Downloads · 30 days
24
44% of all-time downloads
TensorVizion/VexKrea
VexKrea is a text-to-image model from TensorVizion. 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
24
44% of all-time downloads
All-time downloads
54
Public
Repo size
392 MB
Likes
0
Public
Click a slice to open those files.
.safetensors288 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 score_4 to invoke the concept.

"A futuristic cyborg samurai standing in the middle of a neon-drenched Tokyo street during a rainstorm, cinematic lighting, score_4."

"A whimsical miniature village built inside a giant hollowed-out pumpkin, soft golden hour sunlight filtering through the walls, score_4."

"An ancient stone temple floating amidst a sea of swirling cosmic nebulae and sparkling stardust, ethereal atmosphere, score_4."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("TensorVizion/toucanflux")
image = pipe("A futuristic cyborg samurai standing in the middle of a neon-drenched Tokyo street during a rainstorm, cinematic lighting, score_4.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")