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", torch_dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("aimalias/sw33n3y-krea")

prompt = "A sw33n3y woman wearing futuristic neon armor, standing amidst the rain-slicked streets of a cyberpunk Tokyo cityscape with glowing holographic billboards."
image = pipe(prompt).images[0]

Krea 2 LoRA โ€” aimalias/sw33n3y-retrain

Prompt
A sw33n3y woman wearing futuristic neon armor, standing amidst the rain-slicked streets of a cyberpunk Tokyo cityscape with glowing holographic billboards.
Prompt
A sw33n3y woman in a flowing white linen dress, walking through a sun-drenched lavender field in Provence during the golden hour.
Prompt
A sw33n3y woman as a galactic explorer, floating in zero gravity inside a crystalline spaceship cockpit overlooking a swirling violet nebula.

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 sw33n3y woman to invoke the concept.

Samples

sample

"A sw33n3y woman wearing futuristic neon armor, standing amidst the rain-slicked streets of a cyberpunk Tokyo cityscape with glowing holographic billboards."

sample

"A sw33n3y woman in a flowing white linen dress, walking through a sun-drenched lavender field in Provence during the golden hour."

sample

"A sw33n3y woman as a galactic explorer, floating in zero gravity inside a crystalline spaceship cockpit overlooking a swirling violet nebula."

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("aimalias/sw33n3y-retrain")
image = pipe("A sw33n3y woman wearing futuristic neon armor, standing amidst the rain-slicked streets of a cyberpunk Tokyo cityscape with glowing holographic billboards.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
Downloads last month
40
Inference Examples
Examples
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for aimalias/sw33n3y-krea

Base model

krea/Krea-2-Raw
Adapter
(254)
this model