Legostyle1 5

🚀 LegoStyle1.5 Dreambooth Model

This is a fine - tuned Stable Diffusion model trained on lego set images, offering a unique lego - style image - to - image effect.

🚀 Quick Start

This LegoStyle1.5 Dreambooth model is trained with [TheLastBen's fast - DreamBooth](https://colab.research.google.com/github/TheLastBen/fast - stable - diffusion/blob/main/fast - DreamBooth.ipynb) notebook. Use the tokens LegoStyle style in your prompts to achieve the desired effect.

You can test the concept via A1111 Colab [fast - Colab - A1111](https://colab.research.google.com/github/TheLastBen/fast - stable - diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb).

Sample Image

Here is a sample picture of this concept img - to - img: 

Positive: LegoStyle style, smooth objects, high resolution
Negative: curve, circle, blurry, drawing, cartoon illustration

✨ Features

• Lego - Style Generation: Capable of generating images in a unique lego style.
• Compatibility: Can be used just like any other Stable Diffusion model.
• Export Options: The model can be exported to ONNX, MPS and/or FLAX/JAX.

💻 Usage Examples

Basic Usage

from diffusers import StableDiffusionPipeline
import torch
model_id = "sivar/legostyle1-5"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "LegoStyle style, smooth objects, high resolution"
image = pipe(prompt).images[0]
image.save("./lego.png")

📚 Documentation

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

📄 License

This model is open access and available to all, with a CreativeML OpenRAIL - M license further specifying rights and usage.

The CreativeML OpenRAIL License specifies:

1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content.
2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license.
3. You may re - distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL - M to all your users (please read the license entirely and carefully). [Please read the full license here](https://huggingface.co/spaces/CompVis/stable - diffusion - license)