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("Dekonstruktio/30")

prompt = "monochrome ink wash style"
image = pipe(prompt).images[0]

Krea 2 LoRA โ€” darkbrush

A LoRA for Krea 2 โ€” darkbrush (trigger: monochrome ink wash style).

  • Trigger word: monochrome ink wash style
  • To be used on: krea/Krea-2-Turbo, the few-step distilled checkpoint shown in the previews above.
  • Trained on: krea/Krea-2-Raw.
  • Weights: darkbrush.safetensors
  • Previews: rendered on Turbo at 8 steps, guidance 0.0, LoRA weight 1.0.

Usage

import torch
from diffusers import Krea2Pipeline

pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.transformer.load_lora_adapter("krea/Krea-2-LoRA-darkbrush", weight_name="darkbrush.safetensors")
pipe.transformer.set_adapters("default", weights=1.0)

prompt = "A deer grazing in the forest, monochrome ink wash style"
image = pipe(prompt, num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("darkbrush.png")
Prompt
monochrome ink wash style
Prompt
monochrome ink wash style
Prompt
monochrome ink wash style
Prompt
monochrome ink wash style
Prompt
monochrome ink wash style
Prompt
monochrome ink wash style
Prompt
monochrome ink wash style
Prompt
monochrome ink wash style
Downloads last month
104
Inference Providers NEW
Examples

Model tree for Dekonstruktio/30

Base model

krea/Krea-2-Raw
Adapter
(1,766)
this model