modelos/Style Squeeze [LoRA] - v2

Style Squeeze [LoRA] - v2

10/15/2025

10:01:32 AM

Palabras Clave y Etiquetas Relacionadas

clothing,color,composition,helper,lora,machinecode,sd 1.5,squeeze lora,stable diffusion model,style,style squeeze [lora],stylish,transform,v2

A mythical atlantean woman with silver hair and ornate aquatic armor floating gracefully in an oceanic underwater realm surrounded by coral reefs, fish, and luminescent sea life.

Side view portrait of a masculine silver-haired techno-warlock with glowing blue eye, dark mage clothes, sci-fi amulet and goggles, surrounded by floating skulls in a gothic eerie forest.

Parámetros Recomendados

samplers

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

steps

20 - 35

cfg

4 - 9

clip skip

resolution

512x768, 512x960, 512x640

other models

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

Parámetros Recomendados de Alta Resolución

upscaler

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

upscale

1.5

steps

10 - 20

denoising strength

0.4 - 0.6

Consejos

This lora helps primarily with color, composition, clothing and other things that make the image look 'cool'.

All sample images are generated with a weight of 1, but you can go a little overboard if you want.

It's not super good with generating text (or text-like shapes) at the moment.

Aspectos Destacados de la Versión

More images, balanced outputs

Patrocinadores del Creador

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.