alvarobartt/ghibli-characters-flux-lora

Studio Ghibli Characters - FLUX.1 Dev LoRA

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

Prompt

Ghibli style Shrek, a lovable green ogre with a big smile, sitting on a moss-covered rock while enjoying a plate of freshly picked vegetables, in a magical forest filled with whimsical creatures, dappled sunlight filtering through the trees, surrounded by curious fairies peeking out from behind leaves

Prompt

Ghibli style Albus Dumbledore, a wise old wizard with long silver hair and a flowing robe, standing in a lush garden filled with colorful magical plants, gently stroking a phoenix perched on his shoulder, soft morning light filtering through the trees, surrounded by whimsical creatures curiously observing him

Prompt

Ghibli style The Grinch, a mischievous green creature with a sly grin, peeking out from behind a snow-covered tree while plotting his antics, in a quaint snowy village decorated for the holidays, warm light glowing from cozy homes, with playful snowflakes dancing in the air

Prompt

Ghibli style Santa Claus, a jolly old man with a fluffy white beard and a red coat, cheerfully preparing gifts in a cozy workshop filled with magical toys, warm golden light glowing from lanterns, surrounded by adorable elves and whimsical creatures helping him

Prompt

Ghibli style Garfield, a lazy orange cat with a mischievous grin, lounging on a sunny windowsill while dreaming of lasagna, in a cozy home filled with plants and colorful decor, warm light streaming in, with a friendly mouse peeking out from behind a flower pot

Model description

This repository contains the LoRA adapter for FLUX.1-dev, fine-tuned using fal.ai/models/fal-ai/flux-lora-general-training 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]"

Inference with diffusers

import torch
from diffusers import DiffusionPipeline

model_id = "black-forest-labs/FLUX.1-dev"
adapter_id = "alvarobartt/ghibli-characters-flux-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,
    lora_scale=1.0,
).images[0]

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

Disclaimer

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

The FLUX.1-dev fine-tunes fall under the same license as FLUX.1-dev i.e. https://huggingface.co/black-forest-labs/FLUX.1-dev/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.