metadata
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: F0WL3R woman
widget:
- text: >-
A cinematic wide shot of a F0WL3R woman standing amidst a neon-drenched
cyberpunk marketplace, wearing iridescent holographic armor under a heavy
rain.
output:
url: sample_0.png
- text: >-
A serene oil painting of a F0WL3R woman reading an ancient leather-bound
tome in a sun-drenched Victorian library filled with floating dust motes.
output:
url: sample_1.png
- text: >-
A high-action shot of a F0WL3R woman navigating a futuristic white-sand
desert on a hovering chrome surfboard, with three moons hanging in a
violet sky.
output:
url: sample_2.png
Krea 2 LoRA — aimalias/f0wl3r
- Prompt
- A cinematic wide shot of a F0WL3R woman standing amidst a neon-drenched cyberpunk marketplace, wearing iridescent holographic armor under a heavy rain.
- Prompt
- A serene oil painting of a F0WL3R woman reading an ancient leather-bound tome in a sun-drenched Victorian library filled with floating dust motes.
- Prompt
- A high-action shot of a F0WL3R woman navigating a futuristic white-sand desert on a hovering chrome surfboard, with three moons hanging in a violet sky.
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 F0WL3R woman to invoke the concept.
Samples
"A cinematic wide shot of a F0WL3R woman standing amidst a neon-drenched cyberpunk marketplace, wearing iridescent holographic armor under a heavy rain."
"A serene oil painting of a F0WL3R woman reading an ancient leather-bound tome in a sun-drenched Victorian library filled with floating dust motes."
"A high-action shot of a F0WL3R woman navigating a futuristic white-sand desert on a hovering chrome surfboard, with three moons hanging in a violet sky."
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/f0wl3r")
image = pipe("A cinematic wide shot of a F0WL3R woman standing amidst a neon-drenched cyberpunk marketplace, wearing iridescent holographic armor under a heavy rain.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")