import torch
import requests
from PIL import Image
from diffusers import DiffusionPipeline, EulerAncestralDiscreteScheduler

# Load the pipeline
pipeline = DiffusionPipeline.from_pretrained(
    "sudo-ai/zero123plus-v1.1", custom_pipeline="sudo-ai/zero123plus-pipeline",
    torch_dtype=torch.float16
)

# Feel free to tune the scheduler!
# `timestep_spacing` parameter is not supported in older versions of `diffusers`
# so there may be performance degradations
# We recommend using `diffusers==0.20.2`
pipeline.scheduler = EulerAncestralDiscreteScheduler.from_config(
    pipeline.scheduler.config, timestep_spacing='trailing'
)
pipeline.to('cuda:0')

# Download an example image.
cond = Image.open(requests.get("https://d.skis.ltd/nrp/sample-data/lysol.png", stream=True).raw)

# Run the pipeline!
result = pipeline(cond, num_inference_steps=75).images[0]
# for general real and synthetic images of general objects
# usually it is enough to have around 28 inference steps
# for images with delicate details like faces (real or anime)
# you may need 75-100 steps for the details to construct

result.show()
result.save("output.png")