Downloads · 30 days
8
26% of all-time downloads
aimalias/zm1x-512
zm1x-512 is a text-to-image model from aimalias. 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
8
26% of all-time downloads
All-time downloads
31
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 zm1x squeeze to invoke the concept.

"A futuristic cyberpunk city street at midnight, neon signs reflecting in puddles, where a floating robotic orb performs a zm1x squeeze on a glowing data crystal."

"A serene ancient Japanese garden during cherry blossom season, featuring a stone sculpture that applies a zm1x squeeze to a delicate silk ribbon."

"An epic cinematic shot of a deep-sea abyss, where a bioluminescent alien creature executes a zm1x squeeze on a shimmering pearl."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("aimalias/zm1x-512")
image = pipe("A futuristic cyberpunk city street at midnight, neon signs reflecting in puddles, where a floating robotic orb performs a zm1x squeeze on a glowing data crystal.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")