models/FLUX-style Lora for SDXL - v0.2

FLUX-style Lora for SDXL - v0.2

|
10/16/2025
|
11:26:48 PM
| Discussion|
0
A detailed aerial view of an old ruined castle watch tower standing on a rocky hill, with vibrant dramatic clouds and dynamic lighting casting long shadows.
Anthropomorphic hybrid reptile with detailed scales and skin, wearing a dark cloak, standing in a snowy forest under soft falling snow, with a somber and mysterious expression.
A photorealistic winter landscape at night showing a dark purple sky with a full moon, a mountain castle perched atop a snowy cliff, a stream reflecting moonlight, and a lit cabin surrounded by snow-covered pine trees.
A vibrant yellow classic car speeding on a wet urban street with a large explosion in the background under a cloudy sky.
Anthropomorphic orange tabby cat dressed in Princecore costume holding an ornate sword, standing in an autumn forest with falling leaves and pumpkins around.
Front view of a vintage Ford T car with headlights on, engulfed in dramatic flames, featuring deep contrasts and warm cinematic lighting.
Photorealistic image of a human skull on forest ground at low angle with a golden strip in front displaying the words 'This place is death.'
Majestic wolf sitting under a glowing full moon with detailed silvery fur illuminated by soft moonlight against a dark night sky with faint stars.
A floating, triangular rock formation with glowing magical light radiating from the center, two silhouetted figures on its surface, misty water below, and a mystical fantasy environment.
Highly detailed beautiful landscape of a deserted planet, featuring dome-like houses and a giant planet in the sky, in George Lucas art style.
Shadow person holding a black luminous pumpkin balloon in a spooky Halloween fantasy setting with mist and detailed architecture.
A tilt-shift image featuring a surreal oasis landscape with a tiny temple inside a cup, alongside a miniature genie spirit, and lush vegetation.

Recommended Prompts

flux-style

Recommended Negative Prompts

low quality, deformed, boring

Recommended Parameters

samplers

DDPM

steps

14 - 18

cfg

1.2 - 2

clip skip

2

resolution

720x1280

vae

sdxl_vae.safetensors

other models

aidmaFluxStyleXL-v0.2 (6c2a2b2c3859), aidmaBokehmachine-V0.1 (7a79c5da33d1), aidma-Image Upgrader-v0.1 (e4be4bfcf4dc), ForRealXL-V0.5 (6f228e128a), aidmaGlitchStyle-v0.1 (d32a5d50652b), ForArtisticXL-v0.1 (34cd71e533), CBS_novuschroma37 style_b (6e1eab82e245)

Recommended Hires (High-Resolution) Parameters

upscaler

4x_NMKD-Siax_200k, SwinIR_4x

upscale

1.5

steps

14

denoising strength

0.16

Tips

Start with setting value 0.5 for best results.

Try using the 'flux-style' trigger; note that V0.1 uses a different trigger.

Try with and without the trigger to see varied results.

Version Highlights

  • trained with 100 images

  • fixed the Trigger 🫠

  • fixed a bug with the lora name

  • fixed a training image duplicate

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❤️

Made around 5-6k Images with Flux the last 3 days and made this Lora with 50 (100 with v0.2) of my favorite images.

Will train way more in the next versions.

FLUX is way better than this lora (with text), but sometimes you get a cool result with good text.

Settings

0.5 - 1.0

start with 0.5

try with and without Trigger

Trigger

flux-style

careful, if you use V0.1 there is an other trigger to activate

Hope you get a lot of beautiful results

Previous
DucHaiten-Pony-XL (no-score) - Pony-no_score_v5.0
Next
JDM Legends - Mazda RX-7

Model Details

Model type

LORA

Base model

SDXL 1.0

Model version

v0.2

Model hash

e691239869

Trained words

flux-style

Discussion

Please log in to leave a comment.

Model Collection - FLUX-style Lora for SDXL

Images by FLUX-style Lora for SDXL - v0.2

artful Images

experimental Images

style Images