metadata
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: digital cel shaded style
widget:
- text: >-
A majestic snow leopard leaping across a jagged mountain peak under a
brilliant turquoise sky, digital cel shaded style
output:
url: sample_0.png
- text: >-
A futuristic neon-lit hovercar speeding down a rainy Tokyo highway at
midnight, digital cel shaded style
output:
url: sample_1.png
- text: >-
A cozy attic library with golden sunlight streaming through a circular
window onto stacks of ancient books, digital cel shaded style
output:
url: sample_2.png
Krea 2 LoRA — FresherDifference/hundo-reigns
- Prompt
- A majestic snow leopard leaping across a jagged mountain peak under a brilliant turquoise sky, digital cel shaded style
- Prompt
- A futuristic neon-lit hovercar speeding down a rainy Tokyo highway at midnight, digital cel shaded style
- Prompt
- A cozy attic library with golden sunlight streaming through a circular window onto stacks of ancient books, digital cel shaded style
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 digital cel shaded style to invoke the concept.
Samples
"A majestic snow leopard leaping across a jagged mountain peak under a brilliant turquoise sky, digital cel shaded style"
"A futuristic neon-lit hovercar speeding down a rainy Tokyo highway at midnight, digital cel shaded style"
"A cozy attic library with golden sunlight streaming through a circular window onto stacks of ancient books, digital cel shaded style"
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("FresherDifference/hundo-reigns")
image = pipe("A majestic snow leopard leaping across a jagged mountain peak under a brilliant turquoise sky, digital cel shaded style", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")