metadata
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: mrtlarcana cinematic tarot style
widget:
- text: >-
mrtlarcana cinematic tarot style, the Tower struck by lightning, a tall
stone tower splitting as two figures fall, stormy night sky, full-body
wide shot
output:
url: sample_0.png
- text: >-
mrtlarcana cinematic tarot style, the Hermit on a mountain peak holding up
a glowing lantern, cloaked figure seen from behind, vast starry night,
full-body wide shot
output:
url: sample_1.png
- text: >-
mrtlarcana cinematic tarot style, the Sun, a child riding a white horse
beneath a large radiant sun, sunflowers, full-body front shot
output:
url: sample_2.png
Krea 2 LoRA — SilverWulf212/mrtlarcana
- Prompt
- mrtlarcana cinematic tarot style, the Tower struck by lightning, a tall stone tower splitting as two figures fall, stormy night sky, full-body wide shot
- Prompt
- mrtlarcana cinematic tarot style, the Hermit on a mountain peak holding up a glowing lantern, cloaked figure seen from behind, vast starry night, full-body wide shot
- Prompt
- mrtlarcana cinematic tarot style, the Sun, a child riding a white horse beneath a large radiant sun, sunflowers, full-body front shot
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 phrase mrtlarcana cinematic tarot style to invoke the concept.
Samples
"mrtlarcana cinematic tarot style, the Tower struck by lightning, a tall stone tower splitting as two figures fall, stormy night sky, full-body wide shot"
"mrtlarcana cinematic tarot style, the Hermit on a mountain peak holding up a glowing lantern, cloaked figure seen from behind, vast starry night, full-body wide shot"
"mrtlarcana cinematic tarot style, the Sun, a child riding a white horse beneath a large radiant sun, sunflowers, full-body front shot"
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("SilverWulf212/mrtlarcana")
image = pipe("mrtlarcana cinematic tarot style, the Tower struck by lightning, a tall stone tower splitting as two figures fall, stormy night sky, full-body wide shot", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")