import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("smereces/2.1-SD-Modern-Buildings-Style-MD", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Model Trained to create a Midjourney architecture buildings style.
Used 120 images 768x768
Prompts example:
"a photo of a futuristic house with a organic facade, roots, waves, many windows, by midjourneyi"
"a photo of a parametric building midjourneyi, waves, roots, veins, many windows, in a street."
"a photo of a symmetric colored vived midjourneyi house, in a street"
Important: add negative prompts to improve the results.
Examples
license: openrail
- Downloads last month
- 9