import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Jonjew/GhibliStyleFlux")
prompt = "Woman, Ghibli style"
image = pipe(prompt).images[0]Ghibli style Flux
- Prompt
- Woman, Ghibli style
- Prompt
- man, Ghibli style
- Prompt
- Woman, Ghibli style
Model description
FROM https://civitai.com/models/1414930/ghibli-style-flux?modelVersionId=1599234
Trigger Ghibli style
Strength 1.2
Studio Ghibli style
Illustrious version
Img2Img
[Checkpoint: wai nsfw illustrious
Denoise strength: 0.4
CFG: 7
Steps: 40
Sampler: Euler a]
FLUX Version
Img2Img
[Denoise: 0.6
Lora strength: 1.2]
Trigger words
You should use Ghibli style to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 15
Model tree for Jonjew/GhibliStyleFlux
Base model
black-forest-labs/FLUX.1-dev