app_haircolor_pix2pix.py

import spaces
import gradio as gr
import time
import torch
import numpy as np
import cv2

from PIL import Image
from segment_utils import(
    segment_image,
    restore_result,
)
from diffusers import (
    DiffusionPipeline,
    StableDiffusionInstructPix2PixPipeline,
    EulerAncestralDiscreteScheduler,
    T2IAdapter,
)

from controlnet_aux import (
    CannyDetector,
    LineartDetector,
    PidiNetDetector,
    HEDdetector,
)

BASE_MODEL = "timbrooks/instruct-pix2pix"

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

DEFAULT_EDIT_PROMPT = "change hair to blue"
DEFAULT_NEGATIVE_PROMPT = "worst quality, normal quality, low quality, low res, blurry, text, watermark, logo, banner, extra digits, cropped, jpeg artifacts, signature, username, error, sketch ,duplicate, ugly, monochrome, horror, geometry, mutation, disgusting, poorly drawn face, bad face, fused face, ugly face, worst face, asymmetrical, unrealistic skin texture, bad proportions, out of frame, poorly drawn hands, cloned face, double face"

DEFAULT_CATEGORY = "hair"

adapter = T2IAdapter.from_pretrained(
    "TencentARC/t2iadapter_canny_sd15v2",
    torch_dtype=torch.float16,
    varient="fp16",
)

basepipeline = DiffusionPipeline.from_pretrained(
    BASE_MODEL,
    torch_dtype=torch.float16,
    use_safetensors=True,
    adapter=adapter,
    custom_pipeline="./pipelines/pipeline_sd_adapter_p2p.py",
)

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

basepipeline = basepipeline.to(DEVICE)

basepipeline.enable_model_cpu_offload()

@spaces.GPU(duration=30)
def image_to_image(
    input_image: Image,
    edit_prompt: str,
    seed: int,
    num_steps: int,
    guidance_scale: float,
    image_guidance_scale: float,
    generate_size: int,
    cond_scale1: float = 1.2,
):
    run_task_time = 0
    time_cost_str = ''
    run_task_time, time_cost_str = get_time_cost(run_task_time, time_cost_str)
    canny_image = custom_canny_detector(input_image)

    cond_image = canny_image
    cond_scale = cond_scale1

    generator = torch.Generator(device=DEVICE).manual_seed(seed)
    generated_image = basepipeline(
        generator=generator,
        prompt=edit_prompt,
        negative_prompt=DEFAULT_NEGATIVE_PROMPT,
        image=input_image,
        guidance_scale=guidance_scale,
        image_guidance_scale=image_guidance_scale,
        num_inference_steps=num_steps,
        adapter_image=cond_image,
        adapter_conditioning_scale=cond_scale,
    ).images[0]
    
    run_task_time, time_cost_str = get_time_cost(run_task_time, time_cost_str)

    return generated_image, time_cost_str

def custom_canny_detector(image):
    image = np.array(image)

    low_threshold = 100
    high_threshold = 200

    image = cv2.Canny(image, low_threshold, high_threshold)
    image = Image.fromarray(image)
    return image

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)
                    cond_scale1 = gr.Slider(minimum=0, maximum=3, value=1.2, step=0.1, label="Cond_scale1")
                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)
            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, generate_size, cond_scale1],
            outputs=[generated_image, generated_cost],
        ).success(
            fn=restore_result,
            inputs=[croper, category, generated_image],
            outputs=[restored_image],
        )

    return demo