TOWER OF DOOM (S01/E08)
A DARK TOWER SOMEWHERE IN TRANSYLVANIA WITH GOTH GIRLS, VAMPIRE GIRLS, HEAVY METAL CHICKS, BIKER BABES AND KELLY BUNDY IMPERSONATORS
ESTELLA
Meet Estella, a fierce heavy metal babe with a passion for 80s rock legends like Def Leppard, Mötley Crüe, and Judas Priest. When she's not rocking out to her favorite tunes, Estella channels her inner model, captivating the camera with her edgy and bold style. Surprisingly, she's not just about the glamour; Lexi also has a unique skill set as a pineapple peeler, showcasing her versatility and adding a touch of unexpected flair to her vibrant personality. Whether on stage, in front of the camera, or in the kitchen, This babe is a true force to be reckoned with.
WORKS BEST WITH THE TRUALITY ENGINE PRO
DONATIONS MAKE ME BUY FOOD, THANK YOU, CLICK HERE
1 EPISODE PER WEEK FOR EACH SERIES:
| TOWER OF DOOM | E-GIRLS MANSION | TRUALITY CAMPUS | WILD CATS ISLAND |
| GIRLS NEXT DOOR | INFLUENCERS DELXUE |
DISCLAIMER: All Models released by Tower 13 Studios are fictional, I can not know every person, every actor, every influencer in the world and resemblances are purely coincidental. While it is possible that I take inspiration from a look that I like, I have not, not will I ever use any of their original photos to create a resemblance on purpose. If anyone feels that one of my models resembles a celebrity, actress or influencer please leave a comment so I can verify and make an informed decision to delete them or not.
Description
FAQ
Comments (6)
Hot babe ! Was she inspired by that Rock-N-Roll Queen Pat Benatar ?
- Pat Benatar - Heartbreaker (Live)
no she was inspired by "didn't have that haircut yet"
These all look really good. I did want to ask though, any tips for getting these embeddings to have better body proportions? I cannot seem to stop getting the long torso/lanky look with alot of them. Also I seem to struggle with outfits. Most of the time it doesn't obey the prompt fully. Like adding minidress for example would give a bikini and other things like that
It depends on the checkpoint you are using, long torso sounds a lot like the Dream Shaper Checkpoint or a merged checkpoint building up on it. I can't give you any advice for other peoples checkpoints. This could have other reasons like a Lora that aggressively works against your prompt and distorts the embedding. My Models are designed for the Truality Engine and I am providing 20 sample prompts for each model.
If the checkpoint doesn't listen you need to check your spelling first, "minidress" is not a thing in the English language it is a 2 letter word, most checkpoints will ignore it "mini dress" would be proper and if it still doesn't listen you have to add weight (mini dress:1.5) you can as high as 1.7 max.... https://stablediffusion.cdcruz.com/prompts_list.html here are all legit prompt words for SD 1.5
@Tower13Studios Thanks! Yeah looks like I might need to just add more weights. Just thought I'd ask but for sure I need to experiment more
Hello and Good day.
Follow the instructions as posted by Tower13studios and I will also
give you some extra tips for you to test below....
-
If you have a great made model, but write bad prompts, you will not get the
best results from your created Lora or Textual-Inversion model.
ALSO, it is important to use a "checkpoint" for which type of image you want
to create - Photorealistic image ? or a Cartoon/Art type of checkpoint ?
-
These are from my own personal tests done on SD-1.5 since 2022 and I usually create
about 500+ images on a daily basis- Although most images I cannot post here because
I specialize on "Boudoir and Pin-up style images" and "Artist nude photography style images".
I never do porn. Too much of that on the web. LOL
I can leave you only with some Famous faces of my images for you to get an idea
as to how they may look like.
The following images below were created just using the original Stable-Diffusion 1.5
without the use of any Lora/Lycoris/Textual-Inversion, and using the same style
of written prompt as I have posted for you here. In many cases your Stable Diffusion 1.5
has already been trained on creating over 1996 famous faces without the use of any
pre-trained models.
It all depends on how well you write your prompts.
This is the full list of known faces , which is already inside
your Stable-Diffusion 1.5 program - https://laion-aesthetic.datasette.io/laion-aesthetic-6pls/celebrities
-
https://i.imgur.com/VuiQgOU.jpg
-
https://i.imgur.com/4CHOqDC.jpg
-
https://i.imgur.com/SuuGCpx.jpg
-
https://i.imgur.com/3jziP2r.jpg
-
https://i.imgur.com/XgdQVXX.jpg
-
-
I will delete this post in 24 hours - copy everything I have posted for you.
-
Best Samplers:
Euler a (fast render but not always the best for face portraits)
DPM++ 2M Karras
DPM++ SDE Karras
------------------------------
CFG scale: best settings
Portraits: 7 - 8 - 9
Landscape: 9 - 12
-----------------------------
Steps: best settings
Portraits: 30 - 40 - 70
Landscape: 40 - 80 - 100
-
my personal choice for best quality AI photo-realistic photography
images is these settings ...
CFG scale - 8
Steps - 70
------------------------------
Depending on what Checkpoints you will decide to use, each checkpoint
will Create the images differently and with different effects on the images.
My personal choice for Photo-Realistic Photographs has always been...
- Your Main Checkpoint -> Realistic Vision version 1.3, or version 5.1
- Checkpoint Mergers...selected in your SD menu.
A - Protogen X34
B - Clarity version 1.9
C - Deliberate version 2
Overall,
this is the best mix of 4 checkpoints to use for Photo-Realistic AI pictures.
-------------------------------------------------
(BELOW) is a very good prompt script for doing tests and create
some nice images while you test your A.I. to create some famous celebrity faces.
Depending on what Checkpoint you will use, some times it will
create the face and body Very Good (A+), and
if it does not, then you may need to use a Lora, or a T.I. for training your
A.I. to make them better.
.
This is for a female NSFW photo-realistic Photograph !
I will also post for you a SFW image prompt below.
... Do not change the word placement, as this prompt has
been tested for many months as to be the best place for the words to be
in the script. This is important.
Each section has importance for the AI to understand better and to create better images.
-
...........................Positive prompt for Not Safe For Work .......................................
...IF ITS A LORA MODEL - You will write it like this ...
(<YOUR LORA MODEL:0.9>),a Realistic Full Portrait Photo of a ___place LORA Trigger word name here____ with long hair style, Beautiful, Detailed face, Perfect eyes, (highly detailed skin:1.1), (perfect breasts:1.1), ((perfect nipples:1.1)), perfect body, NSFW, nude, pussy, best quality, Modelshoot style, Professional Photography, Photorealistic, standing in a Dark Studio background, blurred background, RAW, analog style, sharp focus, 8k, ultra high resolution, DSLR, high quality, Fujifilm XT3, film grain, award winning, masterpiece
...IF ITS A TEXTUAL-INVERSION (EMBEDDING) MODEL - You will write it like this ...
a Realistic Full Portrait Photo of a ___place Embedding model name here____ with long hair style, Beautiful, Detailed face, Perfect eyes, (highly detailed skin:1.1), (perfect breasts:1.1), ((perfect nipples:1.1)), perfect body, NSFW, nude, pussy, best quality, Modelshoot style, Professional Photography, Photorealistic, standing in a Dark Studio background, blurred background, RAW, analog style, sharp focus, 8k, ultra high resolution, DSLR, high quality, Fujifilm XT3, film grain, award winning, masterpiece
...........................Negative Prompt for NSFW for all.......................................
(Clothes), (clothing), (pants), (bra), (underwear), (dress), (shirt), (skirt), canvas frame, (deformed iris, deformed pupils, semi-realistic, CGI, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers, fused lips and teeth:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, doll, child, un-detailed skin, monochrome, black and white,
.......................................................................................
.......................................................................................
.......................................................................................
...........................Positive prompt for Safe for work .......................................
...IF ITS A LORA MODEL - You will write it like this ...
(<YOUR LORA MODEL:0.9>), a Realistic Full Portrait Photo of a ___place LORA Trigger word name here____ with long hair style, Beautiful, Detailed face, Perfect eyes, (highly detailed skin:1.1), perfect body, best quality, Modelshoot style, Wearing a Gold dress designed by Chanel, Professional Photography, Photorealistic, standing in a Dark Studio background, blurred background, RAW, analog style, sharp focus, 8k, ultra high resolution, DSLR, high quality, Fujifilm XT3, film grain, award winning, masterpiece
...IF ITS A TEXTUAL-INVERSION (EMBEDDING) MODEL - You will write it like this ...
a Realistic Full Portrait Photo of a ___place your embedding model name here____ with long hair style, Beautiful, Detailed face, Perfect eyes, (highly detailed skin:1.1), perfect body, best quality, Modelshoot style, Wearing a Gold dress designed by Chanel, Professional Photography, Photorealistic, standing in a Dark Studio background, blurred background, RAW, analog style, sharp focus, 8k, ultra high resolution, DSLR, high quality, Fujifilm XT3, film grain, award winning, masterpiece
...........................Negative Prompt for SFW for all.......................................
((NSFW)), ((Nude)), (Naked), (pussy), (vagina), canvas frame, (deformed iris, deformed pupils, semi-realistic, CGI, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers, fused lips and teeth:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, doll, child, un-detailed skin, monochrome, black and white,
......................................................................................
IF YOU WISH for the model to be Outdoors, change the word script in that
section areas with these words below ....
Photorealistic, sunny, standing in a beautiful beach background, blurred background, RAW,
-or-
Photorealistic, sunny, standing in a foggy forest background, blurred background, RAW,
......................................................................................
.
.
Using the above posted prompt, your images will look much better in details
and in a Photo-Realistic quality (without the use of any extra Lora or T.I.).
--- This is good for training and testing your A.I. Lora models to see if they are good.
.
BELOW is for the body and what words you should use in your prompts....
Part 10 - What type of body does our main subject have ?
If you do not write anything, the A.I. will take upon itself to do whatever it wants.
In this part , I will describe to the A.I. if we would like to see a particular body
type being created on our main person/subject.
As we all know, there are many body types we can describe to the A.I. to create.
Here are some useful words for you to write in your Prompts,
Examples...
Tall body,
Short body.
Petite body,
Skeleton body,
Starving body,
Very Skinny body,
Skinny body.
Slim body.
perfect body,
Normal body,
Athletic body.
Muscle body,
Curvy body,
Bodybuilder Body,
Plump Body,
Full Size Body,
Fat body,
Overweight body,
Hairy body,
Wet Body,
Sexy body,
NOTE 1 = Just by writing the words, "Sexy Body", the A.I. will often create many variations
on the above written words.
Note 2 = By writing " Wet Body" the A.I. will create the body skin as if it
looks wet, which is good for images of women or men inside water
or standing in the rain and looking wet.
Note 3 = By writing the words "Oily skin" or "Shiny skin", the AI will often create a
body with wet skin as if baby-oil was poured on it. Sometimes using the words "oily skin" but
the model is inside a car garage, the AI might also think you would want to see the skin covered
with black motor oil ! So, be careful on how you describe things tot he AI and where is the
location of the model you want her/him to be in.
........................................................................................
........................................................................................
FOR CLOTHING....
The Stable Diffusion 1.5 has already in its Data/program many styles of clothing.
You can have it create most types of clothing just by writing what you want
to see. If it is a particular (or special) type of clothing, then a pre-trained LORA model
may be needed to be used , so your AI will create it better.
Search on the internet for images which show types of FEMALE CLOTHING NAMES
and you can use those words in your prompts. In most cases, the AI will create them.
-
I have also discovered that if you include a famous dress designer name along
with the clothing types, your AI will also create a dress, or clothing, which that designer made .
This is the "Special trigger words"...
"... Wearing a Classic DRESS in the Style of _________put here name of designer________,"
in style of CHANEL
in style of Coco Chanel
in style of Thierry Mugler
in style of Balenciaga
in style of Jonathan Saunders
in style of Alexander McQueen
in style of Christian Dior
in style of Tom Ford
in style of Nicholas Kirkwood
in style of Alexandre Vauthier
in style of Balmain
in style of Dior
in style of Franck Sorbier
in style of Givenchy
in style of Jean Paul Gaultier
in style of Julien Fournie
in style of Maison Margiela
in style of Schiaparelli
in style of Stephane Rolland
in style of Yves Saint Laurent
in style of Paco Rabanne
in style of Pierre Cardin
in style of Dolce & Gabbana
in style of Valentino
in style of Karl Lagerfeld
in style of Marc Jacobs
in style of Versace
in style of Donatella Versace
in style of Gianni Versace
in style of Calvin Klein
in style of Ralph Lauren
in style of DIOR
in style of Christian Dior
in style of Stella McCartney
in style of Vivienne Westwood (punk designer)
in style of Giorgio Armani
in style of Tom Ford
in style of Donna Karan
in style of ZARA (street wear fashion)
in style of Gucci
in style of Prada
in style of Carolina Herrera
............................................................................
...........................................................................
Back in July 2023 PromptGeek also came up with
a similar discovery as I did, on how to write a better prompt
for the SD-1.5 for creating Photo-Realistic AI photos.
His style is similar to my style, but a little easier to write for begineers.
You may download his PDF-book for free here....
-- Creating Photorealistic Images With AI
https://civitai.com/models/118213/creating-photorealistic-images-with-ai-using-stable-diffusion
-
his YouTube video
https://www.youtube.com/watch?v=z-AoELaJfn0&t=1s
.
I hope this helps you
Cheers
MAX
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.