【5步成像】Hyper-SD XL_Lora

LORA
Original


Updated:

1.6K

✨这是一个采用了字节跳动的【Hyper-SD_4step】加速技术的lora,根据原版自己瞎调的。

他可以在极少的步数下生成高质量的图像,欢迎大家尝试,

❗️我个人喜好设置:

⭕️采样器:DPM++SDE_Karras

⭕️采样步数:5

⭕️CFG:2

👍算力消耗大大降低啦!!

🥳希望你会喜欢,祝你玩得开心!

🈺可以的话,请多多发图啦……

✅推荐参数✅

❌Negative prompt:尽量不写或少写

【ugly, (worst quality, low quality, normal quality:1.45), low-res, simple background, watermark】

🖼️生图尺寸:768*1024、768*1152、768*1280、1024*1024、1024*768、1152*768、1280*768、

⭕️采样器:DPM++SDE_Karras【首推】>Eular_a&Eular>LCM

⭕️采样步数:4➡️5

⭕️CFG:1➡️2

Version Detail

SDXL 1.0

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

No posts yet
Describe the image you want to generate, then press Enter to send.