Downloads · 30 days
17
26% of all-time downloads
Elle-Opp/dzq-lora-krea2
dzq-lora-krea2 is a text-to-image model from Elle-Opp. 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
17
26% of all-time downloads
All-time downloads
66
Public
Repo size
2.1 GB
Likes
1
Trending 1
Click a slice to open those files.
.safetensors1.2 GB · 54%
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 邓紫棋 to invoke the concept.

"A cinematic wide shot of 邓紫棋 performing on a floating crystalline stage amidst a swirling cosmic nebula, surrounded by shimmering stardust and vibrant galactic gases."

"A cozy, hyper-realistic close-up of 邓紫棋 reading a vintage book in a rain-streaked Parisian cafe, with warm amber lighting and soft bokeh city lights in the background."

"An epic fantasy portrait of 邓紫棋 as a warrior queen in ornate gold armor, standing atop a jagged mountain peak during a dramatic lightning storm."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("Elle-Opp/dzq-lora-krea2")
image = pipe("A cinematic wide shot of 邓紫棋 performing on a floating crystalline stage amidst a swirling cosmic nebula, surrounded by shimmering stardust and vibrant galactic gases.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")