shou_xin

Introduction

The shou_xin model, developed by Datou1111, is a text-to-image model that produces pencil sketch-style images. It utilizes the FLUX.1-dev model as its base and is fine-tuned for generating monochromatic and color pencil sketches in a minimalist, impressionist style with negative space.

Architecture

The model is built using the Diffusers library, which is optimized for generating high-quality images from text prompts. It is configured to accept prompts that include the phrase shou_xin, pencil sketch to trigger its unique image generation style.

Training

Fine-tuning was performed using the lora method, a lightweight fine-tuning technique that adapts pre-trained models to specific tasks efficiently. The model leverages a template for diffusion-lora to enhance the generation of detailed pencil sketches.

Model Stats Number

• Base Model: black-forest-labs/FLUX.1-dev
• License: flux.1-dev-non-commercial-license

Guide: Running Locally

To run the shou_xin model locally, follow these steps:

1. Setup Environment:

   • Ensure Python and necessary libraries (e.g., diffusers, torch, etc.) are installed.
   • Use pip install diffusers to install the Diffusers library.

2. Download Model:

   • Access the Files & versions tab to download the weights in Safetensors format.

3. Run the Model:

   • Load the model and initiate the image generation using prompts with the trigger words shou_xin, pencil sketch.

4. Hardware Suggestions:

   • For optimal performance, consider using cloud GPUs such as NVIDIA Tesla V100 or A100 available on platforms like AWS, GCP, or Azure.

License

The shou_xin model is distributed under the flux.1-dev-non-commercial-license, which permits usage for non-commercial purposes only.