flux lora eric cat

Introduction

The FLUX-LORA-ERIC-CAT model is a custom LoRA (Low-Rank Adaptation) model designed for text-to-image generation, specifically featuring the "Eric cat style." It serves as a tribute to the creator's beloved cat, Eric, and is trained to produce images in various Eric cat styles.

Architecture

The model is based on the "black-forest-labs/FLUX.1-dev" as its base model. It incorporates several tags and technologies, including autotrain, spacerunner, text-to-image, flux, lora, and diffusers. The model is designed to be used with the diffusers library for generating images based on text prompts.

Training

The model was trained using the AutoTrain pipeline, which helps in automating the training of deep learning models. The specific focus was on capturing the unique characteristics of the Eric cat style, as inspired by the creator's pet cat.

Guide: Running Locally

1. Download the Model:

   • Access the model weights in Safetensors format from the Files & versions tab on the Hugging Face model page.

2. Setup Environment:

   • Install the diffusers library using pip:

     pip install diffusers
     

3. Load the Model:

   • Use the following Python code to load and run the model:

     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('ginipick/flux-lora-eric-cat', weight_name='flux-lora-eric-cat')
     image = pipeline('eric cat style, cute cat').images[0]
     image.save("my_image.png")
     

4. Hardware Recommendations:

   • For optimal performance, using cloud GPUs such as those provided by AWS, Google Cloud, or Azure is recommended.

License

The FLUX-LORA-ERIC-CAT model is distributed under the "flux-1-dev-non-commercial-license," which restricts its use to non-commercial purposes. Users should review the full license terms before using the model.