openjourney

Introduction

Openjourney is an open-source, fine-tuned Stable Diffusion model developed by Prompthero using images from Midjourney. It specializes in text-to-image generation and supports various styles through prompt customization.

Architecture

Openjourney is built on the Stable Diffusion architecture and can be used with the same parameters. It includes enhancements for specific styles, such as "mdjrny-v4 style," to produce varied and creative outputs.

Training

The model has been fine-tuned on Midjourney images to enhance its ability to generate art in specific styles. It provides tools and courses for users interested in learning AI art generation and fine-tuning techniques.

Guide: Running Locally

1. Install the Required Libraries:
   Ensure you have the diffusers library and PyTorch installed. Use the following command:

   pip install diffusers torch
   

2. Load the Model:
   Use the StableDiffusionPipeline to load the Openjourney model.

   from diffusers import StableDiffusionPipeline
   import torch
   
   model_id = "prompthero/openjourney"
   pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
   pipe = pipe.to("cuda")
   

3. Generate an Image:
   Create a prompt and generate an image.

   prompt = "retro serie of different cars with different colors and shapes, mdjrny-v4 style"
   image = pipe(prompt).images[0]
   image.save("./retro_cars.png")
   

4. Hardware Recommendations:
   For optimal performance, especially when working with large models like Stable Diffusion, consider using cloud GPUs from providers like AWS, Google Cloud, or Azure.

License

Openjourney is distributed under the CreativeML OpenRAIL-M license, allowing free use with some restrictions and conditions.