Downloads · 30 days
7
21% of all-time downloads
Matt444455/ank123
ank123 is a text-to-image model from Matt444455. 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
21% of all-time downloads
All-time downloads
34
Public
Repo size
1.9 GB
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 anka123 to invoke the concept.

"A futuristic cybernetic owl perched on a neon-lit skyscraper overlooking a rainy Tokyo cityscape, anka123, cinematic lighting, 8k resolution."

"A vintage porcelain teacup overflowing with miniature colorful wildflowers in a sun-drenched English cottage garden, anka123, soft bokeh, macro photography."

"An ancient stone temple submerged in a deep turquoise ocean with glowing jellyfish floating around the ruins, anka123, ethereal atmosphere, hyper-realistic."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("Matt444455/ank123")
image = pipe("A futuristic cybernetic owl perched on a neon-lit skyscraper overlooking a rainy Tokyo cityscape, anka123, cinematic lighting, 8k resolution.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")