SGFu | NoobAI Style

LORA
Reprint


Updated:

V1.1

New dataset, doing IL, tweaked training settings.

Recommended settings

Strength: 1.0

CFG: 3-8

Steps: 20-30

Sampler: dpm++ 2m sde

Scheduler: karras

Trained on/best with: Illustrious XL v0.1 or any Finetune or Merge (Wai, Hassaku, Nova,)

Positive:

aGFu, 1girl, solo, depth of field, blurry background,

Negative:

artist name, twitter tag, text

V1.0

Recommended settings

Strength: 1.0

CFG: 3-7

Steps: 20-30

Sampler: Euler

Scheduler: ddim

Trained on/best with: noobai NAIXL epsPred V110

Positive:

1girl, solo, SGFu, eye focus, painting \(medium\), simple background, anime screencap, no lineart, limited palette, ambient occlusion, depth of field

Negative:

artist name, simple coloring, text, signature, weibo username, watermark, watermarks, weibo logo, sample watermark, weibo username,

Version Detail

Illustrious
500
5

Project Permissions

Model reprinted from : https://civitai.com/models/1421713?modelVersionId=1606952

Reprinted models are for communication and learning purposes only, not for commercial use. Original authors can contact us to transfer the models through our Discord channel --- #claim-models.

Related Posts

Describe the image you want to generate, then press Enter to send.