import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Efficient-Large-Model/pi3x-intrinsics-estimator", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Pi3X intrinsics estimator
A remote modular block that estimates
camera intrinsics [fx, fy, cx, cy] for a single image using Pi3X, for use with
SanaWMPipeline.
import torch
from diffusers import ModularPipeline
from diffusers.utils import load_image
estimator = ModularPipeline.from_pretrained(
"Efficient-Large-Model/pi3x-intrinsics-estimator", trust_remote_code=True
)
estimator.load_components(dtype=torch.bfloat16)
intrinsics = estimator(image=load_image("input.png"), output="intrinsics")
Requires pip install pi3-vision torchvision.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support