Type | |
Stats | 3,308 |
Reviews | (326) |
Published | May 25, 2023 |
Base Model | |
Training | Steps: 2,390 Epochs: 10 |
Trigger Words | hishi miracle \(umamusume\) |
Hash | AutoV2 FDB52B484C |
LoHa of Hishi Miracle (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: Pretty Derby, unless there is a special notice.
Recommended options
LoRA weight 0.6 ~ 0.7
Trigger words
Base
hishi miracle \(umamusume\)
Casual :
casual, ear covers, ear ornament, white dress, long sleeves, jeans, blue pants, brown footwear, shoes
Original Art :
ear covers, ear ornament, collared shirt, white shirt, sleeveless shirt, necklace, bare shoulders, detached sleeves, puffy long sleeves, white sleeves, blue dress, white skirt, black pantyhose, boots, white footwear, black footwear
Tracen summer uniform
tracen school uniform, summer uniform, serafuku, puffy short sleeves, purple bowtie, horseshoe ornament, sailor collar, sailor shirt, purple shirt, white skirt, pleated skirt, frilled skirt, miniskirt, zettai ryouiki, white thighhighs, brown footwear, loafers
Tracen winter uniform
tracen school uniform, ear ornament, hairclip, winter uniform, puffy long sleeves, sailor collar, purple shirt, white bowtie, horseshoe ornament, purple skirt, pleated skirt, purple thighhighs, brown footwear, loafers
Use a model derived from or mixed with animefull model.
Settings
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.
Thank you all a lot!
based on Animefull-pruned model
114 images consist of
4x low quality 48 images
8x medium quality 40 images
16x high quality 26 images
=> 1 epoch = 928 images
replaced character feature tags with hishi miracle \(umamusume\)
1girl, white hair, simple background, ahoge, solo, short hair, horse girl, green eyes, blue eyes, brown eyes, grey hair, horse tail, blue hair, long hair, animal ears, medium hair, purple eyes, horse ears, grey eyes, red eyes, yellow eyes, bangs, light purple hair, virtual youtuber,
[a-zA-Z\s\-]+hair, [a-zA-Z\s\-]+eyes, [a-zA-Z\s\-]+ears, horse[a-zA-Z\s\-]+, [a-zA-Z\s\-]+bangs
I think these tags are the essentials of Hishi Miracle 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.