Recommended Negative Prompts

blurry, deformed, low quality, boring

Recommended Parameters

samplers

DDPM, Euler, DPM++ 3M SDE

steps

10 - 17

cfg

1 - 4

clip skip

2

resolution

720x1280

vae

sdxl_vae, sdxl_vae.safetensors

other models

aidmaFluxStyleXL-v0.2 (6c2a2b2c3859), aidma-Image Upgrader-v0.1 (e4be4bfcf4dc), aidmaPsychadelicChaosWorldMorphXL-V0.1 (34060ea154a9)

Recommended Hires (High-Resolution) Parameters

upscaler

SwinIR_4x

upscale

1.5 - 4

steps

14 - 15

denoising strength

0.16

Tips

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

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

Please experiment with Lora weights to enhance model performance.

Version Highlights

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

Creator Sponsors

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

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
Nova Anime XL - IL v8.0
Next
Ath_水墨风ink-style - xl-a31

Model Details

Model type

Checkpoint

Base model

SDXL Lightning

Model version

v1.0

Model hash

ff0240ddf7

Discussion

Please log in to leave a comment.