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-Raw", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("kisersantine/darleen")

prompt = "A cinematic wide shot of Darleen, a futuristic cybernetic explorer, standing on the neon-soaked docks of a floating city in a rainy cyberpunk dystopia."
image = pipe(prompt).images[0]

Krea 2 LoRA β€” kisersantine/darleen

Prompt
A cinematic wide shot of Darleen, a futuristic cybernetic explorer, standing on the neon-soaked docks of a floating city in a rainy cyberpunk dystopia.
Prompt
A soft, ethereal oil painting of Darleen as a Victorian botanist tending to glowing, iridescent flora inside a sun-drenched glass conservatory.
Prompt
A high-action sports photograph of Darleen competing in a high-stakes galactic hover-race, trailing streaks of blue plasma through a jagged asteroid field.

A DreamBooth-LoRA for Krea 2, trained on Krea 2 RAW and shown on Krea 2 Turbo. The samples below were generated with this LoRA on Turbo (8 steps).

Trigger

Use the token Darleen to invoke the concept.

Samples

sample

"A cinematic wide shot of Darleen, a futuristic cybernetic explorer, standing on the neon-soaked docks of a floating city in a rainy cyberpunk dystopia."

sample

"A soft, ethereal oil painting of Darleen as a Victorian botanist tending to glowing, iridescent flora inside a sun-drenched glass conservatory."

sample

"A high-action sports photograph of Darleen competing in a high-stakes galactic hover-race, trailing streaks of blue plasma through a jagged asteroid field."

Use it with diffusers

import torch
from diffusers import Krea2Pipeline

pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("kisersantine/darleen")
image = pipe("A cinematic wide shot of Darleen, a futuristic cybernetic explorer, standing on the neon-soaked docks of a floating city in a rainy cyberpunk dystopia.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
Downloads last month
15
Inference Examples
Examples
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for kisersantine/darleen

Base model

krea/Krea-2-Raw
Adapter
(1,291)
this model