metadata
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: e6gz
widget:
- text: >-
A majestic snow leopard leaping across a jagged Himalayan cliffside during
a swirling blizzard, captured in hyper-realistic detail e6gz
output:
url: sample_0.png
- text: >-
A sleek, neon-lit cyberpunk motorcycle speeding down a rain-slicked Tokyo
street at midnight with vibrant light trails e6gz
output:
url: sample_1.png
- text: >-
An elderly clockmaker meticulously repairing a golden pocket watch inside
a dusty, sun-drenched Victorian workshop e6gz
output:
url: sample_2.png
Krea 2 LoRA — Eggsbena/eggs
- Prompt
- A majestic snow leopard leaping across a jagged Himalayan cliffside during a swirling blizzard, captured in hyper-realistic detail e6gz
- Prompt
- A sleek, neon-lit cyberpunk motorcycle speeding down a rain-slicked Tokyo street at midnight with vibrant light trails e6gz
- Prompt
- An elderly clockmaker meticulously repairing a golden pocket watch inside a dusty, sun-drenched Victorian workshop e6gz
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 e6gz to invoke the concept.
Samples
"A majestic snow leopard leaping across a jagged Himalayan cliffside during a swirling blizzard, captured in hyper-realistic detail e6gz"
"A sleek, neon-lit cyberpunk motorcycle speeding down a rain-slicked Tokyo street at midnight with vibrant light trails e6gz"
"An elderly clockmaker meticulously repairing a golden pocket watch inside a dusty, sun-drenched Victorian workshop e6gz"
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("Eggsbena/eggs")
image = pipe("A majestic snow leopard leaping across a jagged Himalayan cliffside during a swirling blizzard, captured in hyper-realistic detail e6gz", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")