[Stable Diffusion] Prompt Sharing and Learning Thread

modine2021

Member
May 20, 2021
381
1,253
I use one called lora:skirtliftTheAstonishing_skirtliftv1:1

It absolutely loves just doing a torso shot and cutting off the head even if I adjust the negative prompt to account for it. Making the resolution taller helps.

Most of these seem to b e bottomless rather than skirt lift, so you might want to add something about a skirt in the prompt. I don't normally see this, so think it might be something to do with the lab coat prompt.

This was produced with your prompt and negative, but i left everythin esle as the default. the checkpoint is realistic vision v13

View attachment 2520947

The one i use for shirt lift is lora:shirtliftALORAFor_shirtliftv1:1

View attachment 2520972
some success. i swtich models too. to


00000-3908372136.png
 

fried

Almost
Moderator
Donor
Nov 11, 2017
2,311
6,082
Could you please post a PNG with the prompts etc instead of a jpg? Thanks.
It certainly seems weird that it's not picking up the LoRA - unless you're missing the trigger word(s) in the prompt.
JPEG specification allows for metadata and their posted file did include such.

You can output either PNG or JPG files in AUTOMATIC1111 WebUI (perhaps others) with generation metadata included. I am not sure of other WebUIs, but for AUTOMATIC1111, simply drop the above file into the PNG Info tab and it will show full generation information.
 

Jimwalrus

Active Member
Sep 15, 2021
930
3,423
JPEG specification allows for metadata and their posted file did include such.

You can output either PNG or JPG files in AUTOMATIC1111 WebUI (perhaps others) with generation metadata included. I am not sure of other WebUIs, but for AUTOMATIC1111, simply drop the above file into the PNG Info tab and it will show full generation information.
Thanks, this was something I wasn't aware of and, being the know-it-all that I am didn't even try! I stand corrected and have edited my original post.
 

Jimwalrus

Active Member
Sep 15, 2021
930
3,423
anyone with experience with these? they just aint happening for me. even using the exact settings from authors samples. my results are all only normal poses with panties and shirts intact.





my results no panty pull or shirt lift

View attachment 2518558
Looking at the generation info that I now know is in the JPEG metadata, it seems to be referencing "<lora:pantypull-drop-3-000020:1>", while the one from Civitai by default is named "<lora:pantyPullPantyDrop_pantypullPantydropV1:1>".
You may have renamed it of course, but I'd double check your typing and/or redownload it from Civitai.

It certainly looks like what I'd expect if the LoRA is not being successfully referenced at all.
 
  • Like
Reactions: Mr-Fox

Snow972

Member
Dec 4, 2017
114
401
Hello, could someone give me a hand? I'm starting with "stable diffusion" and at boot time it gets stuck at DiffusionWrapper has 859.52 M params.
1680710869202.png

I have used the installer and more solutions such as clearing the cache, using the installer and pressing enter but it still does not advance.


I really don't know what I'm doing wrong
 

Mr-Fox

Well-Known Member
Jan 24, 2020
1,401
3,794


Take a look at the install instructions. "Make sure the required are met and follow the instructions available for both (recommended) and GPUs. "


  1. Install , checking "Add Python to PATH".
  2. Install
  3. Download the stable-diffusion-webui repository, for example by running git clone .
  4. Run webui-user.bat from Windows Explorer as normal, non-administrator, user.

    Watch this to see how git clone works
 

Snow972

Member
Dec 4, 2017
114
401
Did you open that bug? Or are there other pilgrims having the same issue currently:
In my case it shows no error. Perhaps we will have to wait more to see if it marks any errors.
How long do I have to wait for it to go from "DiffusionWrapper has 859.52M"?