[Stable Diffusion] Prompt Sharing and Learning Thread

daddyCzapo

daddyCzapo

Member
Mar 26, 2019
242
1,500
Hi! I recently started messing around with sd, and wanted to share with you some of my very basic prompts, at first i just fulfilled my perv fantasy, so bare with me :p


You don't have permission to view the spoiler content. Log in or register now.

You don't have permission to view the spoiler content. Log in or register now.
You don't have permission to view the spoiler content. Log in or register now.
You don't have permission to view the spoiler content. Log in or register now.

Most of them have vary basic prompts, and are fucked up in some kind of way.. but i like them and just wanted to share with you guys. Models used are either experience or pfg, don't know if that's in the png data
 
  • Like
Reactions: modine2021, Jimwalrus and Mr-Fox
Mr-Fox

Mr-Fox

Well-Known Member
Jan 24, 2020
1,401
3,802
fr1ko said:
Hi! I recently started messing around with sd, and wanted to share with you some of my very basic prompts, at first i just fulfilled my perv fantasy, so bare with me :p


You don't have permission to view the spoiler content. Log in or register now.

You don't have permission to view the spoiler content. Log in or register now.
You don't have permission to view the spoiler content. Log in or register now.
You don't have permission to view the spoiler content. Log in or register now.

Most of them have vary basic prompts, and are fucked up in some kind of way.. but i like them and just wanted to share with you guys. Models used are either experience or pfg, don't know if that's in the png data
Click to expand...
This is very good and better than most that just started. Yes the checkpoint(model) is always in the data.
For the realistic stuff I would like to recommend that you try out
You must be registered to see the links
.
devilkkw have created merged checkpoints that might be good for semirealistic and stylized stuff, at the very least worth checking out.
His latest:
You must be registered to see the links

I'm looking forward to see more from you.
 
  • Like
Reactions: devilkkw, Sepheyer and daddyCzapo
daddyCzapo

daddyCzapo

Member
Mar 26, 2019
242
1,500
Mr-Fox said:
This is very good and better than most that just started. Yes the checkpoint(model) is always in the data.
For the realistic stuff I would like to recommend that you try out
You must be registered to see the links
.
devilkkw have created merged checkpoints that might be good for semirealistic and stylized stuff, at the very least worth checking out.
His latest:
You must be registered to see the links

I'm looking forward to see more from you.
Click to expand...
Oh, i will definitely try these out, thanks. I tried to do as much research beforehand as i can so it's not completely garbo :p From my experience, experience_70 is great for the "wet, sweaty, shiny" look that i was going for, and pfg gives more cartoon-ish vibe to the generated images.
And here's one more, that i forgot to add in the first post:
You don't have permission to view the spoiler content. Log in or register now.
 
  • Like
Reactions: Jimwalrus and Mr-Fox
Mr-Fox

Mr-Fox

Well-Known Member
Jan 24, 2020
1,401
3,802
I have been working on my first Lora. I had a lot of problems at first and had to do a lot of trial and error.
However now I'm starting to get better results.
If you have a pascal 10series card like me, you might get an error and can't use AdamW8bit. I tried to use Lion as recommended but got terrible results. I have set it to get a sample image last step for each source image so I can follow the process.
I found a very good guide
You must be registered to see the links
. This article gave a solution.
You need to download "
You must be registered to see the links
" rename the file libbitsandbytes_cudaall.dll to libbitsandbytes_cuda116.dll, put it in sd-scripts\svenv\Lib\site-packages\bitsandbytes\ (overwrite). Download the 0.35 one
You must be registered to see the links
.
Since I use kohya ss, I put mine in kohya_ss\venv\Lib\site-packages\bitsandbytes.
Now I can use AdamW8bit and is getting much better results. The guides videos I have watched recommended to use clip 2.
I will try to use clip 1 and see if it makes a difference. An observation is that the checkpoint you are using for your training could be something very important that makes a big difference. I don't know yet wich one is a good choice.
To be continued..
 
  • Like
  • Red Heart
  • Love
Reactions: Jimwalrus, devilkkw, Sepheyer and 1 other person
Mr-Fox

Mr-Fox

Well-Known Member
Jan 24, 2020
1,401
3,802
fr1ko said:
Oh, i will definitely try these out, thanks. I tried to do as much research beforehand as i can so it's not completely garbo :p From my experience, experience_70 is great for the "wet, sweaty, shiny" look that i was going for, and pfg gives more cartoon-ish vibe to the generated images.
And here's one more, that i forgot to add in the first post:
You don't have permission to view the spoiler content. Log in or register now.
Click to expand...
Instead of wet skin, wich get you the pink slime:p. I'm assuming here because I can't run SD to check the png info while I'm doing Lora training. Try to use moist skin or oiled skin or oily skin etc.
Liquids are problematic for SD as of yet. Oh and it's well worth the cost to upgrade your pc to 32Gb of ram if you can.
 
  • Like
Reactions: devilkkw, Sepheyer and daddyCzapo
daddyCzapo

daddyCzapo

Member
Mar 26, 2019
242
1,500
Mr-Fox said:
Instead of wet skin, wich get you the pink slime:p. I'm assuming here because I can't run SD to check the png info while I'm doing Lora training. Try to use moist skin or oiled skin or oily skin etc.
Liquids are problematic for SD as of yet. Oh and it's well worth the cost to upgrade your pc to 32Gb of ram if you can.
Click to expand...
actually, i used both, so that's probably why the results are mixed :) as of right now, a lot of what i generate depends highly on the seed, so i just do the trial and error, by generating 10-20 images in a batch, picking the best looking ones and then using the seed, dialing the details a bit.
 
  • Like
Reactions: Mr-Fox
Mr-Fox

Mr-Fox

Well-Known Member
Jan 24, 2020
1,401
3,802
  • Red Heart
  • Like
Reactions: devilkkw, neelsoul, daddyCzapo and 1 other person
devilkkw

devilkkw

Member
Mar 17, 2021
323
1,093
When i merge checkpoint, i do a lot of test before release it.

This is one of some test: how a word change everything.

Prompt: beautiful TYPE portrait of a Spanish woman, details, elegant, centered, symmetrical
Negative prompt: (bad quality, worst quality, low quality:1.2) render

Type= type of image, or something your fantasy think


Action figure
act-fig.png
Anime
anime.png
Crayon
crayon.png
Marble
marble.png
Pencil
pencil.png
Pixel art
pixel.png
Sand
sand.png
Simpsons
Simpsons.png
Splatter
splatter.png

There are many more, just try.
 
  • Like
  • Red Heart
Reactions: modine2021, Jimwalrus, PandaRepublic and 3 others
Mr-Fox

Mr-Fox

Well-Known Member
Jan 24, 2020
1,401
3,802
My experimentation with creating lora's is continuing. From my last post I mentioned testing if using clip 2 is good or bad.
Even though I only have a limited amount of data, it's seems so far that it is indeed giving an improvement over not using it.
I found a setting I had completely missed and that no tutorial video is mentioning and it is Noise Offset.
After reading a few posts about it I'm still not sure what it does. I will try it out in the next training session.
You can set a value between 0-1. In the thread I found about it they said 0.2 looks promising.
To be contiued..
 
  • Like
Reactions: VanMortis, devilkkw, Sepheyer and 1 other person
Mr-Fox

Mr-Fox

Well-Known Member
Jan 24, 2020
1,401
3,802
Great information sources for lora training.
You must be registered to see the links
(both dreambooth SD extension and kohya)
You must be registered to see the links

(more extensive and kohya focused)

Noise Offset : Increases dynamic range (brighter brights, darker darks). May "deep fry" if set too high.
What this means in practice I have no idea, good to know nonetheless.
 
  • Like
  • Red Heart
Reactions: modine2021, VanMortis, devilkkw and 2 others
devilkkw

devilkkw

Member
Mar 17, 2021
323
1,093
Nice one. please add prompt as rule.


Mr-Fox said:
My experimentation with creating lora's is continuing. From my last post I mentioned testing if using clip 2 is good or bad.
Even though I only have a limited amount of data, it's seems so far that it is indeed giving an improvement over not using it.
I found a setting I had completely missed and that no tutorial video is mentioning and it is Noise Offset.
After reading a few posts about it I'm still not sure what it does. I will try it out in the next training session.
You can set a value between 0-1. In the thread I found about it they said 0.2 looks promising.
To be contiued..
Click to expand...
On my pc i can't try Lora, but i trained some Textual inversion.
Lora have many setting's to set, hope you fuond best. You are training lora for style or for person-subject?
 
  • Like
Reactions: Sepheyer and Mr-Fox
Mr-Fox

Mr-Fox

Well-Known Member
Jan 24, 2020
1,401
3,802
devilkkw said:
Nice one. please add prompt as rule.




On my pc i can't try Lora, but i trained some Textual inversion.
Lora have many setting's to set, hope you fuond best. You are training lora for style or for person-subject?
Click to expand...
I guess a bit of both but technically it's a character,
You must be registered to see the links
.

1679515845654.png
 
  • Like
Reactions: Mark17, devilkkw and Sepheyer
devilkkw

devilkkw

Member
Mar 17, 2021
323
1,093
Mr-Fox said:
I guess a bit of both but technically it's a character,
You must be registered to see the links
.

View attachment 2487597
Click to expand...
sorry for double post. i want to see some result on your lora test, when you ready.


fanciful_dream said:
I want to fix my hands :cry:
Click to expand...
Sometimes triggering artist do better result's on hands, and if you have many artist in your prompt, you need to check inspect and prune prompt.
Also negative prompt: start without any negative to understand if prompt is good, then adding negative and keep generation every parameter you put in or stripe out.
 
Last edited:
  • Hey there
Reactions: Mr-Fox
You must log in or register to reply here.
Top Bottom