How to use from the
Use from the
Diffusers library
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("lloydchristmas1231/vanab-claude")

prompt = "A futuristic cyberpunk cityscape where a glowing vanab floats through neon-lit rain, reflecting iridescent lights on metallic surfaces."
image = pipe(prompt).images[0]

Krea 2 LoRA β€” lloydchristmas1231/vanab-claude

Prompt
A futuristic cyberpunk cityscape where a glowing vanab floats through neon-lit rain, reflecting iridescent lights on metallic surfaces.
Prompt
A serene ancient library with floating scrolls and sunbeams illuminating a weathered stone vanab resting on a velvet pedestal.
Prompt
An underwater coral kingdom featuring a translucent, bioluminescent vanab swimming alongside shimmering schools of tropical fish.

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 vanab to invoke the concept.

Samples

sample

"A futuristic cyberpunk cityscape where a glowing vanab floats through neon-lit rain, reflecting iridescent lights on metallic surfaces."

sample

"A serene ancient library with floating scrolls and sunbeams illuminating a weathered stone vanab resting on a velvet pedestal."

sample

"An underwater coral kingdom featuring a translucent, bioluminescent vanab swimming alongside shimmering schools of tropical fish."

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("lloydchristmas1231/vanab-claude")
image = pipe("A futuristic cyberpunk cityscape where a glowing vanab floats through neon-lit rain, reflecting iridescent lights on metallic surfaces.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
Downloads last month
37
Inference Examples
Examples
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for lloydchristmas1231/vanab-claude

Base model

krea/Krea-2-Raw
Adapter
(1,196)
this model