Downloads · 30 days
7
18% of all-time downloads
temdah/krea2-temia
krea2-temia is a text-to-image model from temdah. 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
7
18% of all-time downloads
All-time downloads
40
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 Temia to invoke the concept.

"A cinematic close-up of Temia, a futuristic cyborg with iridescent plating, standing amidst the neon-drenched rain of a cyberpunk Tokyo street."

"Temia as a regal ethereal goddess, draped in flowing silk gowns, floating above a sea of glowing lotus flowers in a celestial dreamscape."

"A rustic oil painting of Temia, a rugged mountain climber in vintage gear, resting beside a crackling campfire under a vast Milky Way galaxy."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("temdah/krea2-temia")
image = pipe("A cinematic close-up of Temia, a futuristic cyborg with iridescent plating, standing amidst the neon-drenched rain of a cyberpunk Tokyo street.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")