Sign In

design perfect eyes

12

Download

1 variant available

fp16 SafeTensor

design perfect eyes.safetensors

Half precision, best balance • 51.84 MB

Verified:

Type
LoRA
Stats

294

12

4

Reviews
Published

Oct 5, 2025

Base Model

SD 1.5

Training
Steps: 16,000
Epochs: 2
Usage Tips
Clip Skip: 2
Hash
AutoV2
73D46CCC94
Trigger Words
1girl, blonde hair, blue eyes, blurry, bob cut, breasts, brown eyes, brown hair, close-up, collarbone, eyelashes, jewelry, lips, long hair, looking at viewer, makeup, mdlnpefeys, mole under mouth, multicolored hair, nipples, realistic, sleeveless dress, solo, upper body
default creator card background decoration
Reactions - 117924

117.9K

Followers - 3289

3.3K

Likes - 15507

15.5K

Snowflake Badge
00004-3034834267.jpg

Lora model trained with 2040 high quality photos, generates images of perfect eyes, made-up faces, done eyebrows, iris tone with 5 different color types

The vae is already included in the model, or use the one of your preference

To activate the model you need to insert the token "mdlnpefeys " and the class "1girl"

recommended strength:

mdlnpefeys <lora:design perfect eyes:0.9>

mdlnpefeys <lora:design perfect eyes:0.8>

mdlnpefeys <lora:design perfect eyes:0.7>

mdlnpefeys <lora:design perfect eyes: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 512 x 768, 768 x 512, 540 x 960, 640 x 960, 960x640 and 1024 x1024

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: 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:

(CyberRealistic_Negative-neg), cartoon, painting, illustration, (grayscale:1.4), (worst quality:2), (low quality:2), (normal quality:2), ugly, fat, 3D rendering, asian, chinese, japansese, bad hands, malformed hand, amorphous hand, multiplied fingers, red skin, long neck