FLUX.1-dev-LoRA-Ghibli Open-Source Model - Freely Generate Exquisite Ghibli-Style Images

FLUX.1 Dev LoRA Ghibli

Developed by InstantX

A LoRA model fine-tuned on FLUX.1-dev for generating Ghibli-style images

Text-to-Image EnglishOpen Source License:Other #Ghibli Style Generation #LoRA Fine-tuned Diffusion Model #Anime Scene Creation

Downloads 2,341

Release Time : 4/2/2025

Model Overview

This is a LoRA model fine-tuned on the FLUX.1-dev model, specifically designed to generate images with the distinctive style of Studio Ghibli. The model is activated with the trigger word 'ghibli style' and can transform text descriptions into visual content with Ghibli-style aesthetics.

Model Features

Ghibli Style Generation

Optimized specifically for the unique artistic style of Studio Ghibli, capable of generating images with its characteristic features.

LoRA Fine-tuning

Utilizes LoRA (Low-Rank Adaptation) technology for lightweight fine-tuning of the base model, maintaining performance while reducing computational resource requirements.

Safe Tensor Format

Model weights are stored in .safetensors format, providing a safer way to load the model.

Model Capabilities

Text-to-Image Generation

Art Style Transformation

High-Resolution Image Generation

Use Cases

Creative Arts

Ghibli-Style Illustration Creation

Automatically generate Ghibli-style illustrations based on text descriptions.

Produces visual content with Studio Ghibli's distinctive characteristics.

Concept Art Design

Quickly generate Ghibli-style concept art for game or animation projects.

Rapid visualization of creative concepts.

Content Creation

Social Media Content Generation

Create unique Ghibli-style visual content for social media.

Eye-catching and distinctive images.

🚀 FLUX.1-dev-LoRA-Ghibli

This project offers a Ghibli style LoRA model trained on FLUX.1-dev, enabling users to generate unique Ghibli-style images.

🚀 Quick Start

Trigger words

You should use ghibli style to trigger the image generation.

Inference

import torch
from diffusers import FluxPipeline

pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipe.load_lora_weights("InstantX/FLUX.1-dev-LoRA-Ghibli", weight_name="ghibli_style.safetensors")
pipe.fuse_lora(lora_scale=1.0)
pipe.to("cuda")

prompt = "ghibli style, a shepherd boy floating on a wooly cloud-whale, holding a glowing dandelion staff to guide sheep-shaped cumulus, miniature storm clouds grazing nearby, his patched jacket flapping in high-altitude winds, aurora-like ribbons in peach and lavender stretching across the sky"

image = pipe(prompt, 
             num_inference_steps=24, 
             guidance_scale=3.5,
             width=960, height=1280,
            ).images[0]
image.save(f"example.png")

✨ Features

Ghibli Style: Generate images in the charming Ghibli style.
Easy to Use: With simple trigger words and inference code, you can quickly start generating images.

📄 License

This project is under the flux-1-dev-non-commercial-license.

📦 Information

Property	Details
Base Model	black-forest-labs/FLUX.1-dev
Instance Prompt	The background is 4 real photos, and in the middle is a cartoon picture summarizing the real photos
Library Name	diffusers
Tags	text-to-image, stable-diffusion, lora, diffusers, image-generation, flux, safetensors

🖼️ Gallery

Example 1

Prompt: ghibli style, a boy and a girl looking out of a window with a cat perched on the window sill. There is a bicycle parked in front of them and a plant with flowers to the right side of the image. The wall behind them is visible in the background.
Output: View Image

Example 2

Prompt: ghibli style, a girl in a green cloak walking alone through an ancient forest, sunlight piercing through towering trees like stained glass, glowing pollen swirling around her boots, a rusted lantern hanging from her wooden staff, shadows of deer spirits flickering between moss-covered stones, muted emerald and gold color palette
Output: View Image

Example 3

Prompt: ghibli style, a shepherd boy floating on a wooly cloud-whale, holding a glowing dandelion staff to guide sheep-shaped cumulus, miniature storm clouds grazing nearby, his patched jacket flapping in high-altitude winds, aurora-like ribbons in peach and lavender stretching across the sky
Output: View Image

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