AIBooru
Login Posts Comments Notes Artists Tags Pools Wiki Forum More »
Listing Upload Hot Changes Help

Search

  • Help
guro
scat

Artist

  • ? neuror1ston 113

Model

  • ? kenything (model) 84

Copyrights

  • ? project moon 33
  • ? ↳ limbus company 25

Character

  • ? faust (project moon) 6

General

  • ? 1girl 116k
  • ? bangs 54k
  • ? black jacket 2.7k
  • ? blue eyes 30k
  • ? blurry 9.5k
  • ? blush 64k
  • ? jacket 9.3k
  • ? looking at viewer 86k
  • ? medium hair 8.4k
  • ? open clothes 7.6k
  • ? open jacket 3.0k
  • ? outdoors 28k
  • ? parted lips 10k
  • ? sky 17k
  • ? solo 97k
  • ? sunset 1.5k
  • ? sweater 2.6k
  • ? turtleneck 1.7k
  • ? turtleneck sweater 671
  • ? upper body 16k
  • ? water 9.2k
  • ? white hair 12k

Meta

  • ? commentary 12k
  • ? english commentary 7.4k
  • ? lora 21k
  • ? non-web source 48k
  • ? resized 7.8k
  • ? ↳ upscaled 7.7k
  • ? self-upload 54k

Information

  • ID: 44930
  • Uploader: neuror1ston »
  • Date: almost 2 years ago
  • Approver: Lyren »
  • Size: 2.12 MB .png (1440x1024) »
  • Source: file://00055-kenything_v5,3689609447.png
  • Rating: General
  • Views: 340
  • Score: 9
  • Favorites: 5
  • Status: Active

Options

  • Resize to window
  • View smaller
  • View original
  • Find similar
  • Download

History

  • Tags
  • Pools
  • Notes
  • Moderation
  • Commentary
  • AI Metadata
This post has 0 children (learn more) « hide
post #44930
Resized to 59% of original (view original)
faust (project moon and 1 more) generated by neuror1ston using kenything_(model)
Original Commentary AI Metadata

Made with my experimental character LoRA. Trained on AnyLoRA model + NoiseOffset.
LoRA: https://civitai.com/models/150285/faust-lora-or-limbus-company
Going to make a lot of other characters from this game too. If there'll be enough images to make a decent dataset...

Prompt <lora:Faust-000001:0.85>, Faust, 1girl, solo, post-apocalypse, night, upper_body, looking_at_viewer, white_hair
Negative prompt (low quality, worst quality:1.4), (bad anatomy), (inaccurate limb:1.2), bad composition, inaccurate eyes, extra digit, fewer digits, (extra arms:1.2) EasyNegative EasyNegativeV2 negative_hand-neg ng_deepnegative_v1_75t bad-artist
Sampler DPM++ 2M Karras
Seed 3689609447
Steps 20
Cfg Scale 7
Model Hash de8e5ec077
  • Comments
  • neuror1ston
    almost 2 years ago
    [hidden]

    Image isn't that good for me to post it without approval, so you guys decide

    2 Reply
    • Copy ID
    • Copy Link
    Nur
    almost 2 years ago
    [hidden]

    It looks nice.

    1 Reply
    • Copy ID
    • Copy Link
    neuror1ston
    almost 2 years ago
    [hidden]

    For some reason training this lora on the model with noise offset mixed in just gives overall better results... More detailed BGs, lower amount of problems with hair and eyes, etc.
    Will do some other LoRAs to check this further.

    1 Reply
    • Copy ID
    • Copy Link
    Terms / Privacy / Contact /