metadata
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: B3THL1LY woman
widget:
- text: >-
A high-fashion B3THL1LY woman wearing a holographic gown, standing amidst
a neon-lit cyberpunk cityscape during a rainstorm.
output:
url: sample_0.png
- text: >-
A B3THL1LY woman dressed as a medieval scholar, reading an ancient
leather-bound tome in a sun-drenched gothic library.
output:
url: sample_1.png
- text: >-
A cinematic shot of a B3THL1LY woman in an astronaut suit, gazing at a
swirling iridescent nebula from the observation deck of a deep-space
station.
output:
url: sample_2.png
Krea 2 LoRA — aimalias/b3thl1ly-krea
- Prompt
- A high-fashion B3THL1LY woman wearing a holographic gown, standing amidst a neon-lit cyberpunk cityscape during a rainstorm.
- Prompt
- A B3THL1LY woman dressed as a medieval scholar, reading an ancient leather-bound tome in a sun-drenched gothic library.
- Prompt
- A cinematic shot of a B3THL1LY woman in an astronaut suit, gazing at a swirling iridescent nebula from the observation deck of a deep-space station.
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 B3THL1LY woman to invoke the concept.
Samples
"A high-fashion B3THL1LY woman wearing a holographic gown, standing amidst a neon-lit cyberpunk cityscape during a rainstorm."
"A B3THL1LY woman dressed as a medieval scholar, reading an ancient leather-bound tome in a sun-drenched gothic library."
"A cinematic shot of a B3THL1LY woman in an astronaut suit, gazing at a swirling iridescent nebula from the observation deck of a deep-space station."
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/b3thl1ly-krea")
image = pipe("A high-fashion B3THL1LY woman wearing a holographic gown, standing amidst a neon-lit cyberpunk cityscape during a rainstorm.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")