Downloads · 30 days
6
11% of all-time downloads
aimalias/t355a-krea
t355a-krea is a text-to-image model from aimalias. 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
6
11% of all-time downloads
All-time downloads
56
Public
Repo size
2.3 GB
Likes
0
Public
Click a slice to open those files.
.safetensors1.3 GB · 53%
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 T3554 woman to invoke the concept.

"A cinematic wide shot of a T3554 woman in a shimmering silver space suit standing on the neon-lit dunes of a futuristic Martian colony."

"A moody, oil painting style portrait of a T3554 woman wearing a Victorian lace gown, reading a leather-bound book in a candlelit gothic library."

"A vibrant, high-action shot of a T3554 woman in professional hiking gear summiting a jagged snow-capped peak during a golden hour sunrise."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("aimalias/t3554")
image = pipe("A cinematic wide shot of a T3554 woman in a shimmering silver space suit standing on the neon-lit dunes of a futuristic Martian colony.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")