sketch_shouxin Open-source Model - Freely Achieve Minimalist Line and White Space Pencil Sketch Style Painting

Sketch Shouxin

Developed by Ttio2

A Stable Diffusion 3.5 Large LoRA model trained on works by contemporary Chinese artist Shouxin, specializing in minimalist line and negative space pencil sketch techniques

Image Generation Open Source License:Apache-2.0 #Minimalist line sketch #Dynamic moment capture #Freehand character essence

Downloads 25

Release Time : 12/18/2024

Model Overview

This model generates pencil sketch images in the style of contemporary Chinese artist Shouxin, particularly excelling at capturing character essence and dynamic moments

Model Features

Shouxin Artistic Style

Imitates the minimalist lines and negative space techniques of contemporary Chinese artist Shouxin, featuring a unique freehand style

Dynamic Capture

Excels at vividly presenting dynamic moments through contrast between bold lines and soft shadows

Eye Depiction

The expressive eye depictions in artworks create striking contrast with abstract forms, giving works vibrant vitality

LoRA Fine-tuning

LoRA fine-tuned based on Stable Diffusion 3.5 Large model, retaining original model capabilities while adding specific style

Model Capabilities

Text-to-Image

Art style transfer

Pencil sketch generation

Specific artist style imitation

Use Cases

Art Creation

Character Sketch Generation

Generate character pencil sketches in Shouxin style

Examples show colored pencil sketch effects of a woman in yellow dress with red hat

Animal Sketch Generation

Generate animal pencil sketches in Shouxin style

Examples show pencil sketch effects of elephant and red panda

Scene Sketch Generation

Generate scene pencil sketches in Shouxin style

Examples show pencil sketch effects of White House and dump truck

Creative Design

Anime Style Conversion

Convert ordinary anime characters to Shouxin-style pencil sketches

🚀 sketch_shouxin

A Stable diffusion 3.5 Large LoRA model trained based on art works by Shou Xin (手訫)

🚀 Quick Start

This model is a Stable diffusion 3.5 Large LoRA model trained based on art works by Shou Xin (手訫). You can use it to generate images similar to Shou Xin's style.

✨ Features

Unique Art Style: Inspired by the works of Shou Xin, a contemporary artist from Henan, China. His art features minimalist linework, skillful use of negative space, and expressive eyes.
Multiple Subjects: While mainly focusing on cats, it can also generate sketches of dogs, anime - inspired figures, and other subjects like men playing basketball, elephants, etc.
Easy to Use: Trigger the image generation by using the words shouxin and pencil sketch.

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

You can use the following prompts to generate images:

a pencil sketch of the white house
shouxin, a pencil sketch of Lionel Messi
shouxin, A color pencil sketch of red panda

You can see some example outputs in the widget section above.

📚 Documentation

Model description

Shou Xin is a contemporary artist from Henan, China, who primarily shares his work on Xiaohongshu (Little Red Book), a popular social media platform. His art features minimalist linework and skillful use of negative space, capturing personality and subtle expressions over precise detail. While cats are his main focus, he occasionally includes dogs and anime - inspired figures. Using pencil, erasers, and small knives for added texture, Shou Xin combines bold lines with soft shading, balancing sharpness and fluidity to convey movement and transience. His sketches are defined by expressive eyes that contrast with abstract forms, bringing lifelike presence.

For use in ComfyUI, see ComfyUI workflow

There is also a video walkthrough of the training