Yousai style版本v1.0 (ID: 1286061)

1. Introduction

This is a LoRA for illustrations in style of Kikuchi Yousai (1788-1878). You can enjoy images used in my training at the National Diet Library in Japan (https://dl.ndl.go.jp/ja/photo), and I would like to serve a LoRA made with 804 public domain images.

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 = 20

• optimizer type = "Lion"

• steps = 8,040

2. Usage

To be a simple way in your prompt, please add LoRA decralation with some weight value just as "<lora:BT_Kikuchi_Yousai_v1:1>" and put the trigger keyword "kikuchi yousai" 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 0.7, 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 2 but also 1.

Anyway, here's a sample image.

Prompt: 1man, solo, solo focus, full body, cinematic pose, innocent, (kimono, Japanese traditional clothes), simple background, cream white background, wallpaper, uncensored, unparalleled masterpiece, finely detail, incredibly absurdres, perfect artwork, highres, concept art, elegant, extremely detailed, intricate, UHD, HDR, 32K, 16K, professional illustration, movie promotional poster, textured skin, vibrant details, abstract beauty, studio quality, kikuchi yousai <lora:BT_Kikuchi_Yousai_v1:0.5>
Negative prompt: (nsfw, nude, sign, text, multiple angles, multiple views, collage, multiple images, frame, border, split frame, split screen:1.5), easynegative, badquality, verybadimagenegative_v1.3
Steps: 30, Sampler: DPM++ 3M SDE, Schedule type: Polyexponential, CFG scale: 7.5, Seed: 3161763089, Size: 1024x576, Model hash: 2289c564ac, Model: ultra_v3, VAE hash: 63aeecb90f, VAE: ClearVAE_V2.3.safetensors, Lora hashes: "BT_Kikuchi_Yousai_v1: 7f8d725a7418", TI hashes: "easynegative: c74b4e810b03, verybadimagenegative_v1.3: d70463f87042", Version: v1.10.1

3. Weight

[Notice] It is hard to add images on the lower part of web page on this editor application, so unfortunately I will not use explanatory images below.

Results would be varied by a weight value in LoRA declaration, depending on other LoRA you use, the position of trigger word ("hiroshige") in your prompt, base model, or others. Generally speaking, a weight under 0.3 will be ineffective and a weight over 0.7 can make an overfitting. But in making of landscape images, this LoRA can give us an interesting taste on image like this.

And for more realistic illustrations, this LoRA can add some nice taste as follows.

4. 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:

This is an initial release.

训练词语: kikuchi yousai