Downloads · 30 days
5
22% of all-time downloads
Hajja/krea-glow
krea-glow is a text-to-image model from Hajja. 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
5
22% of all-time downloads
All-time downloads
23
Public
Repo size
778 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 Krea_Glow to invoke the concept.

"A majestic cybernetic tiger prowling through a neon-drenched Tokyo alleyway, its metallic fur emitting a soft Krea_Glow under the rain."

"An ancient stone golem meditating in a floating zen garden above the clouds, with golden Krea_Glow energy pulsing through its cracks."

"A delicate glass butterfly landing on a bioluminescent mushroom in a deep underwater cavern, surrounded by a shimmering Krea_Glow aura."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("Hajja/krea-glow")
image = pipe("A majestic cybernetic tiger prowling through a neon-drenched Tokyo alleyway, its metallic fur emitting a soft Krea_Glow under the rain.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")