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

ldm = DiffusionPipeline.from_pretrained("fusing/latent-diffusion-text2im-large")

generator = torch.manual_seed(42)

prompt = "A painting of a squirrel eating a burger"
image = ldm([prompt], generator=generator, eta=0.3, guidance_scale=6.0, num_inference_steps=50)

image_processed = image.cpu().permute(0, 2, 3, 1)
image_processed = image_processed  * 255.
image_processed = image_processed.numpy().astype(np.uint8)
image_pil = PIL.Image.fromarray(image_processed[0])

# save image
image_pil.save("test.png")
    
def greet(name):
    return "Hello " + name + "!!"

iface = gr.Interface(fn=greet, inputs="text", outputs="text")
iface.launch()