LoHa of Tanino Gimlet (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. 👍

Recommended options

• LoRA weight around 0.7

• Trigger words

  • Base

    • tanino gimlet \(umamusume\)

  • Racing competition costume :

    • eyepatch, black choker, half gloves, asymmetrical gloves, mismatched gloves, black glove, white glove, shoulder cutout, bare shoulders, detached sleeves, long sleeves, sleeveless shirt, blue necktie, open clothes, black jacket, collared shirt, yellow shirt, striped vest, belt, chain, white shorts, black skirt, thigh strap, black pantyhose, fishnet pantyhose, knee boots, high heel boots, black footwear

  • Casual (I guess) :

    • eyepatch, black choker, off shoulder, tank top, purple shirt, black jacket, open jacket, short shorts, denim shorts, cutoffs, fishnet pantyhose

  • 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, winter uniform, puffy long sleeves, sailor collar, sailor shirt, purple shirt, white bowtie, horseshoe ornament, purple skirt, frills, brown footwear, loafers

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.

  • LyCORIS by KohakuBlueleaf

  • Thank you all a lot!

• based on Animefull-pruned model

• 148 images consist of

  • 4x low quality 65 images

  • 8x medium quality 44 images

  • 16x high quality 39 images

  • => 1 epoch = 1236 images

• replaced character feature tags with tanino gimlet \(umamusume\)

  • 1girl, alternate costume, pink hair, medium hair, horse ears, grey eyes, animal ears, blue hair, purple hair, horse girl, streaked hair, short hair, bangs, black hair, yellow eyes, red eyes, multicolored hair, two-tone hair, puffy sleeves, fishnets, green eyes, simple background, official alternate costume, white hair, solo, brown hair, horse tail, black eyes, blue eyes, brown eyes

  • I think these tags are the essentials of Tanino Gimlet 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.