Antique style版本v1.0 (ID: 1272439)

1. Introduction

This is a LoRA for photorealistic images in style of antique photographs. I love a black and white photograph and antique or vintage scenes. You can enjoy such photographs at the National Diet Library in Japan (https://dl.ndl.go.jp/ja/photo), and I would like to serve a LoRA made with 652 public domain photographs taken in 1911-1937.

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"

The steps for making this LoRA was 9,780.

2. Usage

To be a simple way in your prompt, please add LoRA decralation with some weight value just as "<lora:BT_Antique_v1:1>" and put the trigger keyword "bt antique" 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.

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

Anyway, here's a sample image.

Prompt: no humans, very wide shot, scenary, perspective, outdoors nature, Asian landscape, stunning modern urban upscale environment, wallpaper, uncensored, unparalleled masterpiece, finely detail, incredibly absurdres, perfect artwork, highres, perfect anatomy, perfection style, concept art, intricate, professionally color graded, UHD, HDR, 32K, 16K, professional painting, movie promotional poster, bt antique <lora:BT_Antique_v1:1>
Negative prompt: multiple angles, multiple views, collage, multiple images, frame, border, split frame, split screen, humans, girl, boy, easynegative, badquality, verybadimagenegative_v1.3
Steps: 30, Sampler: DPM++ 3M SDE, Schedule type: Polyexponential, CFG scale: 7.5, Seed: 10000, Size: 1024x576, Model hash: 2289c564ac, Model: ultra_v3, VAE hash: 63aeecb90f, VAE: vae-ft-mse-840000-ema-pruned_fp16.safetensors, Lora hashes: "BT_Antique_v1: 9c0cb621ec4e", TI hashes: "easynegative: c74b4e810b03, verybadimagenegative_v1.3: d70463f87042", 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 (bt antique) in your prompt, base model, or others. Here are samples of image by a different value of weight. Generally speaking, a weight under 0.5 will be ineffective and a weight over 0.7 can make an overfitting.

3.1 <lora:BT_Antique_v1:0.3>
3.2 <lora:BT_Antique_v1:0.5>
3.3 <lora:BT_Antique_v1:0.7>
3.4 <lora:BT_Antique_v1:1>

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 the initial release.

训练词语: bt antique