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("Xopen/oliviannn")
prompt = "A high-fashion cinematic portrait of olivia_n wearing a holographic gown, standing amidst a neon-lit cyberpunk cityscape during a rainstorm."
image = pipe(prompt).images[0]Krea 2 LoRA — Xopen/oliviannn
- Prompt
- A high-fashion cinematic portrait of olivia_n wearing a holographic gown, standing amidst a neon-lit cyberpunk cityscape during a rainstorm.
- Prompt
- A dreamy oil painting of olivia_n reading an ancient leather book in a sun-drenched Victorian library filled with floating dust motes.
- Prompt
- An action shot of olivia_n as a futuristic astronaut exploring a bioluminescent alien jungle with towering glowing mushrooms.
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 olivia_n to invoke the concept.
Samples
"A high-fashion cinematic portrait of olivia_n wearing a holographic gown, standing amidst a neon-lit cyberpunk cityscape during a rainstorm."
"A dreamy oil painting of olivia_n reading an ancient leather book in a sun-drenched Victorian library filled with floating dust motes."
"An action shot of olivia_n as a futuristic astronaut exploring a bioluminescent alien jungle with towering glowing mushrooms."
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("Xopen/oliviannn")
image = pipe("A high-fashion cinematic portrait of olivia_n wearing a holographic gown, standing amidst a neon-lit cyberpunk cityscape during a rainstorm.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
- Downloads last month
- 8
Model tree for Xopen/oliviannn
Base model
krea/Krea-2-Raw