Emiru by 𝓝𝓞𝓑𝓞𝓓𝓨

This LoRA was trained with 100 images of the Twitch Streamer Emiru, each sized 768x768.

The preview images were generated using the model epiCRealism - pure Evolution V5 for SD1.5, JuggernautXL for SDXL, Everclear for PONY

Settings used in the preview images:

• LoRA Weight: (Operates from 0.6 to 1.0) - Recommended: (0.8 to 1)

• Default Resolution: 768x768

• Recommended Resolution: Depending on what you want (NOTE BELOW)

• Sampler: DPM++ 3M SDE Exponential

• Steps: 20

• Cfg Scale: 2 (Depending on your model)

• Keyword: emirulol,

Note:

This model works well at most resolutions, so you won't have many problems. However, in case you get distorted or warped faces, simply try in other resolution. In the preview images, you'll notice that lower resolutions are used for close-up faces, while higher resolutions are used for full-body shots. So, always try to play around the resolution and give a try to this LoRA.

XL UPDATE:

• LoRA Weight: (Operates from 0.8 to 1) - Recommended: (0.8 to 1)

• Default Resolution: 768x768

• Recommended Resolution: (Depending on model). For more image quality use an Upscaler.

• Sampler: DPM++ 3M SDE Exponential

• Steps: 20-50

• Cfg Scale: 2 (Depending on your model)

• Keyword: emirulolxl

PONY UPDATE

KEYWORD: emirulolxl,

It's useful to add: black hair, bangs, eyelashes, To the keyword.

Recomendations:

• Try it from 0.8 to 1.

• I recommend to use face restoration in some cases.

Find my other LoRAs HERE !