LAVLU00 Model Documentation

Introduction

LAVLU00 is a text-to-image model designed to generate images based on text prompts. It leverages the 🧨 Diffusers library and is trained on the black-forest-labs/FLUX.1-dev base model. The model is fine-tuned using LoRA (Low-Rank Adaptation) weights.

Architecture

The model is based on the black-forest-labs/FLUX.1-dev which utilizes a pipeline tagged for text-to-image generation. It employs the FLUX architecture and integrates LoRA layers to enhance its adaptability for specific tasks.

Training

LAVLU00 was trained using the Replicate platform with the flux-dev-lora-trainer. The training process incorporates LoRA weights, allowing efficient fine-tuning while maintaining the performance of the base model.

Guide: Running Locally

To run the LAVLU00 model locally, follow these steps:

1. Install the 🧨 Diffusers library:

   pip install diffusers
   

2. Import necessary libraries and load the model:

   from diffusers import AutoPipelineForText2Image
   import torch
   
   pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
   pipeline.load_lora_weights('MdLavluSheikh/lavlu00', weight_name='lora.safetensors')
   

3. Generate an image using your prompt:

   image = pipeline('your prompt').images[0]
   

4. For optimal performance, consider using a cloud GPU service such as AWS, Google Cloud Platform, or Azure.

License

The model is distributed under the flux-1-dev-non-commercial-license. For more details, please refer to the license documentation.