A dwarf warrior standing in a dark subterranean cave holding a glowing hammer surrounded by fiery crystals and rocky terrain.
A hyper-realistic astronaut time traveler walking forward with a large glowing icy clock behind, Roman numerals visible, surrounded by translucent blue ice and mist.
Highly detailed macro photo of a colorful seashell with fine patterns and textures on a beach, featuring a vibrant blue and orange spiral design.
A highly detailed and realistic turtle wearing a jetpack flying above a colorful canal cityscape with buildings and flowers.
A detailed candle with a calm flame burning in a dark room, placed on a wet surface reflecting warm light.
A highly detailed octopus acting as a DJ at an underwater rave, surrounded by glowing jellyfish lights and vibrant aquatic colors, with DJ equipment in front.
Mystical silhouette figure stands at the edge of a glowing turquoise river inside an ethereal jungle cave, surrounded by lush flora and illuminated by an otherworldly turquoise moon.
Anthropomorphic hybrid reptile standing in a snowy forest, wearing a dark cloak with a light layer of snow on scales and clothing, amidst falling snowflakes.
A photorealistic winter landscape at night featuring snowy mountains, a glowing purple moon, a cabin by the river, and a majestic house atop a steep cliff.
A vibrant yellow classic Mustang car driving down a wet urban street with a large fiery explosion behind it, surrounded by detailed buildings under a cloudy sky.
Anthropomorphic orange tabby cat dressed in ornate medieval attire holding a large detailed sword in an autumn forest surrounded by pumpkins and falling leaves.
A luminous lighthouse on a rocky island at night, surrounded by glowing windows, dynamic cloud formations, a full moon, and shimmering ocean waves.

Empfohlene Negative Prompts

boring, blurry

Empfohlene Parameter

samplers

DDPM, Euler, DPM++ 3M SDE

steps

12 - 19

cfg

1 - 4

clip skip

2

resolution

800x1200, 540x960, 720x1280, 832x1216

vae

sdxl_vae, sdxl_vae.safetensors

other models

aidmaFluxStyleXL-v0.2 (6c2a2b2c3859), aidma-Image Upgrader-v0.1 (e4be4bfcf4dc), CBS_novuschroma37 style_b (6e1eab82e245), aidma RealisticTank (8d2d92c9f2a0), DoubleExposure-000002 (131be0f83471), MTG-CardsXL (032c238d9192), aidmaDoubleExposure-v0.1 (22eeda5c5e1f), sss (079dc17041d4), WildcardX-XL-Detail-Enhancer (69e8c9938bf7), xl_more_art-full_v1 (fe3b4816be83), Ice (2438650d6785), add-detail-xl (9c783c8ce46c), ral-sld (112a50eace66), MJ52 (000c96b6bd08), zavy-flrscnc-sdxl (19c595006ad0)

Empfohlene Hires (Hochauflösungs-) Parameter

upscaler

SwinIR 4x, 4x-UltraSharp, SwinIR_4x

upscale

1.5 - 4

steps

14 - 15

denoising strength

0.16 - 0.28

Tipps

For people and faces, avoid using DDPM sampler; prefer DPM++ 3M SDE or Euler samplers.

Lower CFG scale (1-1.8) produces more realistic results.

Experiment with Lora weights as they significantly impact this model.

Versions-Highlights

v0.5

Small improvements

- better skin, teeth and eyes in humans

- more details

I am still working on the following improvements

- deformed faces / displaced eyes

- faces from a distance

- xxx

Ersteller-Sponsoren

for whatever reason you want to show me appreciation, you can: ❤️Ko-Fi❤️

Special Thanks to

badassdragoon2 georgebanjog Mr_fries1111 barytdruck124

Please take a look at their amazing work!

Hello ♥

for whatever reason you want to show me appreciation, you can: ❤️Ko-Fi❤️

Special Thanks to

badassdragoon2 georgebanjog Mr_fries1111 barytdruck124

Please take a look at their amazing work!

Update v1.0:

if you see when V0.5 was released, you can imagine how hard it was for me to create a better version that is really better in all areas.

This is the result of probably 100 different versions.

  • more Details

  • better colors at low cfg

  • better faces (and more variance) (not perfect)
    For people and faces, you should not use DDPM. Use DPM++ 3M SDE or Euler

Update v0.5:

Small improvements

- better skin, teeth and eyes in humans

- more details

I am still working on the following improvements

- deformed faces / displaced eyes

- faces from a distance

- xxx

Update v0.3:

It's just a small update to fix some issues from v0.1.

It doesn't change every subject, but some improve.

I haven't had a picture in about 1000 pictures where v0.3 wasn't better, so the upgrade is definitely worth it.

I can notice the following improvements:

  • a bit sharper

  • more realistic

  • a bit more creative

  • a bit more possibilities to get nicer hands/faces on full body photos

________________________________________________________________________________

This is a merge of the following Models:

Boltning

JuggernautXL

WILDCARD Lightning

Recommended Settings:

Sampling Method: DDPM (my absolute favorite), Euler, DPM ++ 3M SDE

Sampling Steps: 10 (more very rarely make a difference.)

CFG Scale: 1-4 (lower, more realistic, i prefer 1-1.8)

Upscaler: SwinIR _4x (this is my all time favorite)

(Hires steps: 15; Denoise: 0.28, upscale by 1.5 - 4 (depends on your GPU))

📌 USE sdxl_vae

All Images generated in SD Forge with Nvidia RTX 4090

Please test other Settings and share with the communty, so i will learn about the Settings and can optimize.

Recommended Loras:

Please experiment with the weights. Loras are really gamechanging in this Model!

TESTS

Here you can find and download my tests:


Thank you so much for using this Model. Hope you are get insane results and create some BANGERZ ♥

Zurück
Chris Luka - V1
Weiter
Cryosibilum Style | Illustrious - MCHTv1.0

Modell-Details

Modelltyp

Checkpoint

Basismodell

SDXL Lightning

Modellversion

v0.5

Modell-Hash

6f228e128a

Diskussion

Bitte log in um einen Kommentar zu hinterlassen.