movie poster ce sdxl flux LLM Model

Introduction

The "MOVIE-POSTER-CE-SDXL-FLUX" model by Keltezaa is a text-to-image diffusion model designed specifically for generating movie poster styles. It uses the FLUX.1-dev base model and includes custom LoRA weights to enhance image generation.

Architecture

The model employs the "black-forest-labs/FLUX.1-dev" as its base and integrates LoRA (Low-Rank Adaptation) techniques to refine the output styles, particularly for movie posters. It utilizes the Hugging Face Diffusers library to facilitate text-to-image generation.

Training

This model has been trained with bespoke LoRA weights, designed to capture specific artistic styles pertinent to movie posters. Users can influence the style using the trigger phrase "mvpstrCE style" to generate images with the desired aesthetic.

Guide: Running Locally

To run the model locally, follow these steps:

Set Up Environment: Ensure Python and necessary libraries are installed. You may need a virtual environment.
Install Hugging Face Diffusers:
```
pip install diffusers
```

Load the Model:

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('Keltezaa/movie-poster-ce-sdxl-flux', weight_name='MoviePoster03-02_CE_FLUX_128AIT.safetensors')

Generate an Image:

image = pipeline('Your desired prompt here. mvpstrCE style').images[0]

Suggest Cloud GPUs: For better performance, consider running on cloud environments with GPU support, such as Google Colab or AWS EC2 with GPU instances.

License

The model is licensed under a bespoke LoRA-trained license, which allows for commercial use without requiring credit and prohibits derivatives. More details can be found here.

More Related APIs in Text To Image