al0v3 / README.md
aimalias's picture
Upload README.md with huggingface_hub
0937097 verified
|
Raw
History Blame Contribute Delete
2.03 kB
---
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: "AL0V3 woman"
widget:
- text: "A futuristic cyberpunk cityscape at night with neon signs reflecting in rain puddles, featuring a high-tech AL0V3 woman wearing iridescent chrome armor."
output:
url: sample_0.png
- text: "A serene, sun-drenched Tuscan vineyard during golden hour, where a relaxed AL0V3 woman in a white linen dress reads a leather-bound book."
output:
url: sample_1.png
- text: "An epic underwater fantasy kingdom with bioluminescent coral reefs and floating bubbles, showcasing a mystical AL0V3 woman with flowing ethereal fins."
output:
url: sample_2.png
---
# Krea 2 LoRA — aimalias/al0v3
<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 `AL0V3 woman` to invoke the concept.
## Samples
![sample](./sample_0.png)
> *"A futuristic cyberpunk cityscape at night with neon signs reflecting in rain puddles, featuring a high-tech AL0V3 woman wearing iridescent chrome armor."*
![sample](./sample_1.png)
> *"A serene, sun-drenched Tuscan vineyard during golden hour, where a relaxed AL0V3 woman in a white linen dress reads a leather-bound book."*
![sample](./sample_2.png)
> *"An epic underwater fantasy kingdom with bioluminescent coral reefs and floating bubbles, showcasing a mystical AL0V3 woman with flowing ethereal fins."*
## 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/al0v3")
image = pipe("A futuristic cyberpunk cityscape at night with neon signs reflecting in rain puddles, featuring a high-tech AL0V3 woman wearing iridescent chrome armor.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
```