Downloads · 30 days
6
26% of all-time downloads
mju75/eva-lora-weights-dataset
eva-lora-weights-dataset is a text-to-image model from mju75. 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
26% of all-time downloads
All-time downloads
23
Public
Repo size
779 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 3va to invoke the concept.

"A cinematic shot of a futuristic cyborg 3va lounging in a neon-lit cyberpunk cafe, sipping iridescent tea amidst floating holographic displays."

"A whimsical oil painting of a tiny forest sprite 3va napping inside a dew-covered peony flower during a golden sunrise."

"An epic wide shot of a majestic stone golem 3va standing guard at the entrance of a frozen crystalline temple under a swirling aurora borealis."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("mju75/eva-lora-weights-dataset")
image = pipe("A cinematic shot of a futuristic cyborg 3va lounging in a neon-lit cyberpunk cafe, sipping iridescent tea amidst floating holographic displays.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")