How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("krea/Krea-2-Turbo", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("B4100/fantastykrea")

prompt = "-"
image = pipe(prompt).images[0]

fantasykrea

Prompt
-

Model description

dcd@rkf@ntsy. Medium shot, eye-level viewpoint, a solitary figure in a long dark cloak and wide-brimmed hat stands in the foreground slightly left of center, holding a staff and facing forward, while a lone wolf with its head lowered emerges from behind a tree trunk on the right, both positioned among a dense forest of tall, narrow, pale-barked trees extending into the background, the ground is evenly covered with a light layer that suggests bright blue snow, with vertical tree trunks dominating the environment and creating a sense of depth.

Trigger words

You should use dcd@rkf@ntsy to trigger the image generation.

Download model

Download them in the Files & versions tab.

Downloads last month
37
Inference Providers NEW
Examples

Model tree for B4100/fantastykrea

Base model

krea/Krea-2-Raw
Adapter
(1717)
this model