LoHa of Yaeno Muteki (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. ๐
Recommended options
LoRA weight around 0.6
Trigger words
Base
yaeno muteki \(umamusume\)
Racing competition costume :
japanese clothes, sleeveless, detached sleeves, fingerless gloves, red gloves, cleavage cutout, clothing cutout, sash, obi, hakama, black skirt, ribbon trim, kneehighs, socks, sandals
Casual :
casual, long sleeves, black jacket, track jacket, track suit, black pants, track pants, sneakers
Tracen summer uniform
tracen school uniform, summer uniform, serafuku, puffy short sleeves, bowtie, horseshoe ornament, sailor collar, sailor shirt, frills, white skirt, purple shirt, miniskirt, zettai ryouiki, white thighhighs, brown footwear, shoes
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
40 images of
4x low quality 14 images
8x medium quality 13 images
16x high quality 13 images
=> 1 epoch = 368 images
replaced character feature tags with yaeno muteki \(umamusume\)
1girl, hair between eyes, short hair, tail, brown hair, simple background, solo, horse ears, streaked hair, animal ears, bangs, horse girl, hair ornament, light brown hair, white hair, horse tail, multicolored hair, brown eyes, red eyes, two-tone hair
I think these tags are
the essentials of Yaeno Muteki
or unnecessary for training because of duplication.
resolution : 768x768 with aspect ratio bucketing.
other training settings is included in training_data.zip or metadata in LoRA file.
All uploaded images are generated by AOM3A1
And, special thanks to my best friend. DH.