Souun style版本v1.0 (ID: 1310064)

1. Introduction

This is a LoRA for illustrations in style of 田崎草雲 (Tazaki Souun, 1815-1898). I would like to serve a LoRA made with 35 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 = 30

• optimizer type = "Lion"

• steps = 2,640

2. Usage

To be a simple way in your prompt, please add LoRA decralation with some weight value just as "<lora:BT_Tazaki_Souun_v1:1>" and put the trigger keyword "tazaki souun" 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.

Anyway, here's a sample image.

Prompt: no humans, (painting, restricted colors, ink brush stroke, Japanese art), (simple background, cream white background), very wide shot, scenary, perspective, outdoors landscape, Tokyo Harajuku Fashion Sunset Scene A lively scene with a young Japanese girl walking down Harajuku's famous Takeshita Street during the sunset, surrounded by warm light and trendy fashion stores, highly detailed and sharp focus. in Le Morne Brabant, wallpaper, uncensored, unparalleled masterpiece, finely detail, incredibly absurdres, perfect artwork, highres, concept art, elegant, extremely detailed, intricate, professionally color graded, UHD, HDR, 32K, 16K, professional illustration, vibrant details, abstract beauty, (tazaki souun) <lora:BT_Tazaki_Souun_v1:0.75>

Negative prompt: multiple girls, multiple angles, multiple views, collage, multiple images, frame, border, split frame, split screen, easynegative, FastNegativeV2, an7-neg, badquality, nncursedV0, NegfeetV2, CR1.2-neg, verybadimagenegative_v1.3, ng_deepnegative_v1_75t

Steps: 30, Sampler: DPM++ 3M SDE, Schedule type: Karras, CFG scale: 6, Seed: 2768907422, Size: 1024x576, Model hash: 2289c564ac, Model: ultra_v3, VAE hash: 63aeecb90f, VAE: ClearVAE_V2.3.safetensors, Lora hashes: "BT_Tazaki_Souun_v1: f3e69c2df71a", Version: v1.10.1

3. Weight

Results would be varied by a weight value in LoRA declaration, depending on other LoRA you use, the position of trigger word ("shibata zeshin") 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.

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:

The initial release.

训练词语: tazaki souun