import gradio as gr
import pandas as pd
import torch
import numpy as np
from PIL import Image
from diffusers import DiffusionPipeline
from huggingface_hub import login
import gradio as gr
import torch
import numpy as np
from PIL import Image
from datasets import load_dataset
from diffusers import StableDiffusionImg2ImgPipeline

import torch
from diffusers import StableDiffusionPipeline, DPMSolverMultistepScheduler

model_id = "stabilityai/stable-diffusion-2-1"

device = "cpu"
# DPM-Solver++ scheduler'ını kullan, torch_dtype belirtme
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float32)
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
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, Strength):
    generator = torch.Generator(device).manual_seed(seed)     
    source_image = resize(768, source_img)
    source_image.save('source.png')
    image = pipe(prompt, negative_prompt=negative_prompt, init_image=source_image, strength=Strength, guidance_scale=guide, num_inference_steps=steps).images[0]
    return image
    
gr.Interface(
    fn=infer, 
    inputs=[
        gr.inputs.Image(type="filepath", label="Raw Image. Must Be .png"),  # Güncellenmiş kullanım
        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(2, 15, value=7, label='Guidance Scale'),
        gr.Slider(1, 25, value=10, step=1, label='Number of Iterations'),
        gr.Slider(label="Seed", minimum=0, maximum=987654321987654321, step=1, randomize=True), 
        gr.Slider(label='Strength', minimum=0, maximum=1, step=.05, value=.5)
    ], 
    outputs='image', 
    title="Stable Diffusion 2.1 Image to Image Pipeline on CPU",
    description="For more information on Stable Diffusion 2.1 see https://github.com/Stability-AI/stablediffusion"
).launch()