Instructions to use Nanami231/ruby-26-v4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Nanami231/ruby-26-v4 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("Nanami231/ruby-26-v4") prompt = "A futuristic RUBY@26 cybernetic owl perched on a neon-lit skyscraper overlooking a rainy Tokyo cityscape, cinematic lighting, 8k." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Krea 2 LoRA β Nanami231/ruby-26-v4

- Prompt
- A futuristic RUBY@26 cybernetic owl perched on a neon-lit skyscraper overlooking a rainy Tokyo cityscape, cinematic lighting, 8k.

- Prompt
- An ancient, moss-covered RUBY@26 stone idol hidden deep within a tropical jungle, sunbeams filtering through dense canopy, hyper-realistic.

- Prompt
- A delicate RUBY@26 porcelain tea set floating in zero gravity inside a luxury space station, shimmering stardust reflecting on the surface, ethereal atmosphere.
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 RUBY@26 to invoke the concept.
Samples
"A futuristic RUBY@26 cybernetic owl perched on a neon-lit skyscraper overlooking a rainy Tokyo cityscape, cinematic lighting, 8k."
"An ancient, moss-covered RUBY@26 stone idol hidden deep within a tropical jungle, sunbeams filtering through dense canopy, hyper-realistic."
"A delicate RUBY@26 porcelain tea set floating in zero gravity inside a luxury space station, shimmering stardust reflecting on the surface, ethereal atmosphere."
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("Nanami231/ruby-26-v4")
image = pipe("A futuristic RUBY@26 cybernetic owl perched on a neon-lit skyscraper overlooking a rainy Tokyo cityscape, cinematic lighting, 8k.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
- Downloads last month
- 22
Model tree for Nanami231/ruby-26-v4
Base model
krea/Krea-2-Raw

