[Stable Diffusion] Prompt Sharing and Learning Thread

[Mr-Fox]

I took a quick but gentle stab at Lun@'s lovely succubus. Firstly and foremost because I really liked the image and I was also curious, secondly to show an example of how to structure the prompt.

Example from PromptGeek's awesome ebook:

" [STYLE OF PHOTO] photo of a [SUBJECT],
[IMPORTANT FEATURE], [MORE DETAILS], [POSE OR ACTION],
[FRAMING], [SETTING/BACKGROUND], [LIGHTING],
[CAMERA ANGLE], [CAMERA PROPERTIES],
in style of [PHOTOGRAPHER] "

I use a similar structure but not exactly the same.

If you wish you can compare the two prompts. Not to be pointing finger at Lun@ but for learning.
I grabbed the essentials but simplified it and corrected typo's etc. You could refine it more and expand but it's not my project so I leave that to Lun@.

This was the first and only image I generated.


I made a post recently about Prompt Geeks's book:
https://f95zone.to/threads/stable-diffusion-prompt-sharing-and-learning-thread.146036/post-12775145

 

[Mr-Fox]

Appreciate all the info shared in this thread. I am only just starting to mess with AI image generation. Is anyone aware of a good series of videos that unpack how to get a1111 all setup without focusing on every little nerd-knob and feature? Basically, I'm looking for an a1111 Deployment Guide along the lines of a Quick-Start guide that gets you up and running with everything you need as fast as possible so that you can spend more time creating than configuring the tool you're using to create ;-)

https://f95zone.to/threads/stable-diffusion-prompt-sharing-and-learning-thread.146036/post-12790594

or just scroll up..

 

[me3]

So i pieced together most parts of the prompt from this post by Sepheyer
There might have been some bored student/classmate at one of the desks putting their notebook to some proper use.

Spoiler: prompt

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

 

[devilkkw]

I'll throw out that for a photo realistic but blurry or almost green screened effect the LCM sampler can produce high quality images. LCM can also make a smooth almost 3D looking image when doing image to image without negative prompts just lower the config scale.

The DDPM sampler is my go to now for photoreal even over the new huenpp2.

I can stress the importance of adjusting the config scaling as some samplers will be horrible at the default 8

also...

You must be registered to see the links

View attachment 3293599

Really ddpm for realism? in my test it wash out skin and get like 3d render (like daz3d) image.
The best for me, in CUI, is unipc with those trick:
made half size image with unipcbh2, 5-6 step, normal scheduler, 6 to 8 cfg (prompt depending).
Upscale x2 latent (to get finel size you want) then pass the latent to another ksampler, using cfg 5 to 7, exponential sceduler, 20/25 step.
With this you get good level of detail and good realism.
For example fantasy:

And real:


I used my embedding for photoreal and skin detail, using trick i suggested.
Also i don't know if is different with checkpoint, i have only my self worked checkpoint and don't use any other, need to test if sampler work different in other checkpoint, never had a test on those way.
Can you do some test on this way?
BTW, thx for lora, did you made a 1.5 version?

 

[me3]

I took a quick but gentle stab at Lun@'s lovely succubus. Firstly and foremost because I really liked the image and I was also curious, secondly to show an example of how to structure the prompt.

Example from PromptGeek's awesome ebook:

" [STYLE OF PHOTO] photo of a [SUBJECT],
[IMPORTANT FEATURE], [MORE DETAILS], [POSE OR ACTION],
[FRAMING], [SETTING/BACKGROUND], [LIGHTING],
[CAMERA ANGLE], [CAMERA PROPERTIES],
in style of [PHOTOGRAPHER] "

I use a similar structure but not exactly the same.

If you wish you can compare the two prompts. Not to be pointing finger at Lun@ but for learning.
I grabbed the essentials but simplified it and corrected typo's etc. You could refine it more and expand but it's not my project so I leave that to Lun@.

This was the first and only image I generated.
View attachment 3294744

I made a post recently about Prompt Geeks's book:
https://f95zone.to/threads/stable-diffusion-prompt-sharing-and-learning-thread.146036/post-12775145

Borrowing most of lun@'s prompt and since there was a large number of comic artists mentioned it seems a bit wrong not to have some more "comic" like images.




And something else...


All is the same prompt, just different models.

Spoiler: prompt

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

 

[Microtom]

Ok so I made a post previously about guided training to easy the formation of the neural network. I made a first run.

So the AI associate words with image components. But it has to identify them somehow. For something like a pussy, it has multiple parts that aren't super obvious. The AI might never be able to distinguish them. That's why pussy, hands and other complexe parts are hard for it.

So, the solution is to guide it to make associations. You create an image that contains two identical images. On on side you color the region of the concept you want to teach the AI. It makes the association quickly this way.

Here are examples of such images.

Spoiler

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

For this first attempt, the dataset had about 140 images. 35 were pussy close-ups, either in front side or back side.

The training prompts look like this:

Color-associated regions in two identical side-by-side photographs of the front side view of a spread pussy.
Shaven pussy.
The magenta region is the labia majora.
The green region is the pussy lips or labia minora.
The red region is the clitoris hood. The blue region is the clitoris.
The cyan region is the closed anus or closed asshole.
The yellow region is the slightly opened vaginal opening.

So each region is given a description to associate to.

The dataset didn't have duplicates, if I remember correctly, I did 10 epochs of 6 repeats at 4 batch size.

So, with the lora it gave me, I can ask it to just generate a pussy. Example:

Spoiler

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

As can also ask to generate a pussy and identify a region by giving it a color. A failed attempt:

Spoiler

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

Again, but a successful attempt:

Spoiler

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

I can also ask to show multiple regions like in the training photos.

Spoiler

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

The red color was used to identify the clitoris hood, but it may have been mistaken for the vaginal walls that are seen in some photos.

The magenta might also be problematic. I might have to pick more distinctive colors. But there are just so many colors and I'm not sure if I can use the same for different concepts.

So, for a training set of just 35 pussy close-up, that's pretty fucking good imo. This same method would work well for fingers too.

 

[Fuchsschweif]

Hey guys! After A1 crashed my computer back then, I'd like to give the whole thing another shot, but with Comfy GUI. Can someone point me to a good installation / setup guide, or should I just go to youtube and roll with whatever is high rated?

 

[felldude]

BTW, thx for lora, did you made a 1.5 version?

Not with that dataset but I have an old 1.5 Lora that is on my civitai page.

Also I've noticed that some lora's if the clip is highly trained will require a cfg scale in the 20's to generate good results image to image.

All of these examples are image to image at around .5 (PNG so the data is in the file)

LCM soft background and soft features.



DDPM 14 cfg no negatives.



And the final one is an example of not having "AI girl" show up do to strong negatives using a a Lora at -1.0 and .5


Final is native up scaled to 1280x1536
(I'd fix the color and eye size asymmetry normally....and probably miss something big like 6 fingers )

 

[namhoang909]

Housekeeping regarding settings:

1. Go to tab "Parameters", set "max_new_tokens" to the very max. As of today, the fresh install comes with max of 2000.
2. Go to tab "Chat settings", then subtab "Instruction Template", choose "guanaco non-chat".
3. Go to tab "Text generation", input field, and then: "Write a script for the red riding hood porn film." and watch the magic happen.

I followed the instruction to 3rd step, it said there was no model, so I chose downloaded model at Model tab then it threw this error 'OSError: It looks like the config file at 'models\guanaco-7B.ggmlv3.q4_1.bin' is not a valid JSON file.' Did I miss something?

 

[Sepheyer]

I followed the instruction to 3rd step, it said there was no model, so I chose downloaded model at Model tab then it threw this error 'OSError: It looks like the config file at 'models\guanaco-7B.ggmlv3.q4_1.bin' is not a valid JSON file.' Did I miss something?

So, this language model setup changed since then and regretfully no longer rather valid. The language models are downloaded and installed somewhat differently now.

In the "model" tab, go to field "Download model or LoRA" on the right and paste there the link to a model: TheBloke/Xwin-MLewd-7B-V0.2-AWQ

Then click download.

Now, what happened between here and June when I posted that message, is the UI changed and the new set of models, the AWQ ones got introduced. So now one downloads the models via the UI because there is actually a bunch of files downloaded.

Then, once the download is ready and you choose the model, make sure the type of the model is "AWQ". Good luck.

 

[Mr-Fox]

Hey guys! After A1 crashed my computer back then, I'd like to give the whole thing another shot, but with Comfy GUI. Can someone point me to a good installation / setup guide, or should I just go to youtube and roll with whatever is high rated?

Learn ComfyUi part one of a series by Olivio Sarikas:

You must be registered to see the links

Sepheyer and me3, also a couple more are our local ComfyUi experts. I'm sure they will help you also.

Who knows me and Jim might be persuaded to give it a go also. I know that I for one is intrigued and curious about it but out of boneheaded-ness not taken the plunge yet.

 

[namhoang909]

Spoiler: Model tab

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

Maybe I mess up something because it seems censored now.

Spoiler: Write a script for the red riding hood porn film

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

PS: So I am trying to create some semi-realistic image of a T-rex wearing samurai clothes, this is generated by AI, thing is it is too long, and I don't know if it was the model or the prompt or something else, that I have not got a good render so far, can someone help, please? I have Cyberrealistic & neverendingdream (others are realistic models), what would you suggest?

A magnificent T-Rex known as "Tatsu-Rex," its body was adorned with intricate, hand-painted designs inspired by the famous woodblock prints of Hokusai and Hiroshige. Its scales shimmered with the iridescence of sumi ink on silk, while its eyes bore the intensity of a Shunga painting. The mighty beast moved with the fluidity of a Kabuki dancer, each step leaving a trail of cherry blossoms in its wake.
As Tatsu-Rex stalked its prey among the bamboo groves and serene gardens of feudal Japan, it wore a (samurai helmet) atop its massive head, its crest flickering with the brilliance of a kaleidoscope. With every breath, plumes of smoke issued forth, scented with the fragrance of incense and the earthiness of charcoal. The beast would spend its nights meditating under the moonlight, its mind transcending the boundaries of space and time, much like the great masters of Zen Buddhism.
Tatsu-Rex was not just a fearsome predator, but also a symbol of the harmony between the natural world and the refined arts of Japan. It walked the line between the primordial and the refined, proving that even the most imposing of creatures could be tamed by the beauty and sophistication of Japanese culture.

Spoiler: T-fail

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

PS: After removing most of detail this I what I got, while it look like a dinosaur or lizard? it is not the T-rex I know
PS: I am trying this SDXL model

You must be registered to see the links

while the creator provided it with a workflow for ComfyUI and I have downloaded everything in 'Install missing custom nodes' this one node is still missing "GetLatent_(WidthHeight) _0"

 

[me3]

Spoiler: Model tab

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

Maybe I mess up something because it seems censored now.

Spoiler: Write a script for the red riding hood porn film

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

PS: So I am trying to create some semi-realistic image of a T-rex wearing samurai clothes, this is generated by AI, thing is it is too long, and I don't know if it was the model or the prompt or something else, that I have not got a good render so far, can someone help, please? I have Cyberrealistic & neverendingdream (others are realistic models), what would you suggest?

Spoiler: T-fail

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

PS: After removing most of detail this I what I got, while it look like a dinosaur or lizard? it is not the T-rex I know

Thing is you might be fighting with your choice of model, might be worth doing some very simple tests to see what it "understands".
Try just getting a t-rex and see if that gets you roughly what you're looking for in a few images. Do the same with a samurai and with and try to dress up a more normal thing in samurai clothing/outfit. The more "finetuned" your model is the more "narrow" it gets in it's understanding, so you lose a lot of "general knowledge".

Looking at the image it does seem like there's at least some understanding of the concepts you're after, reason it's on four legs is probably more down to it being a landscape format and the AI tries to use as much of the width as possible. Try a portrait and see if the thing gets up on its hind legs, or force the prompt to do it. IE telling it how to stand.

 

[Mr-Fox]

A small guide for the beginners of A1111: How to install extensions.

Go to the extensions tab and "available",
click "load from", (the database url should already be in the text box).
It will load the extensions database and you can see all that is available.


There is a search bar, type "reactor" for example.
You should now only have one extension in the list, press "install" and then wait for it to finish.


then click "installed" tab and and press "apply and restart Ui".


Sebastian Kamph reactor guide:

You must be registered to see the links

 

[sharlotte]

My take from CUI on the succubus prompt. Now, I can only post the jpg as the PNG is just a wee bit too large for the forum:
I resisted CUI but I've seen the light
Edit: forgot to add, both images above are from the same prompt, random gen, SDXL, originally 1024*1024 upscaled *4.

 

[Lun@]

Looks like I started a Succubus fetish on here

They all look great! I can't wait to spend time at the weekend experimenting in SD. Having to work sucks

 

[Mr-Fox]

Tools tip for reactor.
Sebastian Kamph reactor guide:

You must be registered to see the links

Something Sebastian didn't mention is that you can "create" a face model with reactor, essentially scanning in the image and then save it so you don't need to load in the image manually all the time. You could have different versions of the same character also ofc.
Go to "tools" tab in reactor and load in the image, then name the face model and press "build and save".


Now you only need to go to "Face Model" instead of "Image" and select the facemodel in the list.

 

[Mr-Fox]

My take from CUI on the succubus prompt. Now, I can only post the jpg as the PNG is just a wee bit too large for the forum: View attachment 3297159 View attachment 3297149 View attachment 3297148
I resisted CUI but I've seen the light
Edit: forgot to add, both images above are from the same prompt, random gen, SDXL, originally 1024*1024 upscaled *4.

Wow Some proper ram horns.. You sure it's a succubus and not a female "faun" ? ..


Or SCP 666..

You must be registered to see the links

 

[me3]

Just wanted to see how it would work, but it seems like it should be a doable task.
This is just a very quick test with a very limited prompt so there's a bunch of issues, but the concept should work.


Prompt is basically just t-rex dressed as a samurai, bamboo forest background

 

[modine2021]

anyone else gettin annoyed with Civitai now? this mess is throughout the pages. on the side, at the bottom, at the top, a pop up, mixed with the models results, etc etc..gotta keep blocking with ublock..annoying