metadata
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: Guille
widget:
- text: >-
A cinematic shot of Guille as a futuristic cyberpunk detective standing in
a rain-slicked neon alleyway, wearing a holographic trench coat.
output:
url: sample_0.png
- text: >-
A whimsical oil painting of Guille as a tiny garden sprite napping inside
the petals of a giant, glowing lotus flower.
output:
url: sample_1.png
- text: >-
An epic wide shot of Guille as a majestic astronaut exploring a
crystalline desert on a distant purple planet under three moons.
output:
url: sample_2.png
Krea 2 LoRA — guillekenzo/guille
- Prompt
- A cinematic shot of Guille as a futuristic cyberpunk detective standing in a rain-slicked neon alleyway, wearing a holographic trench coat.
- Prompt
- A whimsical oil painting of Guille as a tiny garden sprite napping inside the petals of a giant, glowing lotus flower.
- Prompt
- An epic wide shot of Guille as a majestic astronaut exploring a crystalline desert on a distant purple planet under three moons.
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 Guille to invoke the concept.
Samples
"A cinematic shot of Guille as a futuristic cyberpunk detective standing in a rain-slicked neon alleyway, wearing a holographic trench coat."
"A whimsical oil painting of Guille as a tiny garden sprite napping inside the petals of a giant, glowing lotus flower."
"An epic wide shot of Guille as a majestic astronaut exploring a crystalline desert on a distant purple planet under three moons."
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("guillekenzo/guille")
image = pipe("A cinematic shot of Guille as a futuristic cyberpunk detective standing in a rain-slicked neon alleyway, wearing a holographic trench coat.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")