metadata
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: TF0 woman
widget:
- text: >-
A TF0 woman wearing high-tech iridescent armor, standing amidst a neon-lit
cyberpunk cityscape during a heavy rainstorm.
output:
url: sample_0.png
- text: >-
A serene TF0 woman in a flowing linen dress, painting a landscape in a
sun-drenched Tuscan vineyard.
output:
url: sample_1.png
- text: >-
A cinematic shot of a TF0 woman as an astronaut, gazing through a
spaceship portal at a swirling gold and violet nebula.
output:
url: sample_2.png
Krea 2 LoRA — aimalias/tf0
- Prompt
- A TF0 woman wearing high-tech iridescent armor, standing amidst a neon-lit cyberpunk cityscape during a heavy rainstorm.
- Prompt
- A serene TF0 woman in a flowing linen dress, painting a landscape in a sun-drenched Tuscan vineyard.
- Prompt
- A cinematic shot of a TF0 woman as an astronaut, gazing through a spaceship portal at a swirling gold and violet nebula.
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 TF0 woman to invoke the concept.
Samples
"A TF0 woman wearing high-tech iridescent armor, standing amidst a neon-lit cyberpunk cityscape during a heavy rainstorm."
"A serene TF0 woman in a flowing linen dress, painting a landscape in a sun-drenched Tuscan vineyard."
"A cinematic shot of a TF0 woman as an astronaut, gazing through a spaceship portal at a swirling gold and violet nebula."
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/tf0")
image = pipe("A TF0 woman wearing high-tech iridescent armor, standing amidst a neon-lit cyberpunk cityscape during a heavy rainstorm.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")