pretty well covered, minor differences, one might suit your needs better in one case, then another the next time. If you use lora/embeddings you might need to use a specific model for "best results". Depending on what you consider "best results" at that time.
I strongly advice staying away from low tier "merges" that's infesting things though. Generally those are poorly done and are leaching off of other peoples work, often without even bothering to give credit to those they are stealing from. And you end up having to fight issues with your renderings that you shouldn't have to deal with simply because others have taken shortcuts etc.
Depending on situation/imagery, i've had pretty good results with these, just to start off with:
If i'd have to pick just one i'd probably agree with Jimwalrus and go with cyber. It's being updated/worked on pretty often and has inpaint model too. So if bandwidth or hdd space is concern, i'd start there, and as Sepheyer mentioned, sampler matters too, so try different ones and see which you like.
I strongly advice staying away from low tier "merges" that's infesting things though. Generally those are poorly done and are leaching off of other peoples work, often without even bothering to give credit to those they are stealing from. And you end up having to fight issues with your renderings that you shouldn't have to deal with simply because others have taken shortcuts etc.
Depending on situation/imagery, i've had pretty good results with these, just to start off with:
You must be registered to see the links
You must be registered to see the links
You must be registered to see the links
You must be registered to see the links
You must be registered to see the links
If i'd have to pick just one i'd probably agree with Jimwalrus and go with cyber. It's being updated/worked on pretty often and has inpaint model too. So if bandwidth or hdd space is concern, i'd start there, and as Sepheyer mentioned, sampler matters too, so try different ones and see which you like.
- Sep 15, 2021
- 903
- 3,341
Absolutely.
Also, never underestimate the usefulness of an X/Y/Z plot of different samplers, models and steps.
Yes, it will take some time (esp on a 1070) but you will gain some really strong insights.
One word of caution though - don't add too many variables. For instance, including 6 samplers, 10 models and eight different numbers of steps will give you... ...hang on a sec... ...carry the one... ...something something... ...480 images to create.
If each one takes 4 minutes that's <gives up, opens calculator app> 32 hours of torture for your GPU!
- Jan 24, 2020
- 1,401
- 3,793
I'm also stuck with a GTX 1070 atm. It does take ages to generate good images but at least it can be done and I have seen people make do with even less vram, creating awesome images. I like Clarity over most other checkpoints as it is consistent and have a somewhat predictable and good respons on the prompt, however there are many others that is definitely worth a try.
For sampler I would recommend either DPM++ 2m karras for semi realism and DPM++ SDE karras for photo realism.
The choice of upscaler is as important as sampler maybe even more.
I'm fond of NMKD Superscale, there's also other dedicated versions of NMKD for specific uses such as face focused for portraits etc. If you are not after highly detailed photo realism but rather hentai, anime or semi realism, 4x-UltraSharp is good and very popular. It gives a smooth image with sharp contours. In the end, nothing can replace a really good and well made prompt.
It's the most effective and powerful part of the generative process.
It does take ages to generate good images but at least it can be done and I have seen people make do with even less vram, creating awesome images. I like Clarity over most other checkpoints as it is consistent and have a somewhat predictable and good respons on the prompt, however there are many others that is definitely worth a try.For sampler I would recommend either DPM++ 2m karras for semi realism and DPM++ SDE karras for photo realism.
The choice of upscaler is as important as sampler maybe even more.
I'm fond of NMKD Superscale, there's also other dedicated versions of NMKD for specific uses such as face focused for portraits etc. If you are not after highly detailed photo realism but rather hentai, anime or semi realism, 4x-UltraSharp is good and very popular. It gives a smooth image with sharp contours. In the end, nothing can replace a really good and well made prompt.
It's the most effective and powerful part of the generative process.
- Dec 21, 2020
- 1,528
- 3,598
I've been on this
You must be registered to see the links
model kick, it even replaced Clarity for a quick minute:
- Jan 24, 2020
- 1,401
- 3,793
Revisiting an oldie, with curtsy of the eminent Sepheyer. You can find his original post and prompt here.
You don't have permission to view the spoiler content.
Log in or register now.
- Jan 24, 2020
- 1,401
- 3,793
Holy ! something.. Lost for words and this doesn't happen often believe me..
This is definitely your best work yet.Amazing
, I gotta try this one out.
- Jan 20, 2022
- 204
- 1,999
Holy ! something.. Lost for words and this doesn't happen often believe me..
Amazing
I as well jumped into the A-Zovya photorealistic wagon.
For my first try, I manage to creep into this wench and took her a candid pic.
Gonna keep stalking her
huahuahua..
- Jan 20, 2022
- 204
- 1,999
Does anyone old enough to remember the DOS game Dune from 1992?
Chani was one of my early crushes
Well this is the remake from 2023
Chani was one of my early crushes
Well this is the remake from 2023
You don't have permission to view the spoiler content.
Log in or register now.
- Jan 24, 2020
- 1,401
- 3,793
Great work.Does anyone old enough to remember the DOS game Dune from 1992?
Chani was one of my early crushes
View attachment 2687439
Well this is the remake from 2023
You don't have permission to view the spoiler content. Log in or register now.
- Dec 21, 2020
- 1,528
- 3,598
So, with Clarity I stopped using "Plus Size Model" because the results were straight out of WALL-E. But with Zovya's, "PSM" yeilds sweet-sweet curves:
- Jan 24, 2020
- 1,401
- 3,793
- Jan 20, 2022
- 204
- 1,999
Hi guys, I was testing new merchandise last night, this one is a little feisty but maybe I went a little overboard; anyways, I will hear your offers...
Status: Used
Condition: untrained, unbranded, unbroken.
Status: Used
You don't have permission to view the spoiler content.
Log in or register now.
- Sep 26, 2017
- 327
- 480
If you want to get a decent prompt add the images to img2img and click Interrogate CLIP and it will give you details of the images. Also, click Interrogate DeepBooru and it gives you porn prompts.Where did you find them? Do you have the original png files? Those ones don't have the metadata you need to get an easy route to copying / cloning them
Interrogating the image though gives us this for the prompt that maybe you can use in a number of different Civitai models to see which fits best:
a sexy woman in a blue costume posing for a picture, hyper-detailed and realistic, fantasy dungeon, plus size woman, doll, hyper-realistic lighting, dark golden hair, featured on amiami, trending on artstartion, real-life big mom, blue skintight closed longcoat, ellora
--
Refining that with a bit of trial and error (we can do this better if we keep going), we can have this:
Positive: (masterpiece:1.2), (best quality), (intricate details:1.2), (photorealism), wallpaper 8k, a beautiful woman, wearing sexy revealing detailed dress, hyper-detailed, fantasy ornate castle window view, cleavage, wide hips, large breasts, sexy cloak, necklace ornament, (sheen to her skin), vibrant colors, (dynamic lighting:1.3), (vibrant cinematic lighting:1.3), (glowing lights and effects and lamps:1.2), lustrous golden hair, realistic skin, smiling, looking at viewer, facing front <lora:hipoly3DModelLora_v10:0.6>
Negative: poor quality, mutant hands, ugly, blurry, low quality, bad-artist, EasyNegative, facing front, boring, dull
--
That gives us something like the attachment - which we can see needs more lighting, and more colors... so you just keep adding to that in the prompt until you get something you need. If you have stable diffusion / automatic1111 - just throw the png into the png info tab and you'll get all the generation details.
View attachment 2531032 View attachment 2531040
- Jan 24, 2020
- 1,401
- 3,793
It's a very good way to get started on the process of making a good prompt but it's very basic and needs a lot more. I haven't tried the DeepBooru option yet, thought it was only aimed at anime..
I will try it next time I begin from scratch.