import gradio as gr
import numpy as np
import random
#import spaces #[uncomment to use ZeroGPU]
from diffusers import StableDiffusionPipeline, StableDiffusionImg2ImgPipeline
import torch

from src.linfusion import LinFusion

device = "cuda" if torch.cuda.is_available() else "cpu"
all_model_id = {
    "DreamShaper-8": "Lykon/dreamshaper-8",
    "SD-v1.4": "CompVis/stable-diffusion-v1-4",
    "RealisticVision-v4.0": "SG161222/Realistic_Vision_V4.0_noVAE"
}

if torch.cuda.is_available():
    torch_dtype = torch.float16
else:
    torch_dtype = torch.float32

MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024

#@spaces.GPU #[uncomment to use ZeroGPU]
def infer_t2i(model, prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, progress=gr.Progress(track_tqdm=True)):

    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
        
    generator = torch.Generator().manual_seed(seed)

    pipe = StableDiffusionPipeline.from_pretrained(all_model_id[model], torch_dtype=torch_dtype)
    pipe = pipe.to(device)
    linfusion = LinFusion.construct_for(pipe)
    
    image = pipe(
        prompt = prompt, 
        negative_prompt = negative_prompt,
        guidance_scale = guidance_scale, 
        num_inference_steps = num_inference_steps, 
        width = width, 
        height = height,
        generator = generator
    ).images[0] 
    
    return image, seed

#@spaces.GPU #[uncomment to use ZeroGPU]
def infer_i2i(model, prompt, image, strength, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, progress=gr.Progress(track_tqdm=True)):

    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
        
    generator = torch.Generator().manual_seed(seed)

    pipe = StableDiffusionImg2ImgPipeline.from_pretrained(all_model_id[model], torch_dtype=torch_dtype)
    pipe = pipe.to(device)
    linfusion = LinFusion.construct_for(pipe)
    
    image = pipe(
        prompt = prompt, 
        image = image.resize((width, height)),
        strength = strength,
        negative_prompt = negative_prompt,
        guidance_scale = guidance_scale, 
        num_inference_steps = num_inference_steps, 
        width = width, 
        height = height,
        generator = generator
    ).images[0] 
    
    return image, seed

#@spaces.GPU #[uncomment to use ZeroGPU]
def infer_ip_adapter(model, prompt, image, scale, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, progress=gr.Progress(track_tqdm=True)):

    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
        
    generator = torch.Generator().manual_seed(seed)

    pipe = StableDiffusionPipeline.from_pretrained(all_model_id[model], torch_dtype=torch_dtype)
    pipe = pipe.to(device)
    pipe.load_ip_adapter("h94/IP-Adapter", subfolder="models", weight_name="ip-adapter-plus_sd15.bin")
    pipe.set_ip_adapter_scale(scale)
    linfusion = LinFusion.construct_for(pipe)
    
    image = pipe(
        prompt = prompt, 
        image = image.resize((width, height)),
        strength = strength,
        negative_prompt = negative_prompt,
        guidance_scale = guidance_scale, 
        num_inference_steps = num_inference_steps, 
        ip_adapter_image = image,
        width = width, 
        height = height,
        generator = generator
    ).images[0]
    
    return image, seed

examples = [
    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
    "An astronaut riding a green horse",
    "A delicious ceviche cheesecake slice",
]

css="""
#col-container {
    margin: 0 auto;
    max-width: 640px;
}
"""

with gr.Blocks(css=css) as demo:

    with gr.Tab("Text-to-Image"):
    
        with gr.Column(elem_id="col-container"):
            gr.Markdown(f"""
            # Text-to-Image Gradio Template
            """)
            
            with gr.Row():
                
                prompt = gr.Text(
                    label="Prompt",
                    show_label=False,
                    max_lines=1,
                    placeholder="Enter your prompt",
                    container=False,
                )
                
                run_button = gr.Button("Run", scale=0)
            
            result = gr.Image(label="Result", show_label=False)
    
            with gr.Accordion("Advanced Settings", open=False):
                
                negative_prompt = gr.Text(
                    label="Negative prompt",
                    max_lines=1,
                    placeholder="Enter a negative prompt",
                    visible=False,
                )
                
                seed = gr.Slider(
                    label="Seed",
                    minimum=0,
                    maximum=MAX_SEED,
                    step=1,
                    value=0,
                )

                model_choice = gr.Dropdown(label="Choose Model", choices=list(all_model_id.keys()), value=list(all_model_id.keys())[0])
                
                randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
                
                with gr.Row():
                    
                    width = gr.Slider(
                        label="Width",
                        minimum=256,
                        maximum=MAX_IMAGE_SIZE,
                        step=32,
                        value=512, #Replace with defaults that work for your model
                    )
                    
                    height = gr.Slider(
                        label="Height",
                        minimum=256,
                        maximum=MAX_IMAGE_SIZE,
                        step=32,
                        value=512, #Replace with defaults that work for your model
                    )
                
                with gr.Row():
                    
                    guidance_scale = gr.Slider(
                        label="Guidance scale",
                        minimum=0.0,
                        maximum=10.0,
                        step=0.1,
                        value=7.5, #Replace with defaults that work for your model
                    )
                    
                    num_inference_steps = gr.Slider(
                        label="Number of inference steps",
                        minimum=1,
                        maximum=50,
                        step=1,
                        value=25, #Replace with defaults that work for your model
                    )
            
            gr.Examples(
                examples = examples,
                inputs = [prompt]
            )
    
            run_button.click(
                fn=infer_t2i,
                inputs = [model_choice, prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
                outputs = [result, seed]
            )

    with gr.Tab("Image-to-Image"):

        with gr.Column(elem_id="col-container"):
            gr.Markdown(f"""
            # Text-to-Image Gradio Template
            """)
            
            with gr.Row():
                
                prompt = gr.Text(
                    label="Prompt",
                    show_label=False,
                    max_lines=1,
                    placeholder="Enter your prompt",
                    container=False,
                )
                
                run_button = gr.Button("Run", scale=0)

            image_upload_input = gr.Image(label="Upload an Image", type="pil")
            
            result = gr.Image(label="Result", show_label=False)
    
            with gr.Accordion("Advanced Settings", open=False):
                
                negative_prompt = gr.Text(
                    label="Negative prompt",
                    max_lines=1,
                    placeholder="Enter a negative prompt",
                    visible=False,
                )
                
                seed = gr.Slider(
                    label="Seed",
                    minimum=0,
                    maximum=MAX_SEED,
                    step=1,
                    value=0,
                )
                
                randomize_seed = gr.Checkbox(label="Randomize seed", value=True)

                model_choice = gr.Dropdown(label="Choose Model", choices=list(all_model_id.keys()), value=list(all_model_id.keys())[0])
                
                with gr.Row():
                    
                    width = gr.Slider(
                        label="Width",
                        minimum=256,
                        maximum=MAX_IMAGE_SIZE,
                        step=32,
                        value=512, #Replace with defaults that work for your model
                    )
                    
                    height = gr.Slider(
                        label="Height",
                        minimum=256,
                        maximum=MAX_IMAGE_SIZE,
                        step=32,
                        value=512, #Replace with defaults that work for your model
                    )
                
                with gr.Row():
                    
                    guidance_scale = gr.Slider(
                        label="Guidance scale",
                        minimum=0.0,
                        maximum=10.0,
                        step=0.1,
                        value=7.5, #Replace with defaults that work for your model
                    )
                    
                    num_inference_steps = gr.Slider(
                        label="Number of inference steps",
                        minimum=1,
                        maximum=50,
                        step=1,
                        value=25, #Replace with defaults that work for your model
                    )

                    editing_strength = gr.Slider(
                        label="Strength of editing",
                        minimum=0,
                        maximum=1,
                        step=0.01,
                        value=0.5, #Replace with defaults that work for your model
                    )
            
            gr.Examples(
                examples = examples,
                inputs = [prompt]
            )
    
            run_button.click(
                fn=infer_i2i,
                inputs = [model_choice, prompt, image_upload_input, editing_strength, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
                outputs = [result, seed]
            )

    with gr.Tab("IP-Adapter"):

        with gr.Column(elem_id="col-container"):
            gr.Markdown(f"""
            # Text-to-Image Gradio Template
            """)
            
            with gr.Row():
                
                prompt = gr.Text(
                    label="Prompt",
                    show_label=False,
                    max_lines=1,
                    placeholder="Enter your prompt",
                    container=False,
                )
                
                run_button = gr.Button("Run", scale=0)

            image_upload_input = gr.Image(label="Upload an Image", type="pil")
            
            result = gr.Image(label="Result", show_label=False)
    
            with gr.Accordion("Advanced Settings", open=False):
                
                negative_prompt = gr.Text(
                    label="Negative prompt",
                    max_lines=1,
                    placeholder="Enter a negative prompt",
                    visible=False,
                )
                
                seed = gr.Slider(
                    label="Seed",
                    minimum=0,
                    maximum=MAX_SEED,
                    step=1,
                    value=0,
                )
                
                randomize_seed = gr.Checkbox(label="Randomize seed", value=True)

                model_choice = gr.Dropdown(label="Choose Model", choices=list(all_model_id.keys()), value=list(all_model_id.keys())[0])
                
                with gr.Row():
                    
                    width = gr.Slider(
                        label="Width",
                        minimum=256,
                        maximum=MAX_IMAGE_SIZE,
                        step=32,
                        value=512, #Replace with defaults that work for your model
                    )
                    
                    height = gr.Slider(
                        label="Height",
                        minimum=256,
                        maximum=MAX_IMAGE_SIZE,
                        step=32,
                        value=512, #Replace with defaults that work for your model
                    )
                
                with gr.Row():
                    
                    guidance_scale = gr.Slider(
                        label="Guidance scale",
                        minimum=0.0,
                        maximum=10.0,
                        step=0.1,
                        value=7.5, #Replace with defaults that work for your model
                    )
                    
                    num_inference_steps = gr.Slider(
                        label="Number of inference steps",
                        minimum=1,
                        maximum=50,
                        step=1,
                        value=25, #Replace with defaults that work for your model
                    )

                    ip_adapter_scale = gr.Slider(
                        label="Strength of image condition",
                        minimum=0,
                        maximum=1,
                        step=0.01,
                        value=0.4, #Replace with defaults that work for your model
                    )
            
            gr.Examples(
                examples = examples,
                inputs = [prompt]
            )
    
            run_button.click(
                fn=infer_ip_adapter,
                inputs = [model_choice, prompt, image_upload_input, ip_adapter_scale, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
                outputs = [result, seed]
            )

demo.queue().launch()