santa hat
deerdeer nosedeer glow
Sign In

Colored ART

491
3.2k
2.0k
42
Verified:
SafeTensor
Type
LoRA
Stats
924
1,256
Reviews
Published
Oct 26, 2023
Base Model
SD 1.5
Training
Steps: 3,000
Epochs: 2
Usage Tips
Clip Skip: 2
Trigger Words
red powder
Hash
AutoV2
A7B7C849AC
default creator card background decoration
First Birthday Badge
vjleoliu's Avatar
vjleoliu

If you enjoy my work, please give me a five-star rating; it means a lot to me! Check out other creations here.

如果你喜欢我的作品,请给我一个五星好评,这对我非常重要!这里看其他作品。

I don't know English, the following translation is from chatGPT.

我不会英文,以下译文来自chatGPT

introduce

This is a series of lora collections with a colored theme. Try to avoid contamination between colors. Although it can be used very well for animation, but it was originally trained for real photos. Of course, I will also work hard to adjust the balance between the two.

这是一个以色彩为主题的lora系列。最大限度的避免了颜色之间的污染。虽然它可以很好地作用于二次元模型,但其实这个系列的初衷是为拟真照片而训练的,所以泛化性还不错,当然,我也在努力调整两者之间的平衡。

Instructions

the trigger word is usually "color-subject", such as "red-blindfold" or "blue-blindfold". of course, you can also enhance the effect by increasing the weight of the trigger words, such as (red-blindfold:1.2)

these lora works well with very low weights, you can mix it with other loras without worrying about the image being destroyed.

Be sure to read "about this version" before downloading these models, it has weight ranges, a complete list of trigger words and some other necessary information.

触发词通常是“颜色-主体”,例如“red-blindfold”即“红色眼罩”。当然,你也可以通过增加触发词的权重来增强效果,例如 (red-blindfold:1.2)

这系列lora的权重在非常低的情况下就可以发挥很好的作用(通常在0.3左右就能看到效果),所以它可以很好的与其他 lora 混合使用,而不必担心图像被破坏。

在下载这些模型之前,请务必阅读右侧的“about this version”,有具体的权重范围、触发词的完整列表和一些其他必要的信息。

If you'd like to support me and do more : ☕ https://ko-fi.com/vjleoliu ☕commissions open

lora: Colored powder

recommended weight: 0.6~0.9

Hires. fix:8x_NMKD-Superscale_150000_G

It requires: ADetailer

lora: Colored blindfold

The recommended weight is: 0.3~0.6

lora: Colored glasses

The recommended weight is: 0.6~0.9

checkpoints

Each lora is trained through hundreds of high-definition pictures, trained on 1.5 checkpoints, and verified on 10 famous checkpoints, almost including all the realistic styles and 2.5D styles on the leaderboard, the list of checkpoints is as follows:

推荐模型

AbsoluteReality

chilloutmix_NiPrunedFp32Fix

CyberRealistic

deliberate

DreamShaper

Edge Of Realism_EOR

Ether Real Mix

lyriel

Realistic Vision

ReV Animated

Since you've reached the end, please give me a five-star review;

it's very, very important for my ongoing creativity! Thank you!

都看到这了,不给个五星好评么?

I hope you equally enjoy my other works.