File size: 12,865 Bytes
579c64b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d5415f5
579c64b
 
 
 
d5415f5
579c64b
 
12a3126
579c64b
 
 
12a3126
579c64b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8a564e4
579c64b
 
d5415f5
579c64b
 
 
8a564e4
579c64b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9360364
 
 
 
579c64b
 
9360364
 
 
 
579c64b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9360364
579c64b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9360364
579c64b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9360364
579c64b
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
import torch
import numpy as np
import random
import os

from diffusers.utils import load_image
from diffusers import EulerAncestralDiscreteScheduler

from huggingface_hub import hf_hub_download
import spaces
import gradio as gr

from pipeline import PhotoMakerStableDiffusionXLPipeline
from style_template import styles

# Download civitai models
civitai_model_path = "./civitai_models"
os.makedirs(civitai_model_path, exist_ok=True)
base_model_name = "sdxlUnstableDiffusers_v11.safetensors"
base_model_path = os.path.join(civitai_model_path, base_model_name)
if not os.path.exists(base_model_path):
    base_model_path = hf_hub_download(repo_id="Paper99/sdxlUnstableDiffusers_v11", filename=base_model_name, repo_type="model")

lora_model_name = "xl_more_art-full.safetensors"
lora_path = os.path.join(civitai_model_path, lora_model_name)
if not os.path.exists(lora_path):
    lora_path = hf_hub_download(repo_id="Paper99/sdxlUnstableDiffusers_v11", filename=lora_model_name, repo_type="model")
    
# global variable
device = "cuda" if torch.cuda.is_available() else "cpu"
MAX_SEED = np.iinfo(np.int32).max
STYLE_NAMES = list(styles.keys())
DEFAULT_STYLE_NAME = "(No style)"

# download PhotoMaker checkpoint to cache
photomaker_ckpt = hf_hub_download(repo_id="TencentARC/PhotoMaker", filename="photomaker-v1.bin", repo_type="model")

pipe = PhotoMakerStableDiffusionXLPipeline.from_single_file(
    base_model_path, 
    torch_dtype=torch.bfloat16, 
    original_config_file=None,
).to(device)

pipe.load_photomaker_adapter(
    os.path.dirname(photomaker_ckpt),
    subfolder="",
    weight_name=os.path.basename(photomaker_ckpt),
    trigger_word="img"
)     
pipe.id_encoder.to(device)

pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
pipe.load_lora_weights(os.path.dirname(lora_path), weight_name=lora_model_name, adapter_name="xl_more_art-full")
pipe.set_adapters(["photomaker", "xl_more_art-full"], adapter_weights=[1.0, 0.5])
pipe.fuse_lora()

@spaces.GPU
def generate_image(upload_images, prompt, negative_prompt, 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!")

    # 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"[Debug] Prompt: {prompt}, \n[Debug] 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,
        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 = "") -> tuple[str, 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/yangmi_woman'),
            "a woman img, retro futurism, retro game art style but extremely beautiful, intricate details, masterpiece, best quality, space-themed, cosmic, celestial, stars, galaxies, nebulas, planets, science fiction, highly detailed",
            35,
            "realistic, photo-realistic, worst quality, greyscale, bad anatomy, bad hands, error, text",
        ],
        [
            get_image_path_list('./examples/lenna_woman'),
            "A girl img riding dragon over a whimsical castle, 3d CGI, art by Pixar, half-body, screenshot from animation",
            20,
            "realistic, photo-realistic, bad quality, bad anatomy, worst quality, low quality, lowres, extra fingers, blur, blurry, ugly, wrong proportions, watermark, image artifacts, bad eyes",
        ],
    ]
    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: Customizing Realistic Human Photos via Stacked ID Embedding</h1>
<h3 align="center">-- Stylization version --</h3>
"""

description = r"""
<b>Official 🤗 Gradio demo</b> for <a href='https://github.com/TencentARC/PhotoMaker' target='_blank'><b>PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding</b></a>.<br>
<br>
For photo-realistic generation, you could use our other gradio demo [PhotoMaker](https://huggingface.co/spaces/TencentARC/PhotoMaker).
<br>
❗️❗️❗️[<b>Important</b>] Personalization steps:<br>
1️⃣ Upload images of someone you want to customize. One image is ok, but more is better.  Although we do not perform face detection, the face in the uploaded image should <b>occupy the majority of the image</b>.<br>
2️⃣ Enter a text prompt, making sure to <b>follow the class word</b> you want to customize with the <b>trigger word</b>: `img`, such as: `man img` or `woman img` or `girl img`.<br>
3️⃣ Choose your preferred style template.<br>
4️⃣ Click the <b>Submit</b> button to start customizing.
"""

article = r"""

If PhotoMaker is helpful, please help to ⭐ the <a href='https://github.com/TencentARC/PhotoMaker' target='_blank'>Github Repo</a>. Thanks! 
[![GitHub Stars](https://img.shields.io/github/stars/TencentARC/PhotoMaker?style=social)](https://github.com/TencentARC/PhotoMaker)
---
📝 **Citation**
<br>
If our work is useful for your research, please consider citing:

```bibtex
@article{li2023photomaker,
  title={PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding},
  author={Li, Zhen and Cao, Mingdeng and Wang, Xintao and Qi, Zhongang and Cheng, Ming-Ming and Shan, Ying},
  booktitle={arXiv preprint arxiv:2312.04461},
  year={2023}
}
```
📋 **License**
<br>
Apache-2.0 LICENSE. Please refer to the [LICENSE file](https://huggingface.co/TencentARC/PhotoMaker/blob/main/LICENSE) for details.

📧 **Contact**
<br>
If you have any questions, please feel free to reach me out at <b>zhenli1031@gmail.com</b>.
"""

tips = r"""
### Usage tips of PhotoMaker
1. Upload more photos of the person to be customized to **improve ID fidelty**. If the input is Asian face(s), maybe consider adding 'asian' before the class word, e.g., `asian woman img`
2. When stylizing, does the generated face look too realistic? Adjust the **Style strength** to 30-50, the larger the number, the less ID fidelty, but the stylization ability will be better.
3. If you want to generate realistic photos, you could try switching to our other gradio application [PhotoMaker](https://huggingface.co/spaces/TencentARC/PhotoMaker).
4. For **faster** speed, reduce the number of generated images and sampling steps. However, please note that reducing the sampling steps may compromise the ID fidelity.
"""
# 3. Don't make the prompt too long, as we will trim it if it exceeds 77 tokens. But we will fix it in the future. 

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="Drag (Select) 1 or more photos of your face",
                        file_types=["image"]
                    )
            uploaded_files = gr.Gallery(label="Your images", visible=False, columns=5, rows=1, height=200)
            with gr.Column(visible=False) as clear_button:
                remove_and_reupload = gr.ClearButton(value="Remove and upload new ones", components=files, size="sm")
            prompt = gr.Textbox(label="Prompt",
                       info="Try something like 'a photo of a man/woman img', 'img' is the trigger word.",
                       placeholder="A photo of a [man/woman img]...")
            style = gr.Dropdown(label="Style template", choices=STYLE_NAMES, value=DEFAULT_STYLE_NAME)
            submit = gr.Button("Submit")

            with gr.Accordion(open=False, label="Advanced Options"):
                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="Generated Images")
            usage_tips = gr.Markdown(label="Usage tips of PhotoMaker", 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, style, num_steps, style_strength_ratio, num_outputs, guidance_scale, seed],
            outputs=[gallery, usage_tips]
        )

    gr.Examples(
        examples=get_example(),
        inputs=[files, prompt, style_strength_ratio, negative_prompt],
        run_on_click=True,
        fn=upload_example_to_gallery,
        outputs=[uploaded_files, clear_button, files],
    )
    
    gr.Markdown(article)
    
demo.launch()