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

LoCon, LoRA for Convolutional Network, is also kind of LoRA.

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

Recommend options

• LoCon weight around 0.9

• Trigger words

  • base

    • copano rickey \(umamusume\)

  • Racing competition clothes :

    • bare shoulder, off-shoulder, blue gloves, bead bracelet, fingerless gloves, detached sleeves, wide sleeves, red ribbon, neck ribbon, cleavage, yellow dress, frilled dress, yellow footwear, white footwear, boots, mismatched footwear, asymmetrical footwear

    • (optional) holding fan, folding fan, hand fan

  • Gaze on me :

    • collarbone, white shirt, side tie, tied shirt, floral print, swim trunks, wrist scrunchie, short sleeves, alternate costume

  • Casual clothes :

    • yellow dress, yellow bowtie, belt, casual, puffy sleeves, short sleeves, plaid, white socks

  • Tracen school uniform :

    • white thighhighs, tracen school uniform, purple shirt, pleated skirt, puffy short sleeves, white skirt, puffy sleeves, summer uniform, frilled skirt, sailor collar, sailor shirt, miniskirt, frills

Use animefull based model

• Settings

  • Stable Diffusion WebUI by Automatic1111

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

  • about 20 steps, CFG scale 3.5~6.5

  • kl-f8-anime2.vae

  • CLIP skip = 1

  • Use Hires.fix to get higher quality image

    • Upscaler : Latent series

    • Denoising strength 0.50~0.65

LoRA training info

• trained on sd-scripts by kohya_ss. Thank you a lot!

• based on Animefull-pruned

• 130 images of copano rickey

  • 4x low quality 44 images

  • 8x medium quality 44 images

  • 16x high quality 42 images

  • => 1 epoch = 1200 images

• replaced character feature tags with copano rickey \(umamusume\)

  • horse girl, horse tail, brown hair, red eyes, etc.

• resolution : 768x768

• rank=alpha=16

• conv_rank=conv_alpha=16

• batch size = 4

• other training settings is included in training_data.zip

This LoRA may be compatible with animefull-based models (ex. AbyssOrangeMix Series...)

All uploaded images are generated by AOM3A1

Thank you KohakuBlueleaf for introducing LoCon.

And, special thanks to my best friend. DH.