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/sh10r1")

prompt = "A cinematic shot of a SH10R1 woman wearing iridescent futuristic armor, standing amidst the neon-lit skyscrapers of a rainy cyberpunk metropolis."
image = pipe(prompt).images[0]

Krea 2 LoRA โ€” aimalias/sh10r1

Prompt
A cinematic shot of a SH10R1 woman wearing iridescent futuristic armor, standing amidst the neon-lit skyscrapers of a rainy cyberpunk metropolis.
Prompt
A soft, ethereal portrait of a SH10R1 woman in a flowing white linen dress, wandering through a sun-drenched wildflower meadow at golden hour.
Prompt
A high-detail macro shot of a SH10R1 woman as a deep-sea diver, surrounded by bioluminescent jellyfish and glowing coral in the midnight zone of the ocean.

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 SH10R1 woman to invoke the concept.

Samples

sample

"A cinematic shot of a SH10R1 woman wearing iridescent futuristic armor, standing amidst the neon-lit skyscrapers of a rainy cyberpunk metropolis."

sample

"A soft, ethereal portrait of a SH10R1 woman in a flowing white linen dress, wandering through a sun-drenched wildflower meadow at golden hour."

sample

"A high-detail macro shot of a SH10R1 woman as a deep-sea diver, surrounded by bioluminescent jellyfish and glowing coral in the midnight zone of the ocean."

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/sh10r1")
image = pipe("A cinematic shot of a SH10R1 woman wearing iridescent futuristic armor, standing amidst the neon-lit skyscrapers of a rainy cyberpunk metropolis.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
Downloads last month
26
Inference Examples
Examples
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for aimalias/sh10r1

Base model

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