T Shirt Vector Style Flux

🚀 T-Shirt Vector Style - FLUX

This project is a LoRA model for Stable Diffusion, designed to generate vector - like t - shirt design images with a solid - color background.

🚀 Quick Start

Trigger Words

You should use 5h1rt to trigger the image generation. It is best used at the end of the prompt, like "tshirt design, (your prompt here), in the style of 5h1rt".

Download Model

Weights for this model are available in Safetensors format. Download them in the Files & versions tab.

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('SouthbayJay/t-shirt-vector-style-flux', weight_name='vector_shirt_flux_v1.safetensors')
image = pipeline('`5h1rt`').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers.

✨ Features

• Specific Style Generation: This LoRA model can generate vector - like images with a solid - color background, which is very suitable for t - shirt designs.
• Easy to Use: Just add the trigger word 5h1rt at the end of the prompt to start generating images.

📦 Installation

The installation mainly involves downloading the model weights and using the diffusers library. You can download the weights from the Files & versions tab and use the provided Python code to load the model.

💻 Usage Examples

Basic Usage

from diffusers import AutoPipelineForText2Image
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('SouthbayJay/t-shirt-vector-style-flux', weight_name='vector_shirt_flux_v1.safetensors')
image = pipeline('tshirt design, a beautiful woman standing next to a chevy impala hot rod, Los Angeles skyline in the background, in the style of 5h1rt').images[0]

📚 Documentation

Model description

The trigger word for this lora is 5h1rt. It is best used at the end of the prompt, like "in the style of 5h1rt". This lora is intended to create vector - like images with a solid - color background for easily removing the background and printing it on a t - shirt or any other items. It is still experimental, and the author is looking for ways to improve the dataset.

The author uses SwarmUI for 95% of image generations and encourages users to try it out. You can check the GitHub repo and also watch this install video from Kleebz Tech AI to get started.

📄 License

This project uses the bespoke - lora - trained - license.