Fart_SDXL版本v5.1 (trash) (trash)

Fart_SDXL版本v5.1 (trash) (trash)

If you find any improvements, please let me know and I will refer to them.

Version 2.1

  1. Increased dataset.

  2. Poses have become more dynamic

  3. The amount of farts increased.

Since this is an increased dataset in addition to the 2.0 dataset, you can consider using both at the same time to find an appropriate value.


Version 2.0

I've completely changed the way the model is trained.

Learning was done using animagine v3.0 base,

but since it was learned individually, it can be used to some extent in a pony environment.

You can apply the sentence, such as "fart squirts from the ass" and "huge fart suqirts from the ass", "green fart", "yellow fart" etc.

And when changing the color, you must add the desired color in front of all fart-related tags.

Farting and farts tags with similar token values ​​are also possible to some extent.

Of course, it's not perfect.

One thing is for sure, this is the most perfect fart model I have made so far.


Version 1.311 changed the data set while learning using the MLP method.

Not intended, but it also works with ponydiffusion.


LOHA has a very strong norm=tensor by nature, requiring a low weight of 0.12 to 0.15.

(This is not the correct answer because it is a personal recommended value.)

First of all, there are three learning tags: fart, farting, and sprays, but due to the nature of SDXL, these three keywords can be applied to other sentences.

An example is “There is a fart below.”

I built this model to act as a secondary, so I don't recommend using it exclusively.

For stability, it is recommended to adjust the tag weight rather than the lora or loha weight.

I bet it's much better than just using v1.2 alone.


Version 1.2 is the same dataset as before, but with a different training method and tags.

It is relatively more purposeful than 1.1.


The 1.1 version still has a lower hit rate than the 5.1 (old) version.

I plan to supplement this part additionally.

However, the overfitting is so severe that I recommend the 1.1 version.


5.1 (old) Due to promiscuous active tags, the Lora model had to be weighted down to overfit, and the model itself was unstable due to frequent mergers.

Version 1.1 recommends a weight of about 0.7.

The reason for version 1.1 from the beginning is that version 1.0 has only increased the same setting and the number of learning steps on the dataset.


描述:

It's a stable version among the versions I made before.

训练词语: fart, farting, yellow smoke, sprays, yellow smoke sprays, yellow gas sprays

名称: Fart_SDXL_v5.1.safetensors

大小 (KB): 475375

类型: Model

Pickle 扫描结果: Success

Pickle 扫描信息: No Pickle imports

病毒扫描结果: Success

Fart_SDXL

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/944488.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