[Stable Diffusion] Prompt Sharing and Learning Thread

Mr-Fox

Well-Known Member
Jan 24, 2020
1,401
3,794
use this Additional Networks extension
https://f95zone.to/threads/stable-diffusion-prompt-sharing-and-learning-thread.146036/post-10255639

then you just use <NAME> just need to remove the lora: and :0.7 or no tag depending on what you are trying to create
It works both ways. The Additional Network extension is just another way of using lora's. It is limited to 5, but if you can't get the result that you want with 5 or less then you are probably doing something wrong.. The only benefit with it is that you can separate UNet/Text Encoder weights and fine adjust both. It's a bit overkill for most since generating images with ai isn't that consistent and predictable. But if you have the need to tickle your OCD go for it.
 
  • Haha
Reactions: sharlotte

Mr-Fox

Well-Known Member
Jan 24, 2020
1,401
3,794
Nah bro its from Social Media, I'm trying to recreate the whole aesthetics of the images I posted, to perfection. which I am not able to achieve 100% on my own.
Well look through civitai, I have seen many similar types of images there. The prompt is what will make it happen for you and the checkpoint will facilitate it. Some checkpoints will be easier to work with than others but it will not be the thing that makes an image possible or not possible, only easier and relatively more consistent. Then of course lora's and similar can of course make it easier as well, as long as it has been trained by someone who has a clue. Don't assume that it was the latest version of the checkpoint that was being used in those images and it's not for sure that it was the same checkpoint in all images.

I just discovered , it looks like it can be a good candidate, at the very least worth a try. I have seen highpoly lora being use in combination with , it's worth a try also.
 
Last edited:

Nano999

Member
Jun 4, 2022
155
69
use this Additional Networks extension
https://f95zone.to/threads/stable-diffusion-prompt-sharing-and-learning-thread.146036/post-10255639

then you just use <NAME> just need to remove the lora: and :0.7 or no tag depending on what you are trying to create
Additional networks are buggy and not working with some loras, I do not recommend to use it and they are also extending the promting time writing, as all promts I have they are pre-written in .doc

My original question was ignored
 

Mr-Fox

Well-Known Member
Jan 24, 2020
1,401
3,794
Additional networks are buggy and not working with some loras, I do not recommend to use it and they are also extending the promting time writing, as all promts I have they are pre-written in .doc

My original question was ignored
No one is ignoring your question, it's just that no one knows either way for sure. The only way is to test it for yourself and you did and couldn't see any difference. Essentially I think you answered your own question. It would be my guess also that it doesn't matter where you put it in the prompt since it's not a normal prompt token.
 

Mimic22

Newbie
Jul 2, 2018
26
10
Hi, i have a problem, i installed Stable Diffusion, but it is running on my CPU rather than on my Nvidia GPU, so it lacks the Vram to do what it needs to do.

How to make it use my Nvidia GPU instead ?

Thanks !
 

Schlongborn

Member
May 4, 2019
383
1,332
Btw. guys there is a fork of automatic1111:

That one seems to be more active development wise, some improvements over automatic1111 already, less clutter, but these things can change fast. Maybe worth checking out though.
 

rayminator

Engaged Member
Respected User
Sep 26, 2018
3,041
3,140
Btw. guys there is a fork of automatic1111:

That one seems to be more active development wise, some improvements over automatic1111 already, less clutter, but these things can change fast. Maybe worth checking out though.

if you one page back you would of seen this post https://f95zone.to/threads/stable-diffusion-prompt-sharing-and-learning-thread.146036/post-10581565

it been posted already

automatic gets updates daily
automatic1111 last update was a month ago
 
  • Like
Reactions: Mr-Fox and osanaiko

TitaniumDickDiamondBalls

Well-Known Member
Mar 24, 2019
1,010
3,416
Found this pretty sweet LoRa tutorial.



Comes with dataset creation tool and LoRa ( LoCon and LoHa can be trained too, I think ? ) trainer forms to make it even more user friendly.


 
Last edited:

Mr-Fox

Well-Known Member
Jan 24, 2020
1,401
3,794
Found this pretty sweet LoRa tutorial.



Comes with dataset creation tool and LoRa ( LoCon and LoHa can be trained too, I think ? ) trainer forms to make it even more user friendly.


A really good place for info about training lora's is this . Op is updating it regularly as he learns more and also the dev community is making progress with new tools and functions being released etc. I learned a lot from reading it when I have been training my own lora.
 

Mr-Fox

Well-Known Member
Jan 24, 2020
1,401
3,794
Hi, i have a problem, i installed Stable Diffusion, but it is running on my CPU rather than on my Nvidia GPU, so it lacks the Vram to do what it needs to do.

How to make it use my Nvidia GPU instead ?

Thanks !
No one can help you with that little information. Are you using Auto1111? How did you install it? And most importantly what kind of gpu do you have and how much vram? Have you made sure you meet the required ?
Read the install instructions on github and also watch the tutorial by Sebastian to see if you have missed something.

 
  • Like
Reactions: devilkkw

Mr-Fox

Well-Known Member
Jan 24, 2020
1,401
3,794
Another user had this problem and it was caused by not having updated the gpu in a long time. Update your stuff and see if it helps.
 

Mr-Fox

Well-Known Member
Jan 24, 2020
1,401
3,794
Can someone find what model/checkpoint this creator uses?
View attachment 2586808 View attachment 2586810
View attachment 2586811 View attachment 2586812
Insta id:-
It's impossible without the meta data. We can only guess and speculate. Or you can message the poster and ask pretty please with sugar on top.. Insta account is dead fyi.




 

Sepheyer

Well-Known Member
Dec 21, 2020
1,531
3,618
a_03169_.png
You don't have permission to view the spoiler content. Log in or register now.
So here is a dillema. The promps are inside the images - they are Comfy UI prompts and look like this:
Illustration.png
They can't really be reproduced in Automatic1111 because of all the composing. Namely there are two sets of prompts and two sets of negative prompts. Three sets of seeds, and three sets of image x steps combinations. These prompts can be reproduced only inside Comfy UI - by loading any of the PNG files inside this post (except for the screenshot of the workspace),
 
Last edited: