Sign In

bodyslider sdxl

88

Download

1 variant available

SafeTensor

217.88 MB

Verified:

Type

LoRA

Stats

680

88

56

Reviews

Published

Dec 18, 2025

Base Model

SDXL 1.0

Hash

AutoV2
5CAB974A99

Trigger Words

black hair, nature, underwear, sideboob, plant, heterochromia, sunlight, hands on own thighs, freckles, bokeh, breasts apart, upper body, highleg, torn pants, short sleeves, earrings, shorts, sand, bare shoulders, brown eyes, own hands together
out-of-frame censoring, bracelet, lamp, dark-skinned female, nail polish, thick eyebrows, gradient background, mascara, purple bra, mole on breast, crop top, earrings, black dress, eyelashes, nude, closed mouth, uncensored, sitting, orange hair, pink bra, lace
traditional media, sleeveless dress, side-tie panties, veil, torn pants, lipstick, jewelry, letterboxed, underwear, lingerie, completely nude, smile, nudist, sand, high-waist pants, curvy, heterochromia, own hands together, out-of-frame censoring, white shirt, lace-trimmed dress

Introducing the Lora model trained with 1000 photos at 640x960 resolution, it has body sliders, and in addition to drastically increasing breast size, it has two added features: perfect eyelashes and 10 detailed iris colors.

To activate the model you need to insert the token "dxdbdsld" and the class "girl"

recommended strength:

dxdbdsld<lora:bodyslider sdxl:0.10>

dxdbdsld<lora:bodyslider sdxl:0.9>

dxdbdsld<lora:bodyslider sdxl:0.8>

dxdbdsld<lora:bodyslider sdxl:0.7>
dxdbdsld<lora:bodyslider sdxl:0.6>

I recommend using the Adetailer extension.

Use this extension to fix hand errors:

https://github.com/licyk/advanced_euler_sampler_extension

It is strictly prohibited to distribute, inside and outside civit ai, this template or post it anywhere or on hosting services, on third party image generation services, you can use it for personal use, if you know who distributed it without my consent , report it immediately.

Resolution settings:

Standard resolutions 512x640, 600x800, 640x690

Resolution: 540x540 select the Hires.fix checkbox, result 1080 x 1080 pixels

Note: I am testing the sampling methods and I will add the others to the settings.

Use these recommended settings for generation:

Sampling method: Euler Max

Sampling steps: 30-50

CFG Scale: 2.0 - 7.0

Skip clip: 1-2

Sampling method: Euler a

Sampling steps: 30-50

CFG Scale: 2.0 - 7.0

Skip clip: 1-2

Sampling method: Restart

Sampling steps: 30-50

CFG Scale: 2.0 - 7.0

Skip clip: 1-2

Sampling method: Kohaku_LoNyu_Yog

Sampling steps: 30-50

CFG Scale: 2.0 - 7.0

Skip clip: 1-2

Sampling method: Euler_Max

Sampling steps: 30-50

CFG Scale: 2.0 - 7.0

Skip clip: 1-2

Sampling method: Euler_Smea_Dy

Sampling steps: 18-50

CFG Scale: 2.0 - 7.0

Skip clip: 1-2

Sampling method: Euler a

Sampling steps: 18-50

CFG Scale: 2.0 - 7.0

Skip clip: 1-2

Sampling method: LCM

Sampling steps: 18-30

CFG Scale: 2.0 - 7.0

Skip clip: 1-2

Sampling method: DDPM Karras

Sampling steps: 18-30

CFG Scale: 2.0 - 7.0

Skip clip: 1-2

Sampling method: DPM++ 2M

Sampling steps: 18-30

CFG Scale: 2.0 - 7.0

Skip clip: 1-2

Sampling method: DPM++ SDE Karras

Sampling steps: 18-30

CFG Scale: 2.0 - 7.0

Skip clip: 1-2

Sampling method: DPM++ 2M SDE Karras

Sampling steps: 18-30

CFG Scale: 2.0 - 7.0

Skip clip: 1-2

Use the recommended negative prompt:

Stable_Yogis_PDXL_Negatives-neg,monochrome, bad fingers, malformed hands, malformed arm, multiplied arm