Create and Fuck your AI Slut -70% OFF
x

[Stable Diffusion] Prompt Sharing and Learning Thread

Sepheyer

Sepheyer

Well-Known Member
Dec 21, 2020
1,703
4,184
448
osanaiko said:
To be hon


To be honest, regional prompting is not a technique I've spend a lot of time on myself. I was parroting some advice I read elsewhere.

In truth, my process is to cut-n-paste the best parts of generated or real art images into a frankenstein's monster that is close to the composition I want, then use repeated cycles of img2img and manual editing +inpaint to finalize the result.

> "turn out exactly like you want is not happening"

This is precisely how the experience of using diffusion image gen goes...
Click to expand...
I am starting to think the answer is to move away from SDxx to Wan VACE, hardware permitting. That's what comes with "built in" hand fixes, regions, characters, consistent characters, muuch stronger context recognition.
 
  • Like
Reactions: mosnew
JhonLui

JhonLui

Well-Known Member
Jan 13, 2020
1,146
1,136
284
mosnew said:
Just found this thread.
Click to expand...
Take this from a "noob", so it may be more of a question than an answer..
but I'm facing the same problem with a different approach: (I'll try to be brief).

First a couple of considerations (maybe superfluous):
-WAI nsfw is an extremely good and complete base, so, before using a Lora, always check if the character is already in the Checkpoint model, than force the original style by adding "anime screencap" for anime or "official art" for 3d. Also the character must be specified with the trigger word WAI uses (there should be a database on the Github page) example:
"Nico Robin" is fine, but Nami has to specified with the series :"Nami \(one piece\)" or "Nami_(one piece)" to get a realistic look.
This yet doesn't solve the "clothes issue".
- For WaiNsfw (at least in HD resolution 1024x1024 etc..) 20 to 24 steps are more than enough, after that either you waist time, or there is a further risk of mismatch.
- Lately a couple of addons/alternatives came up you might wanna try:
"wai-2Rectified-V140": a lora that "focuses" Wai allowing a quality consistent result even with Hyper or Lightning (4steps)
"animeScreenshotMerge_v32": a Checkpoint based on WAI but "specialized" in multiple characters display (didn't try it a lot, but seems to be pretty good).
"koronemixVpred" might also be worth a try, as the VPred Models are still in developement, but seem to be much more precise.

Now onto the method (not a solution but a different approach that may give insights):

Since I use Hyper 4steps (with Fooocus) I tend to use the "strenght in numbers" approach: so start with a basic prompt, than when found the desired overall look, fix the seed or put a high Guidance (>7) and start building up the prompt untill the desired result.
Now.. in Foocus it's a mess specially with different chars because the structure isn't "language logic":
subject/description/action/object/description/reaction/situation but more "situation/description/subject/object/description/action/reaction/details, so switching characters or prevent a mismatch means a prompt overhaul...
But in Forge the "Break" method should still work, you may wanna look into it. (not sure)

As for something close to a solution to your problem.. I'm afraid the only way is to switch to ComfiUI (or SwarmUI: basically the same but with a Forge interface for start) the only way to have a detailed control on separates Loras ..afaik.
[both + many others free, portable and offline capable with Stability Matrix, provided you have a 1TB SD drive to dedicate]
Than use Control.net models (CPDS) for direct posing or inpainting. Yet I can't give you specific directions because I like to "play casually" with AI.

I hope it can be of at least some help, and any further detail or explanation is most welcome to help me too.
 
  • Like
Reactions: mosnew
M

mosnew

Newbie
Jul 12, 2020
19
9
54
Sepheyer said:
I am starting to think the answer is to move away from SDxx to Wan VACE, hardware permitting. That's what comes with "built in" hand fixes, regions, characters, consistent characters, muuch stronger context recognition.
Click to expand...
first time i am hearing of this
 
M

mosnew

Newbie
Jul 12, 2020
19
9
54
JhonLui said:
Take this from a "noob", so it may be more of a question than an answer..
but I'm facing the same problem with a different approach: (I'll try to be brief).

First a couple of considerations (maybe superfluous):
-WAI nsfw is an extremely good and complete base, so, before using a Lora, always check if the character is already in the Checkpoint model, than force the original style by adding "anime screencap" for anime or "official art" for 3d. Also the character must be specified with the trigger word WAI uses (there should be a database on the Github page) example:
"Nico Robin" is fine, but Nami has to specified with the series :"Nami \(one piece\)" or "Nami_(one piece)" to get a realistic look.
This yet doesn't solve the "clothes issue".
- For WaiNsfw (at least in HD resolution 1024x1024 etc..) 20 to 24 steps are more than enough, after that either you waist time, or there is a further risk of mismatch.
- Lately a couple of addons/alternatives came up you might wanna try:
"wai-2Rectified-V140": a lora that "focuses" Wai allowing a quality consistent result even with Hyper or Lightning (4steps)
"animeScreenshotMerge_v32": a Checkpoint based on WAI but "specialized" in multiple characters display (didn't try it a lot, but seems to be pretty good).
"koronemixVpred" might also be worth a try, as the VPred Models are still in developement, but seem to be much more precise.

Now onto the method (not a solution but a different approach that may give insights):

Since I use Hyper 4steps (with Fooocus) I tend to use the "strenght in numbers" approach: so start with a basic prompt, than when found the desired overall look, fix the seed or put a high Guidance (>7) and start building up the prompt untill the desired result.
Now.. in Foocus it's a mess specially with different chars because the structure isn't "language logic":
subject/description/action/object/description/reaction/situation but more "situation/description/subject/object/description/action/reaction/details, so switching characters or prevent a mismatch means a prompt overhaul...
But in Forge the "Break" method should still work, you may wanna look into it. (not sure)

As for something close to a solution to your problem.. I'm afraid the only way is to switch to ComfiUI (or SwarmUI: basically the same but with a Forge interface for start) the only way to have a detailed control on separates Loras ..afaik.
[both + many others free, portable and offline capable with Stability Matrix, provided you have a 1TB SD drive to dedicate]
Than use Control.net models (CPDS) for direct posing or inpainting. Yet I can't give you specific directions because I like to "play casually" with AI.

I hope it can be of at least some help, and any further detail or explanation is most welcome to help me too.
Click to expand...
will try that as alternate...i think my original point got lost. i first make image i like as you suggested with minimal prompt, use the chance to define my first main character and focus.. ie female and then change the second character, I had very decent success with inpainting. what I am trying is to sort out chinks that cant be found on youtube video as its SFW like best way to select a mask, ensure consistent changes like background, action, certain parts of clothes from where the character is swapped out etc.
 
JhonLui

JhonLui

Well-Known Member
Jan 13, 2020
1,146
1,136
284
mosnew said:
will try that as alternate...i think my original point got lost. i first make image i like as you suggested with minimal prompt, use the chance to define my first main character and focus.. ie female and then change the second character, I had very decent success with inpainting. what I am trying is to sort out chinks that cant be found on youtube video as its SFW like best way to select a mask, ensure consistent changes like background, action, certain parts of clothes from where the character is swapped out etc.
Click to expand...
I kind of guessed it, but couldn't take it for granted...
In that case (afaik) the impaint method seems to be the only way, with Control.net for adjusting the character, but at this point I wouldn't consider WaiNsfw + EulerA the best option since they are the most "powerful" but tend to get messy.
I suggest you try the Checkpoints I mentioned for anime, StableYogi's or Cyberillustrius for realistic, and 5MoonDoll for 3d.
Also BeretMixReal is excellent for realistic or 3d for "eastern look" characters.
 
  • Like
Reactions: mosnew
A

andthod

Newbie
Oct 16, 2022
68
43
28
hi bro how to download FLUX LORA from tensor art, CIVITAI got banned celebrity lora, u have torrent download ?
 
XenoHaze

XenoHaze

Member
Feb 10, 2018
449
1,300
250
Hi, do someone of you guys know the name of the following stable diffusion model and maybe also where I can find it?

I assume its a pony SDXL variant.
 
Last edited:
  • Jizzed my pants
Reactions: kaamist
T

thatcantbereal

Newbie
Mar 6, 2023
19
18
94
Can anyone give any suggestions of the type of art you would prompt to get something like the art in Stay Online.

I'm assuming it's some Pony variant or lora, but even the art type as a prompt would be a great start for me to learn.
 
PeachyVN

PeachyVN

Newbie
Jun 14, 2017
86
178
174
Does anyone know of a Discord server dedicated to ComfyUI NSFW workflows?

Or does anyone have any good workflows? Specifically image to video :)
 
osanaiko

osanaiko

Engaged Member
Modder
Jul 4, 2017
3,350
6,436
707
thatcantbereal said:
Can anyone give any suggestions of the type of art you would prompt to get something like the art in Stay Online.

I'm assuming it's some Pony variant or lora, but even the art type as a prompt would be a great start for me to learn.
Click to expand...
Those screenshots are 100% daz renders with some photoshop post-work. Not AI generated.
 
You must log in or register to reply here.
Top Bottom