Downloads · 30 days
7
18% of all-time downloads
xpamelax/pamall-krea2-hf
pamall-krea2-hf is a text-to-image model from xpamelax. 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
970 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 vlk woman to invoke the concept.

"A cinematic shot of a vlk woman wearing iridescent armor, standing amidst a neon-drenched cyberpunk cityscape during a rainstorm."

"An oil painting of a vlk woman in flowing linen robes, reading an ancient leather-bound tome in a sunlit medieval library."

"A macro photography shot of a tiny vlk woman exploring a lush jungle of giant mushrooms and glowing flora in a fantasy realm."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("xpamelax/pamall-krea2-hf")
image = pipe("A cinematic shot of a vlk woman wearing iridescent armor, standing amidst a neon-drenched cyberpunk cityscape during a rainstorm.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")