Instructions to use Wonky468/luna with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Wonky468/luna 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", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Wonky468/luna") prompt = "A futuristic cyberpunk city drenched in neon rain, where a bioluminescent cat named Luna leaps across floating holographic billboards." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Krea 2 LoRA โ Wonky468/luna

- Prompt
- A futuristic cyberpunk city drenched in neon rain, where a bioluminescent cat named Luna leaps across floating holographic billboards.

- Prompt
- A serene, sun-drenched Mediterranean balcony overlooking a turquoise sea, featuring a vintage porcelain tea set and a sleeping white rabbit called Luna.

- Prompt
- An epic cinematic shot of a gothic cathedral ruins under a blood-red eclipse, with a mysterious sorceress named Luna casting a swirling galaxy of gold sparks.
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 Luna to invoke the concept.
Samples
"A futuristic cyberpunk city drenched in neon rain, where a bioluminescent cat named Luna leaps across floating holographic billboards."
"A serene, sun-drenched Mediterranean balcony overlooking a turquoise sea, featuring a vintage porcelain tea set and a sleeping white rabbit called Luna."
"An epic cinematic shot of a gothic cathedral ruins under a blood-red eclipse, with a mysterious sorceress named Luna casting a swirling galaxy of gold sparks."
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("Wonky468/luna")
image = pipe("A futuristic cyberpunk city drenched in neon rain, where a bioluminescent cat named Luna leaps across floating holographic billboards.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
- Downloads last month
- 32
Model tree for Wonky468/luna
Base model
krea/Krea-2-Raw

