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("rorito/ghiblitest")
prompt = "UNICODE\u0000\u0000G\u0000h\u0000i\u0000b\u0000l\u0000i\u0000s\u0000t\u0000y\u0000l\u0000e\u0000,\u0000 \u0000o\u0000u\u0000t\u0000d\u0000o\u0000o\u0000r\u0000s\u0000,\u0000 \u0000w\u0000o\u0000l\u0000f\u0000 \u0000s\u0000t\u0000a\u0000n\u0000d\u0000i\u0000n\u0000g\u0000 \u0000o\u0000n\u0000 \u0000r\u0000o\u0000c\u0000k\u0000,\u0000 \u0000f\u0000o\u0000r\u0000e\u0000s\u0000t\u0000"
image = pipe(prompt).images[0]studio ghibli flux
- Prompt
- UNICODEGhiblistyle, outdoors, wolf standing on rock, forest
Trigger words
You should use Ghiblistyle 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
- 9
Model tree for rorito/ghiblitest
Base model
black-forest-labs/FLUX.1-dev