gokceee_fluxx

Introduction

GOKCEEE_FLUXX is a text-to-image model designed to generate images from text prompts. It utilizes the capabilities of Hugging Face's Diffusers library and is enhanced with LoRA (Low-Rank Adaptation) weights for improved image generation performance.

Architecture

The model is built on the base model black-forest-labs/FLUX.1-dev and leverages the Diffusers library to convert text prompts into images. It incorporates LoRA weights, which allow for fine-tuning and adaptation to specific tasks or datasets.

Training

GOKCEEE_FLUXX was trained using the Replicate platform, specifically with the flux-dev-lora-trainer. This setup enables the use of LoRA weights to fine-tune the model's performance on the task of text-to-image generation.

Guide: Running Locally

To run the GOKCEEE_FLUXX model locally, follow these steps:

1. Install the Diffusers library and required dependencies:

   pip install diffusers torch
   

2. Load the model using the following Python code:

   from diffusers import AutoPipelineForText2Image
   import torch
   
   pipeline = AutoPipelineForText2Image.from_pretrained(
       'alvdansen/flux-koda', torch_dtype=torch.float16
   ).to('cuda')
   pipeline.load_lora_weights('codermert/gokceee_fluxx', weight_name='lora.safetensors')
   image = pipeline('your prompt').images[0]
   

3. Ensure you have a compatible GPU, such as those available on Google Colab or AWS EC2 with GPU support, to accelerate the model's performance.

For more detailed instructions on using LoRA weights with Diffusers, refer to the Diffusers documentation.

License

GOKCEEE_FLUXX is provided under the flux-1-dev-non-commercial-license. For further details about the license terms, please visit the license link.