Downloads · 30 days
16
64% of all-time downloads
lloydchristmas1231/halraul
halraul is a text-to-image model from lloydchristmas1231. 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
16
64% of all-time downloads
All-time downloads
25
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 halraul to invoke the concept.

"A futuristic cyberpunk city street drenched in neon rain, featuring a floating halraul robot serving holographic drinks to crowds. High-contrast cinematic lighting, 8k resolution."

"A serene ancient Japanese garden during cherry blossom season, where a mystical halraul creature rests beside a koi pond. Soft pastel colors, ethereal atmosphere, ukiyo-e style."

"An epic wide shot of a desolate Martian colony under a crimson sky, showcasing a massive halraul mining rig excavating glowing crystals. Industrial sci-fi aesthetic, hyper-realistic textures."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("lloydchristmas1231/halraul")
image = pipe("A futuristic cyberpunk city street drenched in neon rain, featuring a floating halraul robot serving holographic drinks to crowds. High-contrast cinematic lighting, 8k resolution.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")