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/character-l")

prompt = "A cinematic shot of a futuristic cyborg named Lau standing amidst a neon-drenched cyberpunk cityscape during a rainstorm."
image = pipe(prompt).images[0]

Krea 2 LoRA โ€” Wonky468/character-l

Prompt
A cinematic shot of a futuristic cyborg named Lau standing amidst a neon-drenched cyberpunk cityscape during a rainstorm.
Prompt
A whimsical oil painting of Lau as a tiny forest sprite resting on a glowing mushroom in a mystical enchanted woodland.
Prompt
A high-fashion editorial photo of Lau wearing an avant-garde gold silk gown, posing in a minimalist white marble gallery.

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 Lau to invoke the concept.

Samples

sample

"A cinematic shot of a futuristic cyborg named Lau standing amidst a neon-drenched cyberpunk cityscape during a rainstorm."

sample

"A whimsical oil painting of Lau as a tiny forest sprite resting on a glowing mushroom in a mystical enchanted woodland."

sample

"A high-fashion editorial photo of Lau wearing an avant-garde gold silk gown, posing in a minimalist white marble gallery."

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/character-l")
image = pipe("A cinematic shot of a futuristic cyborg named Lau standing amidst a neon-drenched cyberpunk cityscape during a rainstorm.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
Downloads last month
14
Inference Examples
Examples
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Wonky468/character-l

Base model

krea/Krea-2-Raw
Adapter
(51)
this model