metadata
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: K4TD woman
widget:
- text: >-
A K4TD woman wearing futuristic neon armor, standing in the middle of a
rain-slicked cyberpunk street filled with glowing holographic
advertisements.
output:
url: sample_0.png
- text: >-
A K4TD woman in a flowing linen dress, reading an ancient leather-bound
book within a sun-drenched Mediterranean garden overgrown with white
bougainvillea.
output:
url: sample_1.png
- text: >-
A K4TD woman as a deep-sea explorer, wearing a high-tech diving suit and
swimming alongside bioluminescent jellyfish in a dark, shimmering oceanic
abyss.
output:
url: sample_2.png
Krea 2 LoRA — aimalias/k4t
- Prompt
- A K4TD woman wearing futuristic neon armor, standing in the middle of a rain-slicked cyberpunk street filled with glowing holographic advertisements.
- Prompt
- A K4TD woman in a flowing linen dress, reading an ancient leather-bound book within a sun-drenched Mediterranean garden overgrown with white bougainvillea.
- Prompt
- A K4TD woman as a deep-sea explorer, wearing a high-tech diving suit and swimming alongside bioluminescent jellyfish in a dark, shimmering oceanic abyss.
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 K4TD woman to invoke the concept.
Samples
"A K4TD woman wearing futuristic neon armor, standing in the middle of a rain-slicked cyberpunk street filled with glowing holographic advertisements."
"A K4TD woman in a flowing linen dress, reading an ancient leather-bound book within a sun-drenched Mediterranean garden overgrown with white bougainvillea."
"A K4TD woman as a deep-sea explorer, wearing a high-tech diving suit and swimming alongside bioluminescent jellyfish in a dark, shimmering oceanic abyss."
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("aimalias/k4t")
image = pipe("A K4TD woman wearing futuristic neon armor, standing in the middle of a rain-slicked cyberpunk street filled with glowing holographic advertisements.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")