Instructions to use Nanico/take4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Nanico/take4 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("Nanico/take4") prompt = "A futuristic neon cyberpunk cityscape where a floating bbm holographic display illuminates the rainy streets." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Krea 2 LoRA โ Nanico/take4

- Prompt
- A futuristic neon cyberpunk cityscape where a floating bbm holographic display illuminates the rainy streets.

- Prompt
- A serene ancient Japanese garden with a weathered stone bbm sculpture resting beside a koi pond.

- Prompt
- A maximalist galactic nebula where a crystalline bbm artifact drifts among swirling gold stardust.
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 bbm to invoke the concept.
Samples
"A futuristic neon cyberpunk cityscape where a floating bbm holographic display illuminates the rainy streets."
"A serene ancient Japanese garden with a weathered stone bbm sculpture resting beside a koi pond."
"A maximalist galactic nebula where a crystalline bbm artifact drifts among swirling gold stardust."
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("Nanico/take4")
image = pipe("A futuristic neon cyberpunk cityscape where a floating bbm holographic display illuminates the rainy streets.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
- Downloads last month
- 12
Model tree for Nanico/take4
Base model
krea/Krea-2-Raw

