Manhattan Cafe (umamusume)版本V1.0 (ID: 8935)

Manhattan Cafe (umamusume)版本V1.0 (ID: 8935)

LoHa of Manhattan Cafe (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. ?

[2023-03-20 07:40 GMT] LoHa version added. Many costume available!

Recommended options

  • LoRA weight around 0.7

  • Trigger words

    • Base

      • manhattan cafe \(umamusume\)

    • Racing competition costume :

      • black choker, black gloves, long sleeves, collared shirt, yellow necktie, black vest, black coat, belt, black skirt, pleated skirt, black pantyhose, shoes, white footwear

    • SSR Stamina :

      • official alternate costume, alternate hairstyle, ponytail, single earring, long sleeves, layered sleeves, green apron, collared shirt, white shirt, sweater vest, neck ribbon, white ribbon

    • Casual :

      • casual, neck ribbon, black ribbon, puffy long sleeves, bracelet, yellow shirt, collared shirt, frilled shirt collar, shirt tucked in, black belt, belt buckle, green skirt, plaid skirt, long skirt, black pantyhose, black footwear

    • 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

    • Other Costumes :

      • New Year :

        • alternate costume, alternate hairstyle, ponytail, hair flower, hair ornament, japanese clothes, black kimono, sash, obi, long sleeves, wide sleeves, floral print, fur trim

      • Maid :

        • maid headdress, enmaided, black choker, ascot, puffy sleeves, long sleeves, juliet sleeves, black dress, collared dress, maid apron, white apron, frilled apron

      • Swimsuit :

        • tracen swimsuit, blue one-piece swimsuit, competition school swimsuit, white stripes, single vertical stripe

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.

  • based on Animefull-pruned model

  • 235 images of

    • 4x low quality 75 images

    • 8x medium quality 80 images

    • 16x high quality 80 images

    • => 1 epoch = 2220 images

  • replaced character feature tags with manhattan cafe \(umamusume\)

    • 1girl, solo, brown eyes, horse girl, yellow eyes, blue eyes, simple background, white hair, 1girl, streaked hair, bangs, very long hair, horse ears, horse tail, tail through clothes, animal ears, hair between eyes, black hair, multicolored hair, closed eyes, long hair, ahoge, long bangs, piercing, open clothes, jacket, black jacket, ear piercing, single earring,

    • I think these tags are

      • the essentials of Manhattan Cafe

      • 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.

描述:

This is old version.

LoRA of Manhattan Cafe (umamusume).

Recommend options

  • LoRA weight 0.5~0.65

  • Trigger words

    • base

      • manhattan cafe \(umamusume\)

      • (optional) white ahoge, black long hair

    • Racing competition clothes :

      • black coat, black shirt, black skirt, yellow necktie

  • Use animefull based model

  • Settings

    • DPM++ SDE Karras

    • 20 steps, CFG scale 4.5~6.5

    • kl-f8-anime2.vae

    • CLIP skip = 1

    • Highres

      • Latent (bicubic antialiased)

      • Denoising strength 0.55~0.65

LoRA training info

  • based on Animefull-pruned

  • 32 images of manhattan cafe

    • 25x low quality 12 images

    • 50x medium quality 12 images

    • 100x high quality 8 images

    • => 1 epoch = 1700 images

  • rank=alpha=16

  • using dadaptation

  • batch size = 4, 6 epoch trained

  • clip skip = 1

All uploaded images are output of AbyssOrangeMix2-nsfw, kl-f8-anime2.vae

训练词语: manhattan cafe \(umamusume\)

名称: img.zip

大小 (KB): 84085

类型: Training Data

Pickle 扫描结果: Success

Pickle 扫描信息: No Pickle imports

病毒扫描结果: Success

名称: manhattan_cafe_lora.safetensors

大小 (KB): 18544

类型: Model

Pickle 扫描结果: Success

Pickle 扫描信息: No Pickle imports

病毒扫描结果: Success

Manhattan Cafe (umamusume)

Manhattan Cafe (umamusume)

Manhattan Cafe (umamusume)

Manhattan Cafe (umamusume)

Manhattan Cafe (umamusume)

资源下载
下载价格VIP专享
仅限VIP下载升级VIP
犹豫不决让我们错失一次又一次机会!!!
原文链接:https://1111down.com/895274.html,转载请注明出处
由于网站升级,部分用户密码全部设置为111111,登入后自己修改, 并且VIP等级提升一级(包月提升至包季,包季提升到包年 包年提升至永久)
没有账号?注册  忘记密码?

社交账号快速登录