metadata
license: apache-2.0
pipeline_tag: text-to-image
tags:
- art
- flux
- diffusers
- lora
- replicate
language:
- en
base_model:
- black-forest-labs/FLUX.1-dev
library_name: diffusers
instance_prompt: GHIBLI
widget:
- text: >-
GHIBLI A man and a woman wearing sunglasses and smiling with beautiful
scenery all around
output:
url: image_ghibli.png
- text: GHIBLI A man getting ready to fly on his airplane
output:
url: images/example_l5bq123zn.png
Studio Ghibli Art Lora
- Prompt
- GHIBLI A man and a woman wearing sunglasses and smiling with beautiful scenery all around
- Prompt
- GHIBLI A man getting ready to fly on his airplane
Trained on Replicate using:
https://replicate.com/ostris/flux-dev-lora-trainer/train
Trigger words
You should use GHIBLI to trigger the image generation.
Use it with the 🧨 diffusers library
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('rexoscare/ghibli-artwork-lora', weight_name='lora.safetensors')
image = pipeline('your prompt').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers