Buy me a coffee if you like this project ;)

Edit: Link to the project: https://huggingface.co/s3nh/zelda-botw-stable-diffusion

Arcane based Artwork Diffusion Model

I present you fine tuned model of stable-diffusion-v1-5, which heavily based of work of great artworks from Legend of Zelda: Breath of The Wild. Use the tokens botw style in your prompts for the effect.

Model was trained using the diffusers library, which based on Dreambooth implementation. Training steps included:

  • prior preservation loss
  • train-text-encoder fine tuning

🧨 Diffusers

This model can be used just like any other Stable Diffusion model. For more information, please have a look at the Stable Diffusion.

You can also export the model to ONNX, MPS and/or FLAX/JAX.

#!pip install diffusers transformers scipy torch
from diffusers import StableDiffusionPipeline
import torch
model_id = "s3nh/s3nh/zelda-botw-stable-diffusion"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "Rain forest, botw style"
image = pipe(prompt).images[0]
image.save("./example_output.png")

Gallery

Grumpy cat, botw style

Landscape, botw style

image image image image

All opinions are my own. S3nh