import gradio as gr
import modin.pandas as pd
import torch
from PIL import Image
import imageio
from diffusers import DiffusionPipeline
from huggingface_hub import login

device = "cuda" if torch.cuda.is_available() else "cpu"
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", torch_dtype=torch.float16) if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0")
pipe = pipe.to(device)

def resize(value,img):
    img = Image.open(img)
    img = img.resize((value,value))
    return img

def infer(source_img, prompt, negative_prompt, guide, steps, seed):
    generator = torch.Generator(device).manual_seed(seed) 
    imageio.imwrite("data.png", source_img)
    src = resize(768, 'data.png')
    image = pipe(prompt, negative_prompt=negative_prompt, image=src, strength=1, guidance_scale=guide, num_inference_steps=steps).images[0]
    return image

gr.Interface(fn=infer, inputs=[gr.Image(type='numpy', source='canvas'), gr.Textbox(label = 'Prompt Input Text. 77 Token (Keyword or Symbol) Maximum'), gr.Textbox(label='What you Do Not want the AI to generate.'),
    gr.Slider(5, 15, value = 10, label = 'Guidance Scale'),
    gr.Slider(25, 50, value = 25, step = 1, label = 'Number of Iterations'),
    gr.Slider(label = "Seed", minimum = 0, maximum = 987654321987654321, step = 1, randomize = True)], 
    outputs='image',
             title = "Stable Diffusion XL 1.0 Doodle to Image CPU", 
             description = "For more information on Stable Diffusion XL 1.0 see https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0 <br><br>Sketch an Image then enter a Prompt, or let it just do its Thing, then click submit. 10 Iterations takes about ~900-1200 seconds currently. For more informationon about Stable Diffusion or Suggestions for prompts, keywords, artists or styles see https://github.com/Maks-s/sd-akashic", 
             article = "Code Monkey: <a href=\"https://huggingface.co/Manjushri\">Manjushri</a>").queue(max_size=5).launch()