找回密码
 立即注册
查看: 1339|回复: 0

[传统艺术] [SD 1.5][LORA]tama5 Style LoRA v1.0

[复制链接]

3869

主题

36

回帖

4331

积分

管理员

积分
4331
发表于 2023-6-7 20:57:30 | 显示全部楼层 |阅读模式

基础数据

样图
基本模型:
SD 1.5
小模型:
Lora 
下载链接:
您必须是网站正式用户方可进行下载。

tama5 Style LoRA

If you enjoy my models and want to support me you could buy me a coffee!

This LoRA mimics the artstyle of the artist tama5. Keep in mind when using it that it was trained on 6GB VRAM so the embedding might not be as good as other ones on this website but you can still get satisfactory results.

The example images were created with AbyssOrangeMix2 and I was using varying weight but feel free to experiment with other weights and models. It seems to be very good at making portraits and flowers. This might be model-specific but it is much better at making women than men. For the NSFW images i have also been using a couple of Corneo's textual inversion embeddings as well as JustNeutral's Shylily embedding and it seems to be merging decently.

To change the weight just change the '1' in this prompt: <lora:tama5:1>.

I'd love to see the art you guys make with it so feel free to add them in comments.

How to use LoRA's in auto1111:

  • Update webui (use git pull like here or redownload it)

  • Copy the file to stable-diffusion-webui/models/lora

  • Select your LoRA like in this video

  • Make sure to change the weight (by default it's :1 which is usually too high)

您需要登录后才可以回帖 登录 | 立即注册

本版积分规则

Archiver|手机版|小黑屋|金房子

GMT+8, 2024-12-24 09:15 , Processed in 0.038403 second(s), 23 queries .

© 2023 金房子|AI发烧友社区

快速回复 返回顶部 返回列表