Instructions to use aeon37/al1ce-k2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use aeon37/al1ce-k2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("krea/Krea-2-Raw", torch_dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("aeon37/al1ce-k2") prompt = "A futuristic neon-drenched cyberpunk city street at midnight, featuring al1ce-k2 as a holographic advertisement shimmering against the rain-slicked asphalt." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Krea 2 LoRA โ aeon37/al1ce-k2

- Prompt
- A futuristic neon-drenched cyberpunk city street at midnight, featuring al1ce-k2 as a holographic advertisement shimmering against the rain-slicked asphalt.

- Prompt
- A serene, sun-dappled ancient library with floating leather-bound books, where al1ce-k2 is depicted as a marble statue overgrown with delicate ivy.

- Prompt
- A high-octane underwater coral reef scene with vibrant bioluminescent fish, showcasing al1ce-k2 encased in a sleek, pearlescent deep-sea diving suit.
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 al1ce-k2 to invoke the concept.
Samples
"A futuristic neon-drenched cyberpunk city street at midnight, featuring al1ce-k2 as a holographic advertisement shimmering against the rain-slicked asphalt."
"A serene, sun-dappled ancient library with floating leather-bound books, where al1ce-k2 is depicted as a marble statue overgrown with delicate ivy."
"A high-octane underwater coral reef scene with vibrant bioluminescent fish, showcasing al1ce-k2 encased in a sleek, pearlescent deep-sea diving suit."
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("aeon37/al1ce-k2")
image = pipe("A futuristic neon-drenched cyberpunk city street at midnight, featuring al1ce-k2 as a holographic advertisement shimmering against the rain-slicked asphalt.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
- Downloads last month
- -
Model tree for aeon37/al1ce-k2
Base model
krea/Krea-2-Raw

