app.py

import torch
import numpy as np
import random
import os
import sys

from diffusers.utils import load_image
from diffusers import EulerDiscreteScheduler

from huggingface_hub import hf_hub_download
import gradio as gr

from photomaker import PhotoMakerStableDiffusionXLPipeline

from style_template import styles
from aspect_ratio_template import aspect_ratios

# global variable
base_model_path = 'SG161222/RealVisXL_V4.0'
try:
    if torch.cuda.is_available():
        device = "cuda"
    elif sys.platform == "darwin" and torch.backends.mps.is_available():
        device = "mps"
    else:
        device = "cpu"
except:
    device = "cpu"

MAX_SEED = np.iinfo(np.int32).max
STYLE_NAMES = list(styles.keys())
DEFAULT_STYLE_NAME = "Photographic (Default)"
ASPECT_RATIO_LABELS = list(aspect_ratios)
DEFAULT_ASPECT_RATIO = ASPECT_RATIO_LABELS[0]

torch_dtype = torch.bfloat16 if torch.cuda.is_bf16_supported() else torch.float16
if device == "mps":
    torch_dtype = torch.float16

pipe = PhotoMakerStableDiffusionXLPipeline.from_pretrained(
    base_model_path,
    torch_dtype=torch_dtype,
    use_safetensors=True,
    variant="fp16",
    # local_files_only=True,
).to(device)

pipe.load_photomaker_adapter(
    "TencentARC/PhotoMaker",
    subfolder="",
    weight_name="photomaker-v1.bin",
    trigger_word="img",
    pm_version="v1",
)
pipe.id_encoder.to(device)

pipe.scheduler = EulerDiscreteScheduler.from_config(pipe.scheduler.config)
# pipe.set_adapters(["photomaker"], adapter_weights=[1.0])
pipe.fuse_lora()
pipe.to(device)


def generate_image(upload_images, prompt, negative_prompt, aspect_ratio_name, style_name, num_steps,
                   style_strength_ratio, num_outputs, guidance_scale, seed, progress=gr.Progress(track_tqdm=True)):
    # check the trigger word
    image_token_id = pipe.tokenizer.convert_tokens_to_ids(pipe.trigger_word)
    input_ids = pipe.tokenizer.encode(prompt)
    if image_token_id not in input_ids:
        raise gr.Error(f"Cannot find the trigger word '{pipe.trigger_word}' in text prompt! Please refer to step 2️⃣")

    if input_ids.count(image_token_id) > 1:
        raise gr.Error(f"Cannot use multiple trigger words '{pipe.trigger_word}' in text prompt!")

    # determine output dimensions by the aspect ratio
    output_w, output_h = aspect_ratios[aspect_ratio_name]
    print(f"Generate image using aspect ratio [{aspect_ratio_name}] => {output_w} x {output_h}")

    # apply the style template
    prompt, negative_prompt = apply_style(style_name, prompt, negative_prompt)

    if upload_images is None:
        raise gr.Error(f"Cannot find any input face image! Please refer to step 1️⃣")

    input_id_images = []
    for img in upload_images:
        input_id_images.append(load_image(img))

    generator = torch.Generator(device=device).manual_seed(seed)

    print("Start inference...")
    print(f"Prompt: {prompt}, \n Neg Prompt: {negative_prompt}")
    start_merge_step = int(float(style_strength_ratio) / 100 * num_steps)
    if start_merge_step > 30:
        start_merge_step = 30
    print(start_merge_step)
    images = pipe(
        prompt=prompt,
        width=output_w,
        height=output_h,
        input_id_images=input_id_images,
        negative_prompt=negative_prompt,
        num_images_per_prompt=num_outputs,
        num_inference_steps=num_steps,
        start_merge_step=start_merge_step,
        generator=generator,
        guidance_scale=guidance_scale,
    ).images
    return images, gr.update(visible=True)


def swap_to_gallery(images):
    return gr.update(value=images, visible=True), gr.update(visible=True), gr.update(visible=False)


def upload_example_to_gallery(images, prompt, style, negative_prompt):
    return gr.update(value=images, visible=True), gr.update(visible=True), gr.update(visible=False)


def remove_back_to_files():
    return gr.update(visible=False), gr.update(visible=False), gr.update(visible=True)


def remove_tips():
    return gr.update(visible=False)


def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
    return seed


def apply_style(style_name: str, positive: str, negative: str = ""):
    p, n = styles.get(style_name, styles[DEFAULT_STYLE_NAME])
    return p.replace("{prompt}", positive), n + ' ' + negative


def get_image_path_list(folder_name):
    image_basename_list = os.listdir(folder_name)
    image_path_list = sorted([os.path.join(folder_name, basename) for basename in image_basename_list])
    return image_path_list


def get_example():
    case = [
        [
            get_image_path_list('./examples/scarletthead_woman'),
            "instagram photo, portrait photo of a woman img, colorful, perfect face, natural skin, hard shadows, film grain",
            "(No style)",
            "(asymmetry, worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth",
        ],
        [
            get_image_path_list('./examples/newton_man'),
            "sci-fi, closeup portrait photo of a man img wearing the sunglasses in Iron man suit, face, slim body, high quality, film grain",
            "(No style)",
            "(asymmetry, worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth",
        ],
    ]
    return case


### Description and style
logo = r"""
<center><img src='https://photo-maker.github.io/assets/logo.png' alt='PhotoMaker logo' style="width:80px; margin-bottom:10px"></center>
"""
title = r"""
<h1 align="center">PhotoMaker：通过少量样本提取的个性化信息，在自然语言描述引导下，生成逼真的照片或者艺术化的图片</h1>
"""

description = r"""
个性化步骤：<br>
1️⃣ 上传您想要自定义的某个人的图像。一张或多张图片都行，建议多张。此工具不进行人脸检测，上传图像中的人脸应该占据图像的大部分。<br>
2️⃣ 输入文本提示符，确保按照您想要自定义的类单词使用触发词: `img`, 例如： `man img` 、 `woman img` 或 `girl img`。<br>
3️⃣ 选择您喜欢的风格模板。<br>
4️⃣ 单击提交按钮开始自定义。
"""

tips = r"""
### 使用技巧
1. 上传多张要定制的人的照片，以**提高身份识别精度**。如果输入是亚洲面孔，也许可以考虑在类单词之前添加“asian”，例如`asian woman img`
2. 为了**更快**的速度，减少生成的图像数量和采样步骤。但是，请注意，减少采样步骤可能会降低ID保真度。
"""
# We have provided some generate examples and comparisons at: [this website]().
# 3. Don't make the prompt too long, as we will trim it if it exceeds 77 tokens.
# 4. When generating realistic photos, if it's not real enough, try switching to our other gradio application [PhotoMaker-Realistic]().

css = '''
.gradio-container {width: 85% !important}
'''
with gr.Blocks(css=css) as demo:
    gr.Markdown(logo)
    gr.Markdown(title)
    gr.Markdown(description)
    # gr.DuplicateButton(
    #     value="Duplicate Space for private use ",
    #     elem_id="duplicate-button",
    #     visible=os.getenv("SHOW_DUPLICATE_BUTTON") == "1",
    # )
    with gr.Row():
        with gr.Column():
            files = gr.Files(
                label="上传/选择一张或多张人脸照片",
                file_types=["image"]
            )
            uploaded_files = gr.Gallery(label="你的图片", visible=False, columns=5, rows=1, height=200)
            with gr.Column(visible=False) as clear_button:
                remove_and_reupload = gr.ClearButton(value="移除并重新上传", components=files, size="sm")
            prompt = gr.Textbox(label="Prompt",
                                info="尝试类似'a photo of a man/woman img'的词, 'img'是触发词，必须包含",
                                placeholder="A photo of a [man/woman img]...")
            style = gr.Dropdown(label="风格", choices=STYLE_NAMES, value=DEFAULT_STYLE_NAME)
            aspect_ratio = gr.Dropdown(label="输出纵横比", choices=ASPECT_RATIO_LABELS,
                                       value=DEFAULT_ASPECT_RATIO)
            submit = gr.Button("提交")

            with gr.Accordion(open=False, label="高级选项"):
                negative_prompt = gr.Textbox(
                    label="Negative Prompt",
                    placeholder="low quality",
                    value="nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
                )
                num_steps = gr.Slider(
                    label="Number of sample steps",
                    minimum=20,
                    maximum=100,
                    step=1,
                    value=50,
                )
                style_strength_ratio = gr.Slider(
                    label="Style strength (%)",
                    minimum=15,
                    maximum=50,
                    step=1,
                    value=20,
                )
                num_outputs = gr.Slider(
                    label="Number of output images",
                    minimum=1,
                    maximum=4,
                    step=1,
                    value=2,
                )
                guidance_scale = gr.Slider(
                    label="Guidance scale",
                    minimum=0.1,
                    maximum=10.0,
                    step=0.1,
                    value=5,
                )
                seed = gr.Slider(
                    label="Seed",
                    minimum=0,
                    maximum=MAX_SEED,
                    step=1,
                    value=0,
                )
                randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
        with gr.Column():
            gallery = gr.Gallery(label="生成图片")
            usage_tips = gr.Markdown(label="使用技巧", value=tips, visible=False)

        files.upload(fn=swap_to_gallery, inputs=files, outputs=[uploaded_files, clear_button, files])
        remove_and_reupload.click(fn=remove_back_to_files, outputs=[uploaded_files, clear_button, files])

        submit.click(
            fn=remove_tips,
            outputs=usage_tips,
        ).then(
            fn=randomize_seed_fn,
            inputs=[seed, randomize_seed],
            outputs=seed,
            queue=False,
            api_name=False,
        ).then(
            fn=generate_image,
            inputs=[files, prompt, negative_prompt, aspect_ratio, style, num_steps, style_strength_ratio, num_outputs,
                    guidance_scale, seed],
            outputs=[gallery, usage_tips]
        )

    gr.Examples(
        examples=get_example(),
        inputs=[files, prompt, style, negative_prompt],
        run_on_click=True,
        fn=upload_example_to_gallery,
        outputs=[uploaded_files, clear_button, files],
    )

demo.launch(server_name='0.0.0.0', share=True)