Ghibli Diffusion

🚀 Ghibli Diffusion

This project presents a fine - tuned Stable Diffusion model. It's trained on images from modern anime feature films of Studio Ghibli. By using the token ghibli style in your prompts, you can achieve a unique visual effect.

✨ Features

• Stable Diffusion: Leveraging the power of Stable Diffusion for high - quality image generation.
• Text - to - Image and Image - to - Image: Capable of generating images from text descriptions and modifying existing images.
• Ghibli Style: Infusing the charm of Studio Ghibli's modern anime into the generated images.

🚀 Quick Start

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 = "nitrosocke/Ghibli-Diffusion"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "ghibli style magical princess with golden hair"
image = pipe(prompt).images[0]

image.save("./magical_princess.png")

Advanced Usage

You can adjust various parameters to get different results. For example, here are the prompt and settings for the Strom Trooper:

**ghibli style (storm trooper) Negative prompt: (bad anatomy)**
_Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 3450349066, Size: 512x704_

And for the VW Beetle:

**ghibli style VW beetle Negative prompt: soft blurry**
_Steps: 30, Sampler: Euler a, CFG scale: 7, Seed: 1529856912, Size: 704x512_

Visual Samples

Characters rendered with the model: Cars and Animals rendered with the model: Landscapes rendered with the model: ghibli style beautiful Caribbean beach tropical (sunset) - Negative prompt: soft blurry ghibli style ice field white mountains ((northern lights)) starry sky low horizon - Negative prompt: soft blurry

🔧 Technical Details

This model was trained using the diffusers based dreambooth training by ShivamShrirao. It used prior - preservation loss and the train - text - encoder flag in 15,000 steps.

📄 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

💡 Usage Tip

If you enjoy the author's work and want to test new models before release, you can consider supporting the author.