sw33n3y3 / README.md
aimalias's picture
Upload README.md with huggingface_hub
c49abb2 verified
|
Raw
History Blame Contribute Delete
2.04 kB
---
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: "SW33N3Y woman"
widget:
- text: "A cinematic shot of a SW33N3Y woman wearing holographic armor, standing amidst the neon-drenched skyscrapers of a rainy cyberpunk metropolis."
output:
url: sample_0.png
- text: "A soft, ethereal portrait of a SW33N3Y woman dressed in flowing linen, gathering wildflowers in a sun-drenched Tuscan meadow during golden hour."
output:
url: sample_1.png
- text: "A high-contrast noir scene of a SW33N3Y woman in a vintage trench coat, leaning against a brick wall in a foggy 1940s London alleyway under a single streetlamp."
output:
url: sample_2.png
---
# Krea 2 LoRA — aimalias/sw33n3y3
<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 `SW33N3Y woman` to invoke the concept.
## Samples
![sample](./sample_0.png)
> *"A cinematic shot of a SW33N3Y woman wearing holographic armor, standing amidst the neon-drenched skyscrapers of a rainy cyberpunk metropolis."*
![sample](./sample_1.png)
> *"A soft, ethereal portrait of a SW33N3Y woman dressed in flowing linen, gathering wildflowers in a sun-drenched Tuscan meadow during golden hour."*
![sample](./sample_2.png)
> *"A high-contrast noir scene of a SW33N3Y woman in a vintage trench coat, leaning against a brick wall in a foggy 1940s London alleyway under a single streetlamp."*
## 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("aimalias/sw33n3y3")
image = pipe("A cinematic shot of a SW33N3Y woman wearing holographic armor, standing amidst the neon-drenched skyscrapers of a rainy cyberpunk metropolis.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
```