Sign up for free and get 10,000 credits instantly

Starter credits for new creators, added to your account on the day you sign up.

Notice: PixAI iOS App Temporarily Unavailable on the App Store — Dear PixAI users, The PixAI iOS app is currently unavailable for search and download on the App Store. We are actively w…

View details

User LoRA

SD

Mejiro Dober (umamusume)

Mejiro Dober (umamusume) - AI Model cover image
Uploaded at
Jul 26, 2024, 6:22 AM
Uses
360
Reviews
No reviews
Trigger Words

mejiro dober \(umamusume\),

Permissions
  • Allow image generation & sharing
  • Allow users to download this model
  • Allow commercial use of generated images

Description

LoRA of Mejiro Dober (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:weightAll of my works is free. If you'd like to support me, feel free to buy me a coffee. 👍Recommend optionsLoRA weight 0.7~1.0Trigger wordsbasemejiro dober (umamusume)Racing competition clothes :white gloves, sleeveless shirt, white shirt, center frills, collared shirt, bare shoulders, belt, pleated skirt, green skirt, thigh strap, kneehighs, white socks, high heels(optional) suspenderCamping costume :sun hat, straw hat, barefoot, blue dress, sleeveless dress, bracelet , bare shoulders, collarbone, ears through headwearWedding costume :Due to lack of image set, not included in LoRA. Maybe normal wedding dress is possible.Use animefull based modelSettingsDPM++ Series(SDE Karras, 2M Karras, etc.)about 20 steps, CFG scale 3.5~6.5kl-f8-anime2.vaeCLIP skip = 1Use highres.fix to get higher quality imageUpscaler : Latent seriesDenoising strength 0.50~0.65LoRA training infotrained on sd-scripts by kohya_ss. Thank you a lot!based on Animefull-pruned114 images of mejiro dober4x low quality 36 images8x medium quality 39 images16x high quality 39 images=> 1 epoch = 1080 imagesreplaced character feature tags with mejiro dober (umamusume)horse girl, horse tail, brown hair, purple eyes, etc.using aspect ratio bucketingresolution : 768x768rank=alpha=16using dadaptationbatch size = 4, 7 epochs trainedclip skip = 1This LoRA may be compatible with animefull-based models (ex. AbyssOrangeMix Series...)All uploaded images are generated by AOM3A1

Comments

Artwork made by Mejiro Dober (umamusume)