import gradio_client
from gradio_client import Client, file
from urllib.parse import quote
from huggingface_hub import InferenceClient
import numpy as np
import gradio as gr


# Use a pipeline as a high-level helper
from transformers import pipeline
#from optimum.onnxruntime import pipeline
pipe = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")
def generate_img(prompt):


    return client.text_to_image(prompt)

def pollinations_url_seedless(a, width=512, height=512):
        urlprompt=quote(str(a))
        url=f"https://image.pollinations.ai/prompt/{urlprompt}?width={width}&height={height}"
        return url

def interrogate(img):

    result = pipe(img)
    return result['generated_text']
def rountrip(img):
    prompt=interrogate(img)
    print(prompt)
    url=pollinations_url_seedless(prompt)
    return generate_img(prompt),prompt,url

demo = gr.Interface(rountrip, gr.Image(type= 'filepath'),[gr.Image(type= 'filepath'),"textbox",gr.Image(label="pollination")])
demo.launch()