laura / README.md
kisersantine's picture
Upload README.md with huggingface_hub
6809509 verified
|
Raw History Blame Contribute Delete
1.91 kB
---
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: "Laura"
widget:
- text: "A cinematic shot of Laura as a futuristic cyberpunk hacker, surrounded by glowing neon holographic screens in a rainy Tokyo alleyway."
output:
url: sample_0.png
- text: "A dreamy oil painting of Laura wandering through a sun-drenched lavender field in Provence, wearing a flowing white linen dress."
output:
url: sample_1.png
- text: "An epic fantasy portrait of Laura as a battle-worn warrior queen, standing atop a snowy mountain peak with a dragon circling above."
output:
url: sample_2.png
---
# Krea 2 LoRA — kisersantine/laura
<Gallery />
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 `Laura` to invoke the concept.
## Samples
![sample](./sample_0.png)
> *"A cinematic shot of Laura as a futuristic cyberpunk hacker, surrounded by glowing neon holographic screens in a rainy Tokyo alleyway."*
![sample](./sample_1.png)
> *"A dreamy oil painting of Laura wandering through a sun-drenched lavender field in Provence, wearing a flowing white linen dress."*
![sample](./sample_2.png)
> *"An epic fantasy portrait of Laura as a battle-worn warrior queen, standing atop a snowy mountain peak with a dragon circling above."*
## Use it with diffusers
```py
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("kisersantine/laura")
image = pipe("A cinematic shot of Laura as a futuristic cyberpunk hacker, surrounded by glowing neon holographic screens in a rainy Tokyo alleyway.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
```