Downloads · 30 days
18
25% of all-time downloads
volvoman2/krea-2-maisie
krea-2-maisie is a text-to-image model from volvoman2. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.
Downloads · 30 days
18
25% of all-time downloads
All-time downloads
72
Public
Repo size
971 MB
Likes
0
Public
Click a slice to open those files.
.safetensors576 MB · 59%
From the Hugging Face model README
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).
Use the token maisie to invoke the concept.

"A cinematic close-up of a futuristic cyborg named maisie with iridescent chrome skin, standing amidst a neon-drenched cyberpunk cityscape under a heavy rain."

"A whimsical oil painting of a tiny field mouse called maisie wearing a miniature Victorian dress, hosting a tea party inside a hollowed-out oak tree."

"A wide shot of a rugged explorer named maisie scaling a crystalline mountain peak on a distant alien planet with three glowing moons in the purple sky."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("volvoman2/krea-2-maisie")
image = pipe("A cinematic close-up of a futuristic cyborg named maisie with iridescent chrome skin, standing amidst a neon-drenched cyberpunk cityscape under a heavy rain.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")