Sign In

Neo Universe (umamusume)

253
3k
13
Verified:
SafeTensor
Type
LyCORIS
Stats
2,951
Reviews
Published
May 12, 2023
Base Model
SD 1.5
Training
Steps: 3,100
Epochs: 10
Trigger Words
neo universe \(umamusume\)
Training Images
Download
Hash
AutoV2
B773D523A9
default creator card background decoration
Donator Badge
mht's Avatar
mht

LoHa of Neo Universe (umamusume). Put LoHa file in your stable-diffusion-webui/models/lora folder and write LoRA notation in prompt to applying LoHa. <lora:your_loha_name:weight>

All of my works is free. If you'd like to support me, feel free to buy me a coffee. 👍

NOTICE

  • After careful consideration, I decided not to produce LoRA of the characters below.

  • If anyone wants the characters above, I will consider making them.

  • Except for the above, I will make the rest of the characters in umamusume unless there is a special notice.

Recommended options

  • LoRA weight around 0.7

  • Trigger words

    • Base

      • neo universe \(umamusume\)

    • Racing competition costume :

      • single ear cover, puffy long sleeves, sleeves past fingers, sleeves past wrists, oversized clothes, cleavage cutout, clothing cutout, crop top, open jacket, open clothes, white jacket, yellow jacket, two-tone jacket, white leotard, boots, white footwear

    • Casual :

      • casual, collared dress, white dress, puffy long sleeves, white shirt, white skirt, black footwear, sneakers

Use a model derived from or mixed with animefull model.

  • Settings

    • Stable Diffusion WebUI by Automatic1111

    • DPM++ Series(SDE Karras, 2M Karras, etc.)

    • about 20 steps, CFG scale 3.5~6.5

    • I recommend kl-f8-anime2.vae

    • CLIP skip = 1

    • Use Hires.fix to get higher quality image

      • Upscaler

        • Latent, Latent (nearest-exact), Latent (bicubic antialiased) or other Latent series.

      • Denoising strength 0.50~0.65

LoRA training info

  • trained on sd-scripts by kohya_ss.

  • based on Animefull-pruned model

  • 140 images consist of

    • 4x low quality 60 images

    • 8x medium quality 35 images

    • 16x high quality 45 images

    • => 1 epoch = 1240 images

  • replaced character feature tags with neo universe \(umamusume\)

    • 1girl, yellow eyes, gradient hair, tail, fox tail, two-tone hair, blonde hair, streaked hair, long hair, simple background, very long hair, aqua hair, horse girl, virtual youtuber, animal ears, horse ears, hair between eyes, ahoge, multicolored hair, purple eyes, green hair, blue hair, aqua eyes, parted bangs, crossed bangs, brown hair, grey hair, colored inner hair, blue eyes, horse tail, bangs, grey eyes, solo

    • I think these tags are the essentials of Neo Universe or

    • unnecessary for training because of duplication.

  • resolution : 768x768 with aspect ratio bucketing.

  • other training settings is included in training data or metadata of LoRA file.

All uploaded images are generated by AOM3A1

And, special thanks to my best friend. DH.