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("Wonky468/bearpop49")

prompt = "A cinematic wide shot of a neon-lit cyberpunk street in Tokyo, where a holographic Bearpop float hovers above a crowd of androids."
image = pipe(prompt).images[0]

Krea 2 LoRA โ€” Wonky468/bearpop49

Prompt
A cinematic wide shot of a neon-lit cyberpunk street in Tokyo, where a holographic Bearpop float hovers above a crowd of androids.
Prompt
An oil painting of a cozy Victorian library with a plush velvet armchair and a small, ornate Bearpop sculpture resting on a mahogany side table.
Prompt
A breathtaking macro photograph of a crystalline Bearpop frozen inside a shimmering glacier under the vivid colors of the Aurora Borealis.

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 Bearpop to invoke the concept.

Samples

sample

"A cinematic wide shot of a neon-lit cyberpunk street in Tokyo, where a holographic Bearpop float hovers above a crowd of androids."

sample

"An oil painting of a cozy Victorian library with a plush velvet armchair and a small, ornate Bearpop sculpture resting on a mahogany side table."

sample

"A breathtaking macro photograph of a crystalline Bearpop frozen inside a shimmering glacier under the vivid colors of the Aurora Borealis."

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("Wonky468/bearpop49")
image = pipe("A cinematic wide shot of a neon-lit cyberpunk street in Tokyo, where a holographic Bearpop float hovers above a crowd of androids.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
Downloads last month
9
Inference Examples
Examples
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Wonky468/bearpop49

Base model

krea/Krea-2-Raw
Adapter
(597)
this model