# import gradio as gr
#
# def greet(name):
#     return "V5 Hello " + name + "!!"
#
# iface = gr.Interface(
#     fn=greet,
#     inputs="text",
#     outputs="text",
#     title="MB TEST 1",
# )
# iface.launch(share=True)

import gradio as gr
from models import make_inpainting
import io
from PIL import Image
import numpy as np

# from transformers import pipeline
#
# pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")

def image_to_byte_array(image: Image) -> bytes:
    # BytesIO is a fake file stored in memory
    imgByteArr = io.BytesIO()
    # image.save expects a file as a argument, passing a bytes io ins
    image.save(imgByteArr, format='png')  # image.format
    # Turn the BytesIO object back into a bytes object
    imgByteArr = imgByteArr.getvalue()
    return imgByteArr

def predict(input_img1,input_img2):

    # image = Image.open(requests.get("https://applydesignblobs-chh5aahjdzh0cnew.z01.azurefd.net/spaceimages/org_sqr_7fee0869-3187-4363-b5fb-5233e943649d.png", stream=True).raw)
    # mask = Image.open(requests.get("https://applydesign.blob.core.windows.net/spaceimages/mask_e85b1585-8.png", stream=True).raw)

    result_image = make_inpainting(positive_prompt='test1',
                                   image=image_to_byte_array(input_img1),
                                   mask_image=np.array(input_img2),
                                   negative_prompt="xxx",
                                   )


    # predictions = pipeline(input_img1)
    return input_img1

gradio_app = gr.Interface(
    predict,
    inputs=[gr.Image(label="img", sources=['upload', 'webcam'], type="pil"),
            gr.Image(label="mask", sources=['upload', 'webcam'], type="pil")
            ],
    outputs= gr.Image(label="resp"),
    title="rem fur 1",
)


gradio_app.launch(share=True)