[Stable Diffusion] Prompt Sharing and Learning Thread

deadshots2842

Member
Apr 30, 2023
162
277
It is a second step on each iteration to "temper" the result. I've heard it helps with CLIP data not getting extremely corrupted. Let say you had an apple in 50% of your lora images that was drawn at an angle for some reason. But you used WD14 and it tagged apple so the CLIP is strongly being trained on apple.

Maybe just use -apple in your tagger
Or if you have a lot of images 1000 or so and you notice 50-100 instance of apple compared to 999 1girls
maybe through in some regularization photos of an apple. Or 1girl holding an apple.
The issue would be you need regularization for all subjects.

Contrastive Language–Image Pre-training - CLIP

If you have ever had a lora that is garbled when the CLIP is used but works fine when it is disconnected that is likely from bad text encoder training.
And could be from over describing in the CLIP without regularization
It could also be from to high a Text Encoder Learn rate but that is less likely as most people reduce the TE

Their have been claims of teaching an art style with 10 photos of an apple in the style and 10 regularization images of a photo of an apple.
I haven't tried it but my intuition says it would just be a lora that could draw an apple




Likely but I would recommend at minimum knowing what version of Python you used to install (Conda, Windows App store Python, Python from Python.org) before you start deleting folders.

You can also look up where the cache is stored as it should be a few GB also
I think I figured it out got my storage back while everything still works.
 

moodorama

New Member
Mar 13, 2021
3
1
Hi all! What if, when creating a wide-format picture, two people create it instead of one? I would like to make pictures with one person for my desktop background. What are the options?

(I use SD 1.5 models, I specify “solo, alone, 1girl” in promt, and “multiple human, double human” in negative)
 

osanaiko

Engaged Member
Modder
Jul 4, 2017
2,212
3,707
Hi all! What if, when creating a wide-format picture, two people create it instead of one? I would like to make pictures with one person for my desktop background. What are the options?

(I use SD 1.5 models, I specify “solo, alone, 1girl” in promt, and “multiple human, double human” in negative)
use inpaint to mask over the 2nd figure, then in your prompt describe the objects you want in the place, along with the stylistic or scene parts of your original prompt. in the inpaint negative prompt put "1girl, person, human"
 

moodorama

New Member
Mar 13, 2021
3
1
use inpaint to mask over the 2nd figure, then in your prompt describe the objects you want in the place, along with the stylistic or scene parts of your original prompt. in the inpaint negative prompt put "1girl, person, human"
it takes too much time. I want to find a way to generate it with the desired result.
In my case, I generate a stream of images and some have to be deleted, since I will spend extra time on inpaint (stopping generation, manipulating the image, and generating again)

Maybe there are models in which this is fixed?
 
  • Haha
Reactions: osanaiko

EvylEve

Newbie
Apr 5, 2021
31
56
it takes too much time. I want to find a way to generate it with the desired result.
In my case, I generate a stream of images and some have to be deleted, since I will spend extra time on inpaint (stopping generation, manipulating the image, and generating again)

Maybe there are models in which this is fixed?
check Regional Prompt extension, gives you ways to divide your canvas and assign prompt pieces to every region, it may help.
check
 

deadshots2842

Member
Apr 30, 2023
162
277
It will depend on the photo you use as an input, if you use a realistic face it will add a realistic face. If you use an anime style face it should add an anime style face.
Maybe you would show me exampls? I'm having a hard time installing reactor if you would show me some examples and it works I'll install it somehow.
 

deadshots2842

Member
Apr 30, 2023
162
277
It should be pretty easy to install. but if installing it from within A1111 isn't working for you just install from url its what I always do.
Insighface distribution was not found and is required by the application
I'm getting this error I have installed stable diffusion in D drive is that a reason I'm getting this?

And also getting " no module named insightface. App

And ask I have installed roop and insight face and still getting this install Reactor from auto1111 and still this problem
 

devilkkw

Member
Mar 17, 2021
295
997
remove version and install: pip install insightface
but if you are in a1111 with venv, you need to activate venv before install.
after done edit your bat files and add "--skip-install" "--skip-prepare-environment" in set COMMANDLINE_ARGS.
 
  • Like
Reactions: Synalon

deadshots2842

Member
Apr 30, 2023
162
277
remove version and install: pip install insightface
but if you are in a1111 with venv, you need to activate venv before install.
after done edit your bat files and add "--skip-install" "--skip-prepare-environment" in set COMMANDLINE_ARGS.
Now?? Even when I install project do I have to install poetry or something like that too?
 

osanaiko

Engaged Member
Modder
Jul 4, 2017
2,212
3,707
Now?? Even when I install project do I have to install poetry or something like that too?
Bro, none of this stuff you are using comes from a commercial project. The whole automatic1111 toolset and all the plugins etc are just some "Anon"s volunteering their time and efforts to put a relatively usable front end on the free Stable Diffusion models released by StabillityAI. They are just anon hackers who are sharing cool tech with the rest of the world for free.