TRUALITY ENGINE PRO LCM

CHECKPOINT
Reprint


Updated:

1.1K

*These Models are not mine, I'm just sharing:

CREDITS to Tower13Studios (https://civitai.com/user/Tower13Studios)

CREDITS to slashkey (https://civitai.com/user/slashkey) for the LCM merge

----------

Creator'sNotes:

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

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: 8 with this model, too high means it takes longer to load, test it for each scene individually, keep it at 8 if you don't mind waiting a few seconds longer.

CFG: up to 2 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 2 since it has LCM. 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.

Best Size 512 x 768

Best Samplers: LCM

HIRES FIX

Upscale a 512x 768 by 2x UPSCALER for PRO 4x_NMKD-Superscale-SP178000_G.pth Clean and less grainy results, yet very detailed (Resize Steps 15 to 25, Denoise 0.23-0.33)

(Resize Steps 4 to 5, 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.

Version Detail

SD 1.5
This is an LCM version of the TRUALITY ENGINE (PRO) model by CivitAI user Tower13studios. Thank or tip that user, not me. https://civitai.com/models/158621/the-truality-engine https://civitai.com/user/Tower13Studios https://civitai.com/user/slashkey (for this LCM merge) It works quite well for AnimateDiff, cutting down generation times by quite a lot whilst still having decent quality. 8-10 steps works well for both regular image generation and AnimateDiff. For inpainting (including Adetailer) and hires fix it seems best to reduce the steps to 4. And just like all LCM models you have to keep the CFG scale low (1-2). I'd like to find out how to reduce the blur, or other strange quality issues, which seems to be a problem with non-LCM models too. I saw the non-LCM model of this recommended in an AnimateDiff guide, so that's why I chose it to make an LCM with.

Project Permissions

Model reprinted from : https://civitai.com/models/411486/truality-engine-pro-lcm-sd-15-model

Reprinted models are for communication and learning purposes only, not for commercial use. Original authors can contact us to transfer the models through our Discord channel --- #claim-models.

Related Posts

Describe the image you want to generate, then press Enter to send.