Ghibli Flux Cartoon LoRA

🚀 Ghibli-Cartoon-Art

This project offers a LoRA model for generating Ghibli-style cartoon art. It provides specific image processing parameters, optimal dimensions for inference, and easy - to - follow setup steps to help users generate high - quality Ghibli - style images.

🚀 Quick Start

Environment Setup

import torch
from pipelines import DiffusionPipeline

base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)

lora_repo = "strangerzonehf/Ghibli-Flux-Cartoon-LoRA"
trigger_word = "Ghibli Art"  
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)

Image Generation

You should use Ghibli Art to trigger the image generation.

✨ Features

• Ghibli - Style Image Generation: Generate various Ghibli - style cartoon images, such as scenes of fishermen, bookstores, and kittens.
• Customizable Parameters: Offers a series of image processing parameters for users to adjust according to their needs.
• Optimal Inference Dimensions: Provides recommended dimensions and aspect ratios for better inference results.

📦 Installation

The weights for this model are available in Safetensors format. You can Download them in the Files & versions tab.

💻 Usage Examples

Basic Usage

import torch
from pipelines import DiffusionPipeline

base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)

lora_repo = "strangerzonehf/Ghibli-Flux-Cartoon-LoRA"
trigger_word = "Ghibli Art"  
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)

# Generate an image
prompt = f"{trigger_word}, A beautiful landscape"
image = pipe(prompt).images[0]
image.save("generated_image.png")

Advanced Usage

# Advanced usage can adjust more parameters, such as inference steps
import torch
from pipelines import DiffusionPipeline

base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)

lora_repo = "strangerzonehf/Ghibli-Flux-Cartoon-LoRA"
trigger_word = "Ghibli Art"  
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)

# Set advanced parameters
prompt = f"{trigger_word}, A magical forest"
num_inference_steps = 35  # Adjust inference steps
image = pipe(prompt, num_inference_steps=num_inference_steps).images[0]
image.save("advanced_generated_image.png")

📚 Documentation

Model Description