Ghibli-characters-sd3.5-lora Open Source Model - Free to Generate Images in the Style of Studio Ghibli

Ghibli Characters Sd3.5 Lora

Developed by alvarobartt

This is a LoRA adapter based on the StableDiffusion 3.5 large model, specifically designed for generating images in the Ghibli Studio style.

Image Generation Open Source License:Other #Ghibli-style generation #Anime character customization #LoRA fine-tuning adaptation

Downloads 79

Release Time : 10/23/2024

Model Overview

This model uses LoRA fine-tuning technology to enable the StableDiffusion 3.5 large model to generate images with the distinctive Ghibli Studio style, particularly suitable for creating anime-style characters and scenes.

Model Features

Ghibli-style generation

Fine-tuned specifically to generate images with the distinctive characteristics of Ghibli Studio

LoRA adapter

Uses lightweight LoRA technology to fine-tune the base model, adding specific styles while preserving the original model's capabilities

Structured prompt templates

Provides optimized prompt templates to help users better describe the desired Ghibli-style images

Model Capabilities

Text-to-image generation

Stylized image generation

Anime character creation

Use Cases

Art creation

Ghibli-style character design

Generate original characters in the Ghibli Studio style based on text descriptions

Examples showcase a Ghibli-style version of a futuristic stormtrooper

Scene creation

Generate fantasy scenes and environments with Ghibli characteristics

Personal entertainment

Personalized character creation

Users can create their imagined characters in the Ghibli style

🚀 Studio Ghibli Characters - SD 3.5 Large LoRA

This project offers a LoRA adapter for StableDiffusion 3.5 Large, enabling the generation of Studio Ghibli - style images.

📚 Documentation

Model Information

Property	Details
Base Model	stabilityai/stable-diffusion-3.5-large
Library Name	diffusers
Tags	text-to-image, diffusers-training, diffusers, lora, sd3.5, sd3.5-diffusers, template:sd-lora, endpoints-template
Instance Prompt	Ghibli style [character description] with [distinctive features], [action or pose], [environment or background], [lighting or atmosphere], [additional details]
License	other
License Name	stabilityai-ai-community
License Link	https://huggingface.co/stabilityai/stable-diffusion-3.5-large/blob/main/LICENSE.md
Datasets	alvarobartt/ghibli-characters
Pipeline Tag	text-to-image

Model description

This repository contains the LoRA adapter for StableDiffusion 3.5 Large, fine - tuned using Diffusers + Dreambooth with Studio Ghibli images free - to - use downloaded manually from https://ghibli.jp and hosted at alvarobartt/ghibli-characters.

Prompt Template

You should use the following template (defined when annotating the images with the captions) to trigger the image generation:

"Ghibli style [character description] with [distinctive features], [action or pose], [environment or background], [lighting or atmosphere], [additional details]"

💻 Usage Examples

Basic Usage

import torch
from diffusers import DiffusionPipeline

model_id = "stabilityai/stable-diffusion-3.5-large"
adapter_id = "alvarobartt/ghibli-characters-sd3.5-lora"

pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
pipeline.load_lora_weights(adapter_id)
pipeline.to("cuda")

prompt = (
    "Ghibli style futuristic stormtrooper with glossy white armor and a sleek helmet,"
    " standing heroically on a lush alien planet, vibrant flowers blooming around, soft"
    " sunlight illuminating the scene, a gentle breeze rustling the leaves"
)

image = pipeline(
    prompt=prompt,
    num_inference_steps=30,
    width=1024,
    height=768,
    guidance_scale=3.5,
).images[0]

image.save("ghibli.png", format="PNG")

Important Note

⚠️ Important Note

Requires diffusers 0.31.0 or higher, see the release notes.

📄 License

This fine - tune is for personal - use only, with no - commercial purposes as stated within the licensing.

The StableDiffusion 3.5 Large fine - tunes fall under the same license as StableDiffusion 3.5 Large i.e. https://huggingface.co/stabilityai/stable-diffusion-3.5-large/blob/main/LICENSE.md; and the Studio Ghibli dataset is released with a custom non - commercial license based on the interpretation of the findings on their website.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご