app.py

import gradio as gr
import torch
from PIL import Image
from diffusers import DiffusionPipeline
import numpy as np

multi_view_diffusion_pipeline = DiffusionPipeline.from_pretrained(
    "2gnak/multi-view-diffusion-demo",
    custom_pipeline="dylanebert/multi-view-diffusion",
    torch_dtype=torch.float16,
    trust_remote_code=True,
).to("cpu")

def run(image):
  image = np.array(image, dtype=np.float32) / 255.0
  images = multi_view_diffusion_pipeline("", image, guidance_scale=5, num_inference_steps=30, elevation=0)

  images = [Image.fromarray((img * 255).astype("uint8")) for img in images]

  width, height = images[0].size
  grid_img = Image.new("RGB", (2 * width, 2 * height))

  grid_img.paste(images[0], (0, 0))
  grid_img.paste(images[1], (width, 0))
  grid_img.paste(images[2], (0, height))
  grid_img.paste(images[3], (width, height))

  return grid_img

demo = gr.Interface(fn=run, inputs="image", outputs="image")
demo.launch()