Cyberpunk Anime Diffusion

Introduction

Cyberpunk Anime Diffusion is an AI model designed to generate cyberpunk anime characters. It is based on a finetuned version of the Waifu Diffusion V1.3 Model with Stable Diffusion V1.5, utilizing Dreambooth for training. This model can be used to create high-quality, anime-style images with intricate details.

Architecture

The model is compatible with Stable Diffusion pipelines and can be used with both .ckpt and Diffuser model files. It supports conversions to ONNX, MPS, and FLAX/JAX for optimization and performance improvements.

Training

The model was trained using Dreambooth, a popular technique for finetuning AI models, to enhance the capabilities of the original Waifu Diffusion V1.3. It leverages the updated VAE from Stable Diffusion V1.5 to improve the quality and detail of the generated images.

Guide: Running Locally

To run the model locally, follow these steps:

1. Install the required libraries:

   pip install diffusers transformers scipy torch
   

2. Load the model using the following Python code:

   from diffusers import StableDiffusionPipeline
   import torch
   
   model_id = "DGSpitzer/Cyberpunk-Anime-Diffusion"
   pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
   pipe = pipe.to("cuda")
   
   prompt = "a beautiful perfect face girl in dgs illustration style, Anime fine details portrait of school girl in front of modern tokyo city landscape on the background deep bokeh, anime masterpiece, 8k, sharp high quality anime"
   image = pipe(prompt).images[0]
   
   image.save("./cyberpunk_girl.png")
   

3. It is recommended to use cloud GPUs for better performance, such as those available from AWS, Google Cloud, or Microsoft Azure.

License

The usage of this model implies acceptance of the CreativeML Open RAIL-M license. This license outlines the permissions and restrictions associated with using the model and its outputs.