models/Style Squeeze [LoRA] - v2

Style Squeeze [LoRA] - v2

|
8/5/2025
|
9:26:37 AM
| Discussion|
0
A mythical Atlantean woman with silver hair and intricate aquatic armor floats gracefully underwater surrounded by coral reefs, luminescent marine life, and mystical oceanic depths.
Side view portrait of a techno-warlock with silver hair, grey-blue eyes, wearing dark tattered mage clothes and sci-fi goggles in a gothic eerie background.
Portrait of a wise old man with white hair and icy armor looking thoughtfully at a floating futuristic city with tall towers and glowing blue lights under a cloudy sky.

Recommended Parameters

samplers

Euler a, DPM++ 2M SDE Karras, DPM++ 2M Karras

steps

20 - 35

cfg

4 - 9

clip skip

2

resolution

512x640, 512x768, 512x960

other models

darksun_v40 (48a4cb67d2), toonyouJP_alpha1 (022bfe5fa2), MCBS_v2 (faebcebd4c), icbinpICantBelieveIts_afterburn (65cd001daf), aniflatmixAnimeFlatColorStyle_v20 (b0d25db787), babes_20 (65cf944caa)

Recommended Hires (High-Resolution) Parameters

upscaler

R-ESRGAN General 4xV3, R-ESRGAN 4x+

upscale

1.5

steps

10 - 20

denoising strength

0.4 - 0.6

Tips

Use a weight of 1 for the best effect, but can go higher if desired.

Currently not good at generating text or text-like shapes.

Check out other models by the same author for varied styles.

Version Highlights

More images, balanced outputs

Creator Sponsors

NOTE: The SDXL version has been moved into its own listing. Click Here

NOTE: The SDXL version has been moved into its own listing. Click Here

UPDATE:

v3: Larger dataset, better training

v2: More varied dataset used for training

Squeeze every OUNCE of style and coolness from your prompts!

This lora helps primarily with color, composition, clothing and other things that make the image look 'cool'. All the sample images are generated with a weight of 1, but you can go a little overboard if you want.

NOTE: It's not super good with generating text (or text-like shapes) at the moment, something I hope to correct in the future.

Examples

Testing and sample images generated using the following models:

If you like this, check out my other models!

Contributor

Previous
WOW! Flux (Detail and Aesthetics) - v1.0
Next
Touching Grass - IL/NAI - illus01 v0.2

Model Details

Model type

LORA

Base model

SD 1.5

Model version

v2

Model hash

15f222f2f2

Discussion

Please log in to leave a comment.

Model Collection - Style Squeeze [LoRA]

Images by Style Squeeze [LoRA] - v2

style Images

stylish Images

transform Images