TRUALITY ENGINE (PRO)
THE BRAND NEW PRO VERSION IS A MAJOR ENHANCMENT OF V3
More Contrast, More Sharpness, More Depth and More Warmth and all your older and more current prompts from Version 1-3 will still work in the PRO VERSION. DON'T USE VAE
PRO VERSION ADDED JANUARY 6TH 2024
click here if you want to support me and donate to our common cause
SAMPLE IMAGES
Everything you see is coming straight out of the engine, i am using no Loras to create effects, cameras or moods. I am using women and faces from this checkpoint and of course my very own Vicious Girls Series
HOW TO PROMPT?
Prompt as you wish, depending on what you are going for it doesn't need many words.
If you want to create a particular scene with particular assets, put those in brackets or double brackets. If that doesn't do the job use the weighting method (+/-) from 0.5 to 1.5
The higher the weight, the lower the quality.
SETTINGS
Steps: 35
with this model, too high means it takes longer to load, test it for each scene individually, keep it at 35 if you don't mind waiting a few seconds longer.
CFG: 3.5 to 11.5
The higher the value the higher the contrast and the amount of colors. The engine will listen more subtly to your prompt up till CFG 7. Everything above could be described as over-exaggerating your prompt to adding new features. A Lens Flare can become something entirely else. Definitely interesting if you feel like experimenting.
When using TI's and Lora's you should not go higher as 4.5
Best Size 512 x 768
Best Samplers: DPM++ 2M SDE KARRAS
HIRES FIX
Upscale a 512x 768 by 2x
UPSCALER for V3 4x UltraSharp
Clean and less grainy results, yet very detailed
(Resize Steps 15 to 25, Denoise 0.23-0.33)
UPSCALER for V1 & V2 & Pro: 4x_NMKD-Superscale-SP178000_G.pth
(Resize Steps 10 to 15, Denoise 0.17-0.33)
This upscaler provides a special layer of depth for photo realistic images, slightly grainy.
LORAS
Most Loras will distort your results, you have to weigh them in, 0.7 seems to work best by default, each Lora is different and behaves differently. Many... if not the most will mess with your models face because they were trained with a different face, sometimes you can fix it with clip skip and if that doesn't work just use roop or face swap and write your girls face over the trained face. Most Loras are designed for 512x512, when bodies or objects get strethed or appear twice then lower the output size.
WEIRD FACES
Especially from side angles and long distances you will keep running into weird faces, Hires Fix will 9/10 times fix this.
Please share your favorite results, consider rating this model if you like it.
Get your own custom and exclusive Influencer---> contact me in chat
or see my Fiver Page
DISCLAIMER: All Models released under the Vicious Family 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 fotos to create a resemblance on porpuse. All my models are either entirely created by prompts and trained on the results or mixed with body parts, facial features of 2 female friends who have consented in writing for their images being used in my process. If anyone feels that one of my models resembles a celebrity, actress or influencer and feels concerned about it, please leave a comment, I will take it to the person, management or representative directly.
Description
THE TRUALITY ENGINE V2 - (VAE PRUNED)
(October 28th)
This model was re-designed / merged with a lot of attention to detail and versatile results.
If you had good results before, your results will be great now. Better saturation, more depths and greater sharpness when needed. It also work a lot better with most Loras. Embeddings should be used with CFG Scale 3.5 to 4.5
The least of us have tons of SDD-Space on our rigs and having 20 different models to achieve different results to realize your vision is not making things better and is also very time consuming.
My goal was to cherry pick models that deliver absolutely stunning and realistic photographs but also satisfy the 2.5 and fantasy lovers. It's also very "potent" with NSFW content. People who are creating series of images, i.E. Influencer Content, will find that this merge has a very high consistency. Hands and fingers are quite decent but not perfect.
HOW TO PROMPT?
I tried to use models where you have the ultimate freedom, if you are are used to slider from 0.5 to 1.5 you will do fine. If you are more the descriptive kind of person the model won't fight you. I have added a lot of examples with demos, no Loras been used, i used a few 2 TI's for influencer faces. Not to fool anyone but to show how well they work with this model.
SETTINGS
Steps: 25 to 35
CFG: 3.5 to 7 depending on how much saturation, freckles etc. you want. Wenn using TI's never go above 4
Best Size 512 x 768 or 768 x 1024 if you have a 3090 or higher
Best Samplers: DPM++ 2M SDE HEUN KARRAS or DPM++ 2M SDE KARRAS
HIRES FIX
UPSCALER: 4x_NMKD-Superscale-SP178000_G.pth
(Resize Steps 7 to 15, Denoise 0.17-0.33)
This upscaler provides a special layer of depth for photo realistic images.
REFINER
If you like the content of your favorite model more but would like to add some of the sharpness and lighting features to your output, add this model as refiner or upscale model. When using as refiner put at 0.85
VAE Pruned
LORAS
Most Loras will distort your results, you have to weigh them in, 0.25 to 0.65 seems to work best. Many... if not the most will mess with your models face because they were trained with a different face, sometimes you can fix it with clip skip and if that doesn't work just use roop or face swap and write your girls face over the trained face. Most Loras are designed for 512x512, when bodies or objects get strethed or appear twice then lower the output size.
WEIRD FACES
Especially from side angles and long distances you will keep running into weird faces, Hires Fix will 9/10 times fix this, if that still doesn't work use roop or face swap in your chain.
Please share your favorite results