Instructions to use TensorVizion/PurpleRain-Krea with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use TensorVizion/PurpleRain-Krea 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("TensorVizion/PurpleRain-Krea") prompt = "A futuristic cyberpunk city street at midnight, featuring a neon-lit cyborg subject standing under a glowing umbrella in the pouring rain." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Krea 2 LoRA โ TensorVizion/purplerain

- Prompt
- A futuristic cyberpunk city street at midnight, featuring a neon-lit cyborg subject standing under a glowing umbrella in the pouring rain.

- Prompt
- A cinematic wide shot of a weathered ancient warrior resting on a mossy battlefield, with a soft, misty rain falling over the silent landscape.

- Prompt
- A cozy, high-detail interior of a Victorian library where a scholarly subject reads by a fireplace while rain streaks the large bay windows.
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 rain to invoke the concept.
Samples
"A futuristic cyberpunk city street at midnight, featuring a neon-lit cyborg subject standing under a glowing umbrella in the pouring rain."
"A cinematic wide shot of a weathered ancient warrior resting on a mossy battlefield, with a soft, misty rain falling over the silent landscape."
"A cozy, high-detail interior of a Victorian library where a scholarly subject reads by a fireplace while rain streaks the large bay windows."
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("TensorVizion/PurpleRain-Krea")
image = pipe("A futuristic cyberpunk city street at midnight, featuring a neon-lit cyborg subject standing under a glowing umbrella in the pouring rain.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
- Downloads last month
- 4
Model tree for TensorVizion/PurpleRain-Krea
Base model
krea/Krea-2-Raw

