metadata
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: model-Risa-krea2
widget:
- text: >-
A high-fashion editorial shot of model-Risa-krea2 wearing a shimmering
holographic gown, standing amidst a neon-lit futuristic Tokyo street
during a rainy night.
output:
url: sample_0.png
- text: >-
A serene cinematic portrait of model-Risa-krea2 dressed in rustic linen
attire, foraging for wildflowers in a sun-drenched Tuscan meadow at golden
hour.
output:
url: sample_1.png
- text: >-
An atmospheric action shot of model-Risa-krea2 as a cyberpunk mercenary,
equipped with glowing tactical gear inside a gritty, smoke-filled
industrial warehouse.
output:
url: sample_2.png
Krea 2 LoRA — misapapa71/model-risa-krea2
- Prompt
- A high-fashion editorial shot of model-Risa-krea2 wearing a shimmering holographic gown, standing amidst a neon-lit futuristic Tokyo street during a rainy night.
- Prompt
- A serene cinematic portrait of model-Risa-krea2 dressed in rustic linen attire, foraging for wildflowers in a sun-drenched Tuscan meadow at golden hour.
- Prompt
- An atmospheric action shot of model-Risa-krea2 as a cyberpunk mercenary, equipped with glowing tactical gear inside a gritty, smoke-filled industrial warehouse.
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 model-Risa-krea2 to invoke the concept.
Samples
"A high-fashion editorial shot of model-Risa-krea2 wearing a shimmering holographic gown, standing amidst a neon-lit futuristic Tokyo street during a rainy night."
"A serene cinematic portrait of model-Risa-krea2 dressed in rustic linen attire, foraging for wildflowers in a sun-drenched Tuscan meadow at golden hour."
"An atmospheric action shot of model-Risa-krea2 as a cyberpunk mercenary, equipped with glowing tactical gear inside a gritty, smoke-filled industrial warehouse."
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("misapapa71/model-risa-krea2")
image = pipe("A high-fashion editorial shot of model-Risa-krea2 wearing a shimmering holographic gown, standing amidst a neon-lit futuristic Tokyo street during a rainy night.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")