Stable_ Diffusion_ Voxel Art_ Model

Introduction

The Stable Diffusion VoxelArt Model is a fine-tuned version of the Stable Diffusion 1.5 model, specifically trained on Voxel Art images. It allows users to generate voxel-style art by incorporating "VoxelArt" into their prompts.

Architecture

The model is built upon the Stable Diffusion framework and can be integrated with the Diffusers library. It supports export to various formats, including ONNX, MPS, and FLAX/JAX, enabling flexible deployment options.

Training

This model has been trained on a dataset of Voxel Art images to adapt the Stable Diffusion model for voxel-style outputs. Users can leverage this fine-tuned model to generate voxel art by using specific prompts.

Guide: Running Locally

To run the Stable Diffusion VoxelArt Model locally, follow these steps:

1. Install the Diffusers Library: Ensure you have the necessary libraries installed, such as diffusers and torch.
2. Load the Model: Use the following Python code to load and run the model:

   from diffusers import StableDiffusionPipeline
   import torch
   
   model_id = "Fictiverse/Stable_Diffusion_VoxelArt_Model"
   pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
   pipe = pipe.to("cuda")
   
   prompt = "VoxelArt Castle"
   image = pipe(prompt).images[0]
   
   image.save("./castle.png")
   

3. Hardware Recommendation: For optimal performance, it is recommended to use a GPU. Consider using cloud providers such as AWS, Google Cloud, or Azure that offer GPU instances.

License

The Stable Diffusion VoxelArt Model is distributed under the CreativeML OpenRAIL-M license. Users must comply with the terms and conditions specified in this license.