app_base.py

import spaces
import gradio as gr
import time
import torch

from PIL import Image
from segment_utils import(
    segment_image,
    restore_result,
)
from enhance_utils import enhance_image

DEFAULT_SRC_PROMPT = "a woman, photo"
DEFAULT_EDIT_PROMPT = "a beautiful woman, photo, hollywood style face, 8k, high quality"

DEFAULT_CATEGORY = "face"

device = "cuda" if torch.cuda.is_available() else "cpu"

def create_demo() -> gr.Blocks:
    from inversion_run_base import run as base_run

    @spaces.GPU(duration=30)
    def image_to_image(
        input_image: Image,
        input_image_prompt: str,
        edit_prompt: str,
        seed: int,
        w1: float,
        num_steps: int,
        start_step: int,
        guidance_scale: float,
        generate_size: int,
        enhance_scale: int,
        enhance_face: bool = True,
    ):
        w2 = 1.0
        run_task_time = 0
        time_cost_str = ''
        run_task_time, time_cost_str = get_time_cost(run_task_time, time_cost_str)
        run_model = base_run
        res_image = run_model(
            input_image,
            input_image_prompt,
            edit_prompt,
            generate_size,
            seed,
            w1,
            w2,
            num_steps,
            start_step,
            guidance_scale,
        )
        run_task_time, time_cost_str = get_time_cost(run_task_time, time_cost_str)
        enhance_mode = 0 if enhance_face else 2
        enhanced_image = enhance_image(res_image, enhance_scale, enhance_mode)
        run_task_time, time_cost_str = get_time_cost(run_task_time, time_cost_str)

        return enhanced_image, res_image, time_cost_str

    def get_time_cost(run_task_time, time_cost_str):
        now_time = int(time.time()*1000)
        if run_task_time == 0:
            time_cost_str = 'start'
        else:
            if time_cost_str != '': 
                time_cost_str += f'-->'
            time_cost_str += f'{now_time - run_task_time}'
        run_task_time = now_time
        return run_task_time, time_cost_str

    with gr.Blocks() as demo:
        croper = gr.State()
        with gr.Row():
            with gr.Column():
                input_image_prompt = gr.Textbox(lines=1, label="Input Image Prompt", value=DEFAULT_SRC_PROMPT)
                edit_prompt = gr.Textbox(lines=1, label="Edit Prompt", value=DEFAULT_EDIT_PROMPT)
                category = gr.Textbox(label="Category", value=DEFAULT_CATEGORY, visible=False)
            with gr.Column():
                num_steps = gr.Slider(minimum=1, maximum=100, value=30, step=1, label="Num Steps")
                start_step = gr.Slider(minimum=1, maximum=100, value=20, step=1, label="Start Step")
                with gr.Accordion("Advanced Options", open=False):
                    guidance_scale = gr.Slider(minimum=0, maximum=20, value=0, step=0.5, label="Guidance Scale")
                    generate_size = gr.Number(label="Generate Size", value=1024)
                    mask_expansion = gr.Number(label="Mask Expansion", value=50, visible=True)
                    mask_dilation = gr.Slider(minimum=0, maximum=10, value=2, step=1, label="Mask Dilation")
                    enhance_scale = gr.Slider(minimum=1, maximum=4, value=2, step=1, label="Enhance Scale")
                    enhance_face = gr.Checkbox(label="Enhance Face", value=False)
            with gr.Column():
                seed = gr.Number(label="Seed", value=8)
                w1 = gr.Number(label="W1", value=2)
                g_btn = gr.Button("Edit Image")
                
        with gr.Row():
            with gr.Column():
                input_image = gr.Image(label="Input Image", type="pil")
            with gr.Column():
                restored_image = gr.Image(label="Restored Image", format="png", type="pil", interactive=False)
                download_path = gr.File(label="Download the output image", interactive=False)
            with gr.Column():
                origin_area_image = gr.Image(label="Origin Area Image", format="png", type="pil", interactive=False)
                enhanced_image = gr.Image(label="Enhanced Image", format="png", type="pil", interactive=False)
                generated_cost = gr.Textbox(label="Time cost by step (ms):", visible=True, interactive=False)
                generated_image = gr.Image(label="Generated Image", format="png", type="pil", interactive=False)
        
        g_btn.click(
            fn=segment_image,
            inputs=[input_image, category, generate_size, mask_expansion, mask_dilation],
            outputs=[origin_area_image, croper],
        ).success(
            fn=image_to_image,
            inputs=[origin_area_image, input_image_prompt, edit_prompt,seed,w1, num_steps, start_step, guidance_scale, generate_size, enhance_scale, enhance_face],
            outputs=[enhanced_image, generated_image, generated_cost],
        ).success(
            fn=restore_result,
            inputs=[croper, category, enhanced_image],
            outputs=[restored_image, download_path],
        )

    return demo