app_haircolor_pix2pix.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
from diffusers import (
    StableDiffusionInstructPix2PixPipeline,
    EulerAncestralDiscreteScheduler,
    DDIMScheduler,
)

BASE_MODEL = "timbrooks/instruct-pix2pix"

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

DEFAULT_EDIT_PROMPT = "hair to linen-blonde-hair"

DEFAULT_CATEGORY = "hair"

basepipeline = StableDiffusionInstructPix2PixPipeline.from_pretrained(
    BASE_MODEL,
    torch_dtype=torch.float16,
    use_safetensors=True,
)

basepipeline.scheduler = DDIMScheduler.from_config(basepipeline.scheduler.config)

basepipeline = basepipeline.to(DEVICE)

basepipeline.enable_model_cpu_offload()

@spaces.GPU(duration=15)
def image_to_image(
    input_image: Image,
    edit_prompt: str,
    seed: int,
    num_steps: int,
    guidance_scale: float,
    image_guidance_scale: float,
):
    run_task_time = 0
    time_cost_str = ''
    run_task_time, time_cost_str = get_time_cost(run_task_time, time_cost_str)

    generator = torch.Generator(device=DEVICE).manual_seed(seed)
    generated_image = basepipeline(
        generator=generator,
        prompt=edit_prompt,
        image=input_image,
        guidance_scale=guidance_scale,
        image_guidance_scale=image_guidance_scale,
        num_inference_steps=num_steps,
    ).images[0]
    
    run_task_time, time_cost_str = get_time_cost(run_task_time, time_cost_str)
    enhanced_image = enhance_image(generated_image, False)
    run_task_time, time_cost_str = get_time_cost(run_task_time, time_cost_str)
    return enhanced_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

def create_demo() -> gr.Blocks:
    with gr.Blocks() as demo:
        croper = gr.State()
        with gr.Row():
            with gr.Column():
                edit_prompt = gr.Textbox(lines=1, label="Edit Prompt", value=DEFAULT_EDIT_PROMPT)
                generate_size = gr.Number(label="Generate Size", value=512)
            with gr.Column():
                num_steps = gr.Slider(minimum=1, maximum=100, value=20, step=1, label="Num Steps")
                guidance_scale = gr.Slider(minimum=0, maximum=30, value=5, step=0.5, label="Guidance Scale")
            with gr.Column():
                image_guidance_scale = gr.Slider(minimum=0, maximum=30, value=1.5, step=0.1, label="Image Guidance Scale")
                with gr.Accordion("Advanced Options", open=False):
                    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")
                    seed = gr.Number(label="Seed", value=8)
                    category = gr.Textbox(label="Category", value=DEFAULT_CATEGORY, visible=False)
                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", 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", type="pil", interactive=False)
                generated_image = gr.Image(label="Generated Image", type="pil", interactive=False)
                generated_cost = gr.Textbox(label="Time cost by step (ms):", visible=True, 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, edit_prompt,seed, num_steps, guidance_scale, image_guidance_scale],
            outputs=[generated_image, generated_cost],
        ).success(
            fn=restore_result,
            inputs=[croper, category, generated_image],
            outputs=[restored_image, download_path],
        )

    return demo