Instructions to use dimadand/sandra with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use dimadand/sandra 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("dimadand/sandra") prompt = "A cinematic wide shot of @sandra as a futuristic neon-clad cyberpunk hacker in a rainy Tokyo alleyway, surrounded by floating holographic screens." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Krea 2 LoRA β dimadand/sandra

- Prompt
- A cinematic wide shot of @sandra as a futuristic neon-clad cyberpunk hacker in a rainy Tokyo alleyway, surrounded by floating holographic screens.

- Prompt
- A soft, oil-painting style portrait of @sandra wearing a Victorian gown, lounging in a sun-drenched English garden filled with blooming peonies.

- Prompt
- An epic action shot of @sandra as an astral explorer floating in a vibrant nebula, wearing a sleek chrome spacesuit that reflects shimmering distant stars.
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 @sandra to invoke the concept.
Samples
"A cinematic wide shot of @sandra as a futuristic neon-clad cyberpunk hacker in a rainy Tokyo alleyway, surrounded by floating holographic screens."
"A soft, oil-painting style portrait of @sandra wearing a Victorian gown, lounging in a sun-drenched English garden filled with blooming peonies."
"An epic action shot of @sandra as an astral explorer floating in a vibrant nebula, wearing a sleek chrome spacesuit that reflects shimmering distant stars."
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("dimadand/sandra")
image = pipe("A cinematic wide shot of @sandra as a futuristic neon-clad cyberpunk hacker in a rainy Tokyo alleyway, surrounded by floating holographic screens.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
- Downloads last month
- 14
Model tree for dimadand/sandra
Base model
krea/Krea-2-Raw

