Tardisfusion

🚀 TARDISfusion

TARDISfusion is a Dreamboothed Stable Diffusion model trained on 3 style concepts, enabling text-to-image and image-to-image generation.

🚀 Quick Start

TARDISfusion is a Dreamboothed Stable Diffusion model trained on 3 Style concepts. The total dataset consists of 209 pictures, and the training was conducted on runawayml 1.5 with 2500 steps and the new VAE.

The following tokens will add their corresponding concept:

• Classic Tardis style: Architectural and furniture style seen inside the TARDIS in the series before the reboot.
• Modern Tardis style: Architectural and furniture style seen inside the TARDIS in the series after the reboot.
• Tardis Box style: A style made from the TARDIS seen from the outside. Summons a TARDIS anywhere.

CKPT download link

✨ Features

• Multiple Style Concepts: Incorporates Classic Tardis style, Modern Tardis style, and Tardis Box style.
• Versatile Usage: Can be used for text - to - image and image - to - image generation.
• Exportable: Can be exported to ONNX, MPS, and/or FLAX/JAX.

📦 Installation

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.

💻 Usage Examples

Basic Usage

from diffusers import StableDiffusionPipeline
import torch

model_id = "Guizmus/Tardisfusion"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "a bedroom, Classic Tardis style"
image = pipe(prompt).images[0]

image.save("./TARDIS Style.png")

📄 License

This model is licensed under the creativeml - openrail - m license.