Satono-Diamond-umamusume

我要开发同款
匿名用户2024年07月31日
14阅读
开发技术Pytorch
所属分类ai、text-to-image、lora
开源地址https://modelscope.cn/models/sd_lora/Satono-Diamond-umamusume
授权协议Apache License 2.0

作品详情

LoRA of Satono Diamond (umamusume). Put LoRA file in your stable-diffusion- webui/models/lora folder and write LoRA __ notation in prompt to applying LoRA. <lora :yourlohaname:weight>

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

Recommend options

  • LoRA weight 0.7~0.9

  • Trigger words

    • base

    • satono diamond \(umamusume\)

    • Racing competition clothes :

    • sleeves past wrists, sleeves past fingers, frilled sleeves, frills, long sleeves, corset, green dress, braid, ascot, green jacket, green skirt, black thighhighs, boots, white footwear

    • 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

    • New year costume :

    • official alternate costume, hair flower, frills, red flower, japanese clothes, white kimono, wide sleeves, long sleeves, thighhighs

    • Due to lack of sample image, it comes out rarely, sry!

    • Casual clothes :

    • She has too normal casual clothes…

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 highres. 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

  • 225 images of satono diamond

    • 4x low quality 71 images

    • 8x medium quality 66 images

    • 16x high quality 88 images

    • => 1 epoch = 2220 images

  • replaced character feature tags with satono diamond \(umamusume\)

    • horse girl, horse tail, brown hair, orange eyes, etc.
  • resolution : 768x768

  • rank=alpha=16

  • batch size = 4, 5 epochs trained

  • other training settings included in training_data.zip

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

All uploaded images are generated by AOM3A1

声明:本文仅代表作者观点,不代表本站立场。如果侵犯到您的合法权益,请联系我们删除侵权资源!如果遇到资源链接失效,请您通过评论或工单的方式通知管理员。未经允许,不得转载,本站所有资源文章禁止商业使用运营!
下载安装【程序员客栈】APP
实时对接需求、及时收发消息、丰富的开放项目需求、随时随地查看项目状态

评论