[Stable Diffusion] Prompt Sharing and Learning Thread

[Mr-Fox]

dont know whats going on. but now all my images look like this. no matter what model i use. no mater what settings i use, they all end up like this. looks like HDR overkill. perhaps a setting in main got messed up. no idea. got all these nicely created girls etc. but the overall is this ugly result.

View attachment 2565737

When you get strange result like this, reboot everything and try again.
Just a guess, it could be that you used an embedding or hypernetwork and it is somehow lingering and breaking the prompt.
I have experienced this kind of issues also and it's the reason I stay clear of embeddings and hypernetworks most of the time.
In my experience they have a too large tendency to break things.
When I hade my issues it was like the cash or something related to memory hade been "clogged" by these type of injections and I had to restart and generate a bunch of throw away images to clear it out.
I could see it become less and less messed up when it finally "let go".
In your case maybe it was something else entirely, idk. That's SD for ya..
I see that you are using Unspeakable-Horrors embedding (TI). Try remove it and generate again.

 

[rayminator]

dont know whats going on. but now all my images look like this. no matter what model i use. no mater what settings i use, they all end up like this. looks like HDR overkill. perhaps a setting in main got messed up. no idea. got all these nicely created girls etc. but the overall is this ugly result.

View attachment 2565737

I have notice that too when I put CFG Scale or Sampling steps is up to high

 

[Elefy]

all my images look like this

Looks like hi CFG scale (but your PNG info show CFG 7)


this is CFG 30



and this is CFG 5



Or something is overdo here:

Model: NSFW-Style_chilloutmix_NiPrunedFp32Fix, ENSD: 31337, NPW_weight: 1.4, AddNet Enabled: True, 
AddNet Module 1: LoRA, AddNet Model 1: accidentalExposure_v10(6f7b8fdc6491), AddNet Weight A 1: 0.85, 
AddNet Weight B 1: 0.85

 

[HardcoreCuddler]

Looks like hi CFG scale (but your PNG info show CFG 7)
View attachment 2567649

this is CFG 30

View attachment 2567653

and this is CFG 5

View attachment 2567657

Or something is overdo here:

Model: NSFW-Style_chilloutmix_NiPrunedFp32Fix, ENSD: 31337, NPW_weight: 1.4, AddNet Enabled: True,
AddNet Module 1: LoRA, AddNet Model 1: accidentalExposure_v10(6f7b8fdc6491), AddNet Weight A 1: 0.85,
AddNet Weight B 1: 0.85

CFG 18 is literaly the pinnacle of AI

 

[Elefy]

I sank into a puddle of cum

 

[Mr-Fox]

View attachment 2567935

I sank into a puddle of cum

Liquids in SD.. No bueno..

 

[KingBel]

Hi, for those interested in training their own TI's, the tutorial by BelieveDiffusion is now available again:

You must be registered to see the links

 

[sharlotte]

Thanks KingBel, it's a fantastic step by step for TI and works perfectly too.

 

[Sepheyer]

Now ComfyUI can do face restore internally:

You must be registered to see the links

Also, Clarity 2.0 is out.

Spoiler: More

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

 

[Mr-Fox]

Also, Clarity 2.0 is out.

Yes for quite some time.. Apr 03.

 

[PandaRepublic]

Tried making a LORA of Bo-Katan but for some reason SD thinks she's really old lol any way to fix it?

Spoiler: mommy

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

 

[Mr-Fox]

Tried making a LORA of Bo-Katan but for some reason SD thinks she's really old lol any way to fix it?

Spoiler: mommy

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

Try to specify the age in positive (18, 20, 25 years old) and in negative add "wrinkles", "old" etc.
You can even add "young woman", followed by specified age.
Like so:
Photography, young woman, 20 years old, bo-katan, full body view, etc.

 

[Hunter9836]

Hey, what's up guys? I'm seriously hooked on this checkpoint and don't even wanna try anything else. I've experimented with a bunch of other models and even mixed some up, but still can't replicate this one on my own. Would really appreciate any help I can get. P.S: [1] Maybe Model NED is in the mix , and hipoly3Dmodel lora used [2]I've already gone through all the info available on this forum, but still struggling to nail this style View attachment 2576525

 

[Hunter9836]

how can i create this image, i am using SD can you help me

Can you please tell me the name of mix or the ckpt used???

 

[Mr-Fox]

Can you please tell me the name of mix or the ckpt used???

Use a checkpoint aimed for semirealism like deliberate, experience etc. Specify the style in your prompt. Keyword "fantasy".
Write in the positive what you wish to see in your image and write in the negative what you don't wish to see in your image.
Look around on civitai for user sample images in the style that you want and you will find a prompt that you can start out with.

 

[Hunter9836]

Use a checkpoint aimed for semirealism like deliberate, experience etc. Specify the style in your prompt. Keyword "fantasy".
Write in the positive what you wish to see in your image and write in the negative what you don't wish to see in your image.
Look around on civitai for user sample images in the style that you want and you will find a prompt that you can start out with.

I'm comfortable with the prompts, loras and embeds... But struggling with the Base Model itself... Can't seem to nail the image to perfection like the images I posted. FYI I've tried NED, REV, chilloutmix, Perfect World etc.

 

[Mr-Fox]

I'm comfortable with the prompts, loras and embeds... But struggling with the Base Model itself... Can't seem to nail the image to perfection like the images I posted. FYI I've tried NED, REV, chilloutmix, Perfect World etc.

What is it specifically you don't achieve? Where did you find those images? They look like they could come from civitai and if so you should know the checkpoint and the prompt.

 

[Hunter9836]

What is it specifically you don't achieve? Where did you find those images? They look like they could come from civitai and if so you should know the checkpoint and the prompt.

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.

 

[Nano999]

Recenetly I just tested over 200 checkpoints xD

btw a quick question. Does it make a difference if you put you <lora:NAME:0.6> right after trigger words in the middle of promt or in the end?

e.g. (trigger word is trigger1)

milf, outdors, trigger1, <lora:NAME:0.6>, looking at the viewer, grin, beautiful landscape, Egypt architecture

OR

milf, outdors, trigger1, looking at the viewer, grin, beautiful landscape, Egypt architecture
<lora:NAME:0.6>

I am doing it in the following way:

milf, looking at the viewer, grin,
beautiful landscape, Egypt architecture
outdors,
trigger1,
<lora:NAME#1:0.6>
<lora:NAME#2:0.6>
<lora:NAME#3:0.6>
<lora:NAME#4:0.6>

I see no difference, but maybe it might go wrong at some point?

 

[rayminator]

Recenetly I just tested over 200 checkpoints xD

btw a quick question. Does it make a difference if you put you <lora:NAME:0.6> right after trigger words in the middle of promt or in the end?

e.g. (trigger word is trigger1)

milf, outdors, trigger1, <lora:NAME:0.6>, looking at the viewer, grin, beautiful landscape, Egypt architecture

OR

milf, outdors, trigger1, looking at the viewer, grin, beautiful landscape, Egypt architecture
<lora:NAME:0.6>

I am doing it in the following way:

milf, looking at the viewer, grin,
beautiful landscape, Egypt architecture
outdors,
trigger1,
<lora:NAME#1:0.6>
<lora:NAME#2:0.6>
<lora:NAME#3:0.6>
<lora:NAME#4:0.6>

I see no difference, but maybe it might go wrong at some point?

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