Orange filter版本v1.0 (ID: 1302943)

1. Introduction

This is a LoRA to add an effect of orange filter used in photography. You should know this LoRA can change expected composition, color, and object from the original result, so it is hard to say that the LoRA can be used as an actual filter for your physical camera.

The source image is just a single and simple colored PNG image.

This LoRA was trained on my computer (Ryzen 5 2600 + 16 GB RAM + 500 GB SSD + NVIDIA GeForce RTX 2060 6 GB) with SD-Trainer by Akegarasu (https://github.com/Akegarasu/lora-scripts), on sd-scripts by kohya-ss (https://github.com/kohya-ss/sd-scripts/tree/main), and well known configurations of training as follows (I don't change most default parameters):

• DreamBooth method without regularization images

• pretrained model: ULTRA v3 (for SD 1.5) https://civitai.com/models/228525?modelVersionId=470417

• resolution = 512 x 512

• epochs = 10

• optimizer type = "Lion"

• steps = 40 (yes 40!)

2. Usage

To be a simple way in your prompt, please add LoRA decralation with some weight value just as "<lora:BT_Orange_Filter_100_v1:1>" and put the trigger keyword "orange filter 100" in some place of your prompt. In most cases, a keyword of style will be better to write a later position in your prompt.

A weight value can vary a result, you know. When you set "0," no effect will be shown, and when you set "1" or more value, the result may be worse by the well-known "overfitting," and most images are likely resembled with the original images used in my training. So, you will have to set the value in your own situtation (what other LoRA you use, and where do you put a keyword in your prompt, and son on.) If you set a weight over 1.0, the overfitting may be happen. But most results of larger images are well painted by a weight of 1.0 as the following image.

A value for CLIP SKIP will be available not only 1 but also 2.

Here're sample images of the original (without LoRA) and enabled result by the same seed and configuration besides the LoRA declaration and trigger word.

2.1 original

2.2 <lora:BT_Orange_Filter_100_v1:1>

Results would be varied not only in colors but also in composition and components of image by a weight value in LoRA declaration, depending on other LoRA you use, the position of trigger word ("orange filter 100") in your prompt, base model, or others. Generally speaking, a weight under 0.5 will be ineffective and a weight over 1.0 can make an overfitting

3. the Last word

Have fun, and thanks to users, creators of scripts, applications, models, and at last but not least, to crews at Civitai.

描述:

The initial release!

训练词语: orange filter 100