HANBOK Model

Introduction

The HANBOK model is a text-to-image model designed to generate images based on descriptions. It utilizes the FLUX.1-dev architecture with LoRA integration to create detailed visual representations, such as a traditional Korean Hanbok.

Architecture

The model is based on the black-forest-labs/FLUX.1-dev architecture and incorporates LoRA (Low-Rank Adaptation) to enhance the generation capabilities. It supports the Diffusers library, allowing flexible and efficient image generation.

Training

The model leverages the FLUX.1-dev base model with additional training using LoRA for specific prompts, such as "hanbok," to ensure it can generate accurate and aesthetically pleasing images based on detailed text descriptions.

Guide: Running Locally

To run the HANBOK model locally, follow these steps:

1. Environment Setup:

   • Ensure you have Python installed.
   • Install the Diffusers library using pip:

     pip install diffusers
     

2. Download Model Weights:

   • Visit the Files & Versions tab to download the model weights in Safetensors format.

3. Load and Run Model:

   • Use the following Python code to load the model and generate an image:

     from diffusers import AutoPipelineForText2Image
     import torch
     
     pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to('cuda')
     pipeline.load_lora_weights('seawolf2357/hanbok', weight_name='hanbok.safetensors')
     image = pipeline('a woman wearing a traditional Korean Hanbok, a long-sleeved blouse with intricate embroidery and a high-waisted skirt. The blouse is a deep blue color with a white collar and cuffs, and the skirt is a lighter shade of blue with a pattern of small white flowers. The woman is standing in a graceful pose, her hands clasped in front of her and her head tilted slightly to the side. [trigger]').images[0]
     image.save("my_image.png")
     

4. Suggested Cloud GPUs:

   • For optimal performance, consider using cloud services that provide GPU support, such as AWS EC2 with NVIDIA GPUs, Google Cloud Platform, or Azure.

License

The HANBOK model is released under the flux-1-dev-non-commercial-license. For more details, refer to the license link. This license restricts usage to non-commercial purposes.