import gradio as gr
import requests
import io
from PIL import Image
import json
import os

# Load LoRAs from JSON
with open('loras.json', 'r') as f:
    loras = json.load(f)

# API call function
def query(payload, api_url, token):
    headers = {"Authorization": f"Bearer {token}"}
    response = requests.post(api_url, headers=headers, json=payload)
    return io.BytesIO(response.content)

# Define the function to run when the button is clicked
def run_lora(prompt, weight):
    selected_lora = loras[0]
    api_url = f"https://api-inference.huggingface.co/models/{selected_lora['repo']}"
    trigger_word = selected_lora["trigger_word"]
    token = os.getenv("API_TOKEN")
    payload = {"inputs": f"{prompt} {trigger_word}"}
    image_bytes = query(payload, api_url, token)
    return Image.open(image_bytes)

# Gradio UI
print("Before Gradio Interface")

with gr.Blocks() as app:
    title = gr.HTML("<h1>LoRA the Explorer</h1>")
    gallery = gr.Gallery(
        [(item["image"], item["title"]) for item in loras],
        label="LoRA Gallery",
        allow_preview=False,
        columns=3,
    )
    prompt = gr.Textbox(label="Prompt", lines=1, max_lines=1, placeholder="Type a prompt after selecting a LoRA")
    advanced_options = gr.Accordion("Advanced options", open=False)
    weight = gr.Slider(0, 10, value=1, step=0.1, label="LoRA weight")
    result = gr.Image(interactive=False, label="Generated Image")

    with gr.Row():
        with gr.Column():
            title
            gallery
            prompt
            advanced_options
            weight
            gr.Button("Run").click(
                fn=run_lora,
                inputs=[prompt, weight],
                outputs=[result]
            )
        with gr.Column():
            result

print("After Gradio Interface")

# Launch the Gradio interface with a queue
app.launch(share=True, debug=True, queue=True)