Downloads · 30 days
71
100% of all-time downloads
Saref123/krea-ade1
krea-ade1 is a text-to-image model from Saref123. 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
71
100% of all-time downloads
All-time downloads
71
Public
Repo size
971 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 krea-ade1 to invoke the concept.

"A futuristic cyborg samurai standing in a neon-drenched cyberpunk alleyway under heavy rain, krea-ade1, cinematic lighting and hyper-realistic reflections."

"A whimsical tea party hosted by a fluffy red panda in a sun-dappled enchanted forest with floating lanterns, krea-ade1, soft pastel colors and ethereal atmosphere."

"A colossal ancient stone temple carved into a frozen Arctic cliffside during a vivid aurora borealis, krea-ade1, epic scale and intricate architectural detail."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("Saref123/krea-ade1")
image = pipe("A futuristic cyborg samurai standing in a neon-drenched cyberpunk alleyway under heavy rain, krea-ade1, cinematic lighting and hyper-realistic reflections.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")