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("Giorgebest/steffy2-30")
prompt = "A cinematic wide shot of a vqx woman wearing neon-cyberpunk armor, standing amidst the rain-slicked streets of a futuristic Tokyo metropolis with glowing holograms."
image = pipe(prompt).images[0]Krea 2 LoRA — Giorgebest/steffy2-30
- Prompt
- A cinematic wide shot of a vqx woman wearing neon-cyberpunk armor, standing amidst the rain-slicked streets of a futuristic Tokyo metropolis with glowing holograms.
- Prompt
- A serene oil painting of a vqx woman in a flowing white linen dress, reading an ancient leather book in a sun-drenched Mediterranean garden filled with blooming bougainvillea.
- Prompt
- A high-detail macro photograph of a vqx woman as an astronaut, her face reflected in a gold-tinted visor while floating in the silent, starry void of deep space.
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 vqx woman to invoke the concept.
Samples
"A cinematic wide shot of a vqx woman wearing neon-cyberpunk armor, standing amidst the rain-slicked streets of a futuristic Tokyo metropolis with glowing holograms."
"A serene oil painting of a vqx woman in a flowing white linen dress, reading an ancient leather book in a sun-drenched Mediterranean garden filled with blooming bougainvillea."
"A high-detail macro photograph of a vqx woman as an astronaut, her face reflected in a gold-tinted visor while floating in the silent, starry void of deep space."
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("Giorgebest/steffy2-30")
image = pipe("A cinematic wide shot of a vqx woman wearing neon-cyberpunk armor, standing amidst the rain-slicked streets of a futuristic Tokyo metropolis with glowing holograms.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
- Downloads last month
- 4
Model tree for Giorgebest/steffy2-30
Base model
krea/Krea-2-Raw