1. Introduction

This is a LoRA for illustrations and paintings in style of an artist 董源 (Dong Yuan, 934-962). Training resources are taken from works on the web, and I would like to serve a LoRA made with 208 images as separated blocks from sources.

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 = 3,120

2. Usage

To be a simple way in your prompt, please add LoRA decralation with some weight value just as "<lora:BT_Dong_Yuan_v1:0.5>" and put the trigger keyword "dong yuan" 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, the overfitting may be happen.

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

Anyway, here's a sample image.

Prompt: (no humans, black ink painting, monochrome, brown background, brush painting, scenary, painting, traditional media, antique, 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) (dong yuan) <lora:BT_Dong_Yuan_v1:0.7> landscape is characterized by its serene and tranquil atmosphere, evoking a sense of harmony between humans and nature. focusing on creating a sense of depth and atmosphere. use soft brushwork and subtle ink washes to create a hazy and ethereal effect, and pay attention to the placement of elements in the composition, creating a sense of balance and harmony. (rolling hills: haracterized by their rounded forms and gentle slopes, these hills create a sense of tranquility and harmony)

Negative prompt: multiple angles, multiple views, collage, multiple images, frame, border, split frame, split screen, humans, girl, boy, easynegative, badquality, verybadimagenegative_v1.3

Steps: 15, Sampler: DPM++ 3M SDE, Schedule type: Polyexponential, CFG scale: 7.5, Seed: 3046329076, Size: 1024x576, Model hash: 2289c564ac, Model: ultra_v3, VAE hash: 63aeecb90f, VAE: ClearVAE_V2.3.safetensors, Lora hashes: "BT_Dong_Yuan_v1: a07034b5b86e", Hardware Info: "RTX 2060 6GB, 5 2600 Six- Processor, 16GB RAM", Time taken: 6.9 sec., Version: v1.10.11

3. Weight

Results would be varied by a weight value in LoRA declaration, depending on other LoRA you use, the position of trigger word ("dong yuan") in your prompt, base model, or others. Generally speaking, a weight under 0.1 will be ineffective and a weight over 0.5 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.

Search AI Models & Addons

very few results