models/HL's Styles - WAI | ILLUSTRIOUS - KLSKX - Depth and Blurry

HL's Styles - WAI | ILLUSTRIOUS - KLSKX - Depth and Blurry

|
10/18/2025
|
11:34:12 PM
| Discussion|
0
Close-up portrait of a dark elf with glowing yellow eyes using icekinesis, with snow and fantasy cityscape in the background.

Recommended Prompts

1girl, masterpiece, best quality, amazing quality

Recommended Negative Prompts

worst quality

Recommended Parameters

samplers

dpmpp_sde_karras, Euler a

steps

28 - 40

cfg

4 - 7

clip skip

2

resolution

768x1280, 960x1280, 832x1216, 512x512, 896x1152, 1024x2048

other models

klskx_wai (6d07ba56761c), takeda_hiromitsu_style_illustrious_goofy (6b14ad1aec67), waiNSFWIllustrious_v90 (178fc987b2), NOOB_EPSv1_1_detailer_by_vlnvk_v0_5 (2fdc73373296), ~~nill5B (d40bcbb8ad), NOOB_EPSv1_1_detailer_by_vlnvk_v1_0 (3d45d9ee77cb), spo_sdxl_10ep_4k-data_lora_webui (5e19ac2efbc8), ~WIN (7abd2a1860), rouwei_v07Epsilon (fba49f1a4f), ponyv6_noobE11_2_adamW (c8237b8ce9a9), cfg_scale_boost (c071fe08ab71), Sinfully_Stylish_1.0_for_Illustrious (749fae9cdbbb), YTSKX-WAI (ebb0dac7aae8), Aurastronger_SDXL (e3fbebf35c97), add-detail-xl (9c783c8ce46c), 绪儿 厚涂构图光影质感增强V3 (1e731b0e6bb0), waiNSFWIllustrious_v110 (c3688ee04c)

Recommended Hires (High-Resolution) Parameters

upscaler

4x_NMKD-YandereNeoXL_200k, Latent (nearest-exact), R-ESRGAN 4x+ Anime6B

upscale

1.3 - 2

steps

20 - 25

denoising strength

0.4 - 0.65

Tips

All information about each LoRA can be found in the “About this version” section.

Acknowledgement to @wwHEY for advice, although not responsible for the quality of LoRAs.

Version Highlights

Illustrious/WAI version. It is more like the artist style. Much more stable but less aesthetically pleasing and flexible than NoobAI-XL version.

Some information and tips from my experience.

  • Trained on the WAI-NSFW-illustrious-SDXL v8. But it seems to work fine on the v9 version as well.

  • Trained on artworks (edited in photoshop by me with some effects) of Kan Liu (666k).

  • The weight is around 0.7-0.8, but you can play with the values. Didn't experiment much yet.

  • Use a klskx tag.

  • Use ‘blurry background’, ‘depth of field’, ‘bokeh’ tags for blurred background.

  • Use tags ‘dynamic pose’, ‘dutch angle’ - for dynamics of the image.

  • Add ‘outdoors’ and ‘indoors’ tags depending on the scene. Optional.

  • Tags for lighting help aesthetics: 'backlighting', 'sidelighting', 'underlighting', 'sunrays', 'sunlight', 'dappled sunlight' etc.

  • Sometimes ‘hydrokinesis’ and ‘water’ appear. Just add them to the negative prompt. Or in the positive if you want to see it in the picture.

  • Artist tags seem to work pretty well and fit with this LoRA. Give it a try.

Still in the process of checking out this model

!!! LoRA can be difficult to use !!!

This is the WAI/ILLUSTRIOUS version of these loras.

All information about each lora can be found in the “About this version” section.

Many thanks to @wwHEY — I couldn’t have done it without her advice!

But she's not responsible for the crappy quality of my LoRAs. x)

Previous
PHOTOSTYLE BY SEAN ARCHER ( NSFW ) - v1.0
Next
Realistic Skin Texture style XL (Detailed Skin) + SD1.5 + Flux1D + Pony + Illu - Skin Texture Flux1D v1.0

Model Details

Model type

LORA

Base model

Illustrious

Model version

KLSKX - Depth and Blurry

Model hash

a50376f7d2

Trained words

klskx

Discussion

Please log in to leave a comment.