A grand palace dining room featuring a long table set with celestial-themed dinner plates with gold accents, crystal glassware, and an elegant floral centerpiece beneath ornate chandeliers and an intricately designed ceiling depicting a starry night sky.
Sepia-toned vintage photo of a woman in aviator goggles and pilot outfit standing in front of an old airplane.
A highly detailed metal beer tankard designed in a Giger-inspired biomechanical style, shaped like a skull and crafted with smoky quartz elements, filled with frothy beer.
A hyper-realistic cyborg mermaid with metallic scales and glowing bioluminescent accents, set against a detailed underwater metropolis backdrop filled with aquatic life and advanced technology.
A hyper-realistic humanoid jellyfish with translucent skin and glowing tendrils floating inside a crowded subway car during rush hour, surrounded by commuters.

Recommended Negative Prompts

(bandhands, bad hands:1.2), (naked boobs:1.3), iphone, smartphone, (nsfw, nude, naked, nipple:1.4), low detailed, deformed iris, deformed pupils, jpeg artifacts, ugly, duplicate, morbid, mutilated, too many fingers, mutated hands, poorly drawn hands, mutation, deformed, bad anatomy, bad proportions, extra limbs, cloned face, malformed limbs, extra arms, text, extra legs, fused fingers, logo, signature, watermark, autograph, trademark, cut off, censored, inaccurate body, inaccurate face, bad teeth, deformities, (boring, uninteresting:1.1)

Recommended Parameters

samplers

DDPM, Euler, DPM++ 3M SDE

steps

10 - 15

cfg

1 - 4

clip skip

2

resolution

850x1280, 520x960

vae

sdxl_vae, sdxl_vae.safetensors

other models

ral-drp (33d3d95bec73), casting shadow style v2 (8f86f8482514), add-detail-xl (9c783c8ce46c), WildcardX-XL-Detail-Enhancer (69e8c9938bf7), xl_more_art-full_v1 (fe3b4816be83), ral-ertmsphr (0d7803cec887), ral-apoctvisn-sdxl (04f9cdbb3aa2), InkArtXL_1.2 (0ac1b33af01a)

Recommended Hires (High-Resolution) Parameters

upscaler

SwinIR 4x, SwinIR_4x

upscale

1.5 - 4

steps

10 - 17

denoising strength

0.28 - 0.29

Tips

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

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

Experiment with Lora weights as they can be game-changing for this model.

Test and share your settings with the community to optimize performance.

Version Highlights

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

Creator Sponsors

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

Special Thanks to badassdragoon2 georgebanjog Mr_fries1111 barytdruck124

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 ♥

Previous
RealVisXL V5.0 - V5.0 (BakedVAE)
Next
NightDust - V1

Model Details

Model type

Checkpoint

Base model

SDXL Lightning

Model version

v0.3

Model hash

bb92aba905

Discussion

Please log in to leave a comment.