[Stable Diffusion] Prompt Sharing and Learning Thread

rayminator

Engaged Member
Respected User
Sep 26, 2018
3,126
3,187
i have been test Stable Diffusion AUTOMATIC1111 and Stable Diffusion Automatic

Stable Diffusion AUTOMATIC1111 is a little slow on generating images
Stable Diffusion Automatic is a little faster on generating image

Stable Diffusion Automatic link


they are similar to each other
I have been trying to install xformer for while a and no luck I have follow all instruction from text and video

Stable Diffusion AUTOMATIC1111 = hard to install, I have tried to put into extensions didn't work
Stable Diffusion Automatic = just have to put xformer into extensions and it installed fine
 

Mr-Fox

Well-Known Member
Jan 24, 2020
1,401
3,802
I have been trying to install xformer for while a and no luck I have follow all instruction from text and video

Stable Diffusion AUTOMATIC1111 = hard to install, I have tried to put into extensions didn't work
Stable Diffusion Automatic = just have to put xformer into extensions and it installed fine
No need to install anything at least not for Auto1111. Just open webui-user.bat with notepad and add the argument like so:
"set COMMANDLINE_ARGS= --xformers" and save. Then start webui-user.bat , done.
 

Mr-Fox

Well-Known Member
Jan 24, 2020
1,401
3,802
So here was this mornings exercise.

The model used was Hyper V1 -

So I saw this picture and thought I would do something with it :-

It uses the prompt -
award winning photo, extremely detailed, amazing, fine detail, highly detailed woman, (extremely detailed eyes and face), full body, large breasts, (blue jeans), fitness, short blond hair, (stripes, belts), by Frank Cho and Terry Dodson, wrist watch, (dark alley, dark night), (white croptop),


Trying the exact same prompt but using the Hyper model gave me this :-
View attachment 2562637

So then I decided to take out the 'by Frank and Terry' part. Prompt now was award winning full body photo, extremely detailed, amazing, fine detail, highly detailed woman, (extremely detailed eyes and face), full body, large breasts, (white croptop), (blue jeans), fitness, short blond hair, (stripes, belts), wrist watch, (dark alley, dark night),

View attachment 2562639

I wasn't really liking the jeans so decided on miniskirt instead and decided to bling it up and change the dimensions to try and get full body shots. Prompt changed to :- award winning full body photo, extremely detailed, amazing, fine detail, highly detailed woman, (extremely detailed eyes and face), full body, large breasts, (intricate croptop), (intricate miniskirt), fitness, short blond hair, intricate jewelery, wrist watch, (dark alley, dark night)

View attachment 2562644

Lets get rid of the alleyway and try a fashion catwalk. Prompt now is :- award winning full body photo, extremely detailed, amazing, fine detail, highly detailed woman, (catwalk), (extremely detailed eyes and face), strong jaw, high cheekbones, full body, large breasts, (intricate transparent croptop), (intricate miniskirt), fitness, short blond hair, intricate jewelery

View attachment 2562646

Got a bit lucky with the background girl as A. I didn't prompt for her and B. She doesn't look like a monster, even has 5 fingers!

So that was my morning while hard at work :p
I wanted to have a go too, but went in a slightly different direction.. :sneaky:

Rule 1 : No safeword!

Rule 2 : No crying!

Rule 3 : Scream all you want no one can hear you.

ok let's begin :devilish:

00025-1676492286.png 00026-1676492286.png 00034-1676492286.png
00049-1676492286.png
 

Nano999

Member
Jun 4, 2022
166
73
Guys do you know how can I adjust the volume of notification.mp3 file for task completion?

1682180437816.png
1682180426483.png
 

modine2021

Member
May 20, 2021
417
1,389
dont know whats going on. but now all my images look like this. no matter what model i use. no mater what settings i use, they all end up like this. looks like HDR overkill. perhaps a setting in main got messed up. no idea. got all these nicely created girls etc. but the overall is this ugly result.

00003-3482785258.jpg
 
Last edited:

modine2021

Member
May 20, 2021
417
1,389
I have been trying to install xformer for while a and no luck I have follow all instruction from text and video

Stable Diffusion AUTOMATIC1111 = hard to install, I have tried to put into extensions didn't work
Stable Diffusion Automatic = just have to put xformer into extensions and it installed fine
i found this easy to install various version of SD (no idea if yall already knew about it):
 

modine2021

Member
May 20, 2021
417
1,389
this is a nice fork of automtically1111. faster(including modeling loading time) and everything not all in the way. can customize the interface.. i switched to it...take a peek
<<<---
 
Last edited:
  • Like
Reactions: Mr-Fox

Mr-Fox

Well-Known Member
Jan 24, 2020
1,401
3,802
dont know whats going on. but now all my images look like this. no matter what model i use. no mater what settings i use, they all end up like this. looks like HDR overkill. perhaps a setting in main got messed up. no idea. got all these nicely created girls etc. but the overall is this ugly result.

View attachment 2565737
When you get strange result like this, reboot everything and try again.
Just a guess, it could be that you used an embedding or hypernetwork and it is somehow lingering and breaking the prompt.
I have experienced this kind of issues also and it's the reason I stay clear of embeddings and hypernetworks most of the time.
In my experience they have a too large tendency to break things.
When I hade my issues it was like the cash or something related to memory hade been "clogged" by these type of injections and I had to restart and generate a bunch of throw away images to clear it out.
I could see it become less and less messed up when it finally "let go".
In your case maybe it was something else entirely, idk. That's SD for ya..
I see that you are using Unspeakable-Horrors embedding (TI). Try remove it and generate again.
 
Last edited:

rayminator

Engaged Member
Respected User
Sep 26, 2018
3,126
3,187
dont know whats going on. but now all my images look like this. no matter what model i use. no mater what settings i use, they all end up like this. looks like HDR overkill. perhaps a setting in main got messed up. no idea. got all these nicely created girls etc. but the overall is this ugly result.

View attachment 2565737
I have notice that too when I put CFG Scale or Sampling steps is up to high
 

Elefy

Member
Jan 4, 2022
239
918
all my images look like this
Looks like hi CFG scale (but your PNG info show CFG 7)
1682269768912.png

this is CFG 30

1682269863881.png

and this is CFG 5

1682269957466.png

Or something is overdo here:
Code:
Model: NSFW-Style_chilloutmix_NiPrunedFp32Fix, ENSD: 31337, NPW_weight: 1.4, AddNet Enabled: True, 
AddNet Module 1: LoRA, AddNet Model 1: accidentalExposure_v10(6f7b8fdc6491), AddNet Weight A 1: 0.85, 
AddNet Weight B 1: 0.85
 
Last edited:
  • Like
Reactions: modine2021

HardcoreCuddler

Engaged Member
Aug 4, 2020
2,533
3,228
Looks like hi CFG scale (but your PNG info show CFG 7)
View attachment 2567649

this is CFG 30

View attachment 2567653

and this is CFG 5

View attachment 2567657

Or something is overdo here:
Code:
Model: NSFW-Style_chilloutmix_NiPrunedFp32Fix, ENSD: 31337, NPW_weight: 1.4, AddNet Enabled: True,
AddNet Module 1: LoRA, AddNet Model 1: accidentalExposure_v10(6f7b8fdc6491), AddNet Weight A 1: 0.85,
AddNet Weight B 1: 0.85
CFG 18 is literaly the pinnacle of AI