File size: 16,820 Bytes
3c49f9a
 
 
0ba2339
3c49f9a
 
0ba2339
 
3c49f9a
 
0ba2339
3c49f9a
0ba2339
 
 
 
3c49f9a
0ba2339
 
 
 
4912220
 
3c49f9a
 
0ba2339
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3c49f9a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0ba2339
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3c49f9a
 
 
0ba2339
 
 
 
 
 
 
3c49f9a
0ba2339
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3c49f9a
0ba2339
3c49f9a
 
 
 
 
 
 
 
 
 
0ba2339
 
 
3c49f9a
 
 
 
 
 
 
 
 
 
52ae519
 
 
 
 
3c49f9a
 
 
 
 
 
 
 
 
0ba2339
 
 
 
3c49f9a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0ba2339
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3c49f9a
 
 
 
0ba2339
3c49f9a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0ba2339
3c49f9a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0ba2339
3c49f9a
 
 
0ba2339
 
 
 
 
 
 
 
 
 
3c49f9a
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
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
import os
import cv2
import math
import torch
import random
import numpy as np

import PIL
from PIL import Image

import diffusers
from diffusers.utils import load_image
from diffusers.models import ControlNetModel

import insightface
from insightface.app import FaceAnalysis

from style_template import styles
from pipeline_stable_diffusion_xl_instantid import StableDiffusionXLInstantIDPipeline

import spaces
import gradio as gr

# global variable
MAX_SEED = np.iinfo(np.int32).max
device = "cuda" if torch.cuda.is_available() else "cpu"
STYLE_NAMES = list(styles.keys())
DEFAULT_STYLE_NAME = "Watercolor"

# download checkpoints
from huggingface_hub import hf_hub_download
hf_hub_download(repo_id="InstantX/InstantID", filename="ControlNetModel/config.json", local_dir="./checkpoints")
hf_hub_download(repo_id="InstantX/InstantID", filename="ControlNetModel/diffusion_pytorch_model.safetensors", local_dir="./checkpoints")
hf_hub_download(repo_id="InstantX/InstantID", filename="ip-adapter.bin", local_dir="./checkpoints")

# Load face encoder
app = FaceAnalysis(name='antelopev2', root='./', providers=['CUDAExecutionProvider', 'CPUExecutionProvider'])
app.prepare(ctx_id=0, det_size=(640, 640))

# Path to InstantID models
face_adapter = f'./checkpoints/ip-adapter.bin'
controlnet_path = f'./checkpoints/ControlNetModel'

# Load pipeline
controlnet = ControlNetModel.from_pretrained(controlnet_path, torch_dtype=torch.float16)

base_model_path = 'GHArt/Unstable_Diffusers_YamerMIX_V9_xl_fp16'

pipe = StableDiffusionXLInstantIDPipeline.from_pretrained(
    base_model_path,
    controlnet=controlnet,
    torch_dtype=torch.float16,
    safety_checker=None,
    feature_extractor=None,
)
pipe.cuda()
pipe.load_ip_adapter_instantid(face_adapter)

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

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 get_example():
    case = [
        [
            ['./examples/yann-lecun_resize.jpg'],
            "a man",
            "Snow",
            "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
        ],
        [
            ['./examples/musk_resize.jpeg'],
            "a man",
            "Mars",
            "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
        ],
        [
            ['./examples/sam_resize.png'],
            "a man",
            "Jungle",
            "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, gree",
        ],
        [
            ['./examples/schmidhuber_resize.png'],
            "a man",
            "Neon",
            "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
        ],
        [
            ['./examples/kaifu_resize.png'],
            "a man",
            "Vibrant Color",
            "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
        ],
    ]
    return case

def convert_from_cv2_to_image(img: np.ndarray) -> Image:
    return Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))

def convert_from_image_to_cv2(img: Image) -> np.ndarray:
    return cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)

def draw_kps(image_pil, kps, color_list=[(255,0,0), (0,255,0), (0,0,255), (255,255,0), (255,0,255)]):
    stickwidth = 4
    limbSeq = np.array([[0, 2], [1, 2], [3, 2], [4, 2]])
    kps = np.array(kps)

    w, h = image_pil.size
    out_img = np.zeros([h, w, 3])

    for i in range(len(limbSeq)):
        index = limbSeq[i]
        color = color_list[index[0]]

        x = kps[index][:, 0]
        y = kps[index][:, 1]
        length = ((x[0] - x[1]) ** 2 + (y[0] - y[1]) ** 2) ** 0.5
        angle = math.degrees(math.atan2(y[0] - y[1], x[0] - x[1]))
        polygon = cv2.ellipse2Poly((int(np.mean(x)), int(np.mean(y))), (int(length / 2), stickwidth), int(angle), 0, 360, 1)
        out_img = cv2.fillConvexPoly(out_img.copy(), polygon, color)
    out_img = (out_img * 0.6).astype(np.uint8)

    for idx_kp, kp in enumerate(kps):
        color = color_list[idx_kp]
        x, y = kp
        out_img = cv2.circle(out_img.copy(), (int(x), int(y)), 10, color, -1)

    out_img_pil = Image.fromarray(out_img.astype(np.uint8))
    return out_img_pil

def resize_img(input_image, max_side=1280, min_side=1024, size=None, 
               pad_to_max_side=False, mode=PIL.Image.BILINEAR, base_pixel_number=64):

        w, h = input_image.size
        if size is not None:
            w_resize_new, h_resize_new = size
        else:
            ratio = min_side / min(h, w)
            w, h = round(ratio*w), round(ratio*h)
            ratio = max_side / max(h, w)
            input_image = input_image.resize([round(ratio*w), round(ratio*h)], mode)
            w_resize_new = (round(ratio * w) // base_pixel_number) * base_pixel_number
            h_resize_new = (round(ratio * h) // base_pixel_number) * base_pixel_number
        input_image = input_image.resize([w_resize_new, h_resize_new], mode)

        if pad_to_max_side:
            res = np.ones([max_side, max_side, 3], dtype=np.uint8) * 255
            offset_x = (max_side - w_resize_new) // 2
            offset_y = (max_side - h_resize_new) // 2
            res[offset_y:offset_y+h_resize_new, offset_x:offset_x+w_resize_new] = np.array(input_image)
            input_image = Image.fromarray(res)
        return input_image

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

@spaces.GPU
def generate_image(face_image, pose_image, prompt, negative_prompt, style_name, enhance_face_region, num_steps, identitynet_strength_ratio, adapter_strength_ratio, guidance_scale, seed, progress=gr.Progress(track_tqdm=True)):

    if face_image is None:
        raise gr.Error(f"Cannot find any input face image! Please upload the face image")
    
    if prompt is None:
        prompt = "a person"
    
    # apply the style template
    prompt, negative_prompt = apply_style(style_name, prompt, negative_prompt)
    
    face_image = load_image(face_image[0])
    face_image = resize_img(face_image)
    face_image_cv2 = convert_from_image_to_cv2(face_image)
    height, width, _ = face_image_cv2.shape
    
    # Extract face features
    face_info = app.get(face_image_cv2)
    
    if len(face_info) == 0:
        raise gr.Error(f"Cannot find any face in the image! Please upload another person image")
    
    face_info = face_info[-1]
    face_emb = face_info['embedding']
    face_kps = draw_kps(convert_from_cv2_to_image(face_image_cv2), face_info['kps'])
    
    if pose_image is not None:
        pose_image = load_image(pose_image[0])
        pose_image = resize_img(pose_image)
        pose_image_cv2 = convert_from_image_to_cv2(pose_image)
        
        face_info = app.get(pose_image_cv2)
        
        if len(face_info) == 0:
            raise gr.Error(f"Cannot find any face in the reference image! Please upload another person image")
        
        face_info = face_info[-1]
        face_kps = draw_kps(pose_image, face_info['kps'])
        
        width, height = face_kps.size
    
    if enhance_face_region:
        control_mask = np.zeros([height, width, 3])
        x1, y1, x2, y2 = face_info['bbox']
        x1, y1, x2, y2 = int(x1), int(y1), int(x2), int(y2)
        control_mask[y1:y2, x1:x2] = 255
        control_mask = Image.fromarray(control_mask.astype(np.uint8))
    else:
        control_mask = None
    
    generator = torch.Generator(device=device).manual_seed(seed)
    
    print("Start inference...")
    print(f"[Debug] Prompt: {prompt}, \n[Debug] Neg Prompt: {negative_prompt}")
    
    pipe.set_ip_adapter_scale(adapter_strength_ratio)
    images = pipe(
        prompt=prompt,
        negative_prompt=negative_prompt,
        image_embeds=face_emb,
        image=face_kps,
        control_mask=control_mask,
        controlnet_conditioning_scale=float(identitynet_strength_ratio),
        num_inference_steps=num_steps,
        guidance_scale=guidance_scale,
        height=height,
        width=width,
        generator=generator
    ).images

    return images, gr.update(visible=True)

### Description
title = r"""
<h1 align="center">InstantID: Zero-shot Identity-Preserving Generation in Seconds</h1>
"""

description = r"""
<b>Official 🤗 Gradio demo</b> for <a href='https://github.com/InstantID/InstantID' target='_blank'><b>InstantID: Zero-shot Identity-Preserving Generation in Seconds</b></a>.<br>

How to use:<br>
1. Upload a person image. For multiple person images, we will only detect the biggest face. Make sure face is not too small and not significantly blocked or blurred.
2. (Optionally) upload another person image as reference pose. If not uploaded, we will use the first person image to extract landmarks. If you use a cropped face at step1, it is recommeneded to upload it to extract a new pose.
3. Enter a text prompt as done in normal text-to-image models.
4. Click the <b>Submit</b> button to start customizing.
5. Share your customizd photo with your friends, enjoy😊!
"""

article = r"""
---
📝 **Citation**
<br>
If our work is helpful for your research or applications, please cite us via:
```bibtex
@article{wang2024instantid,
  title={InstantID: Zero-shot Identity-Preserving Generation in Seconds},
  author={Wang, Qixun and Bai, Xu and Wang, Haofan and Qin, Zekui and Chen, Anthony},
  journal={arXiv preprint arXiv:2401.07519},
  year={2024}
}
```
📧 **Contact**
<br>
If you have any questions, please feel free to open an issue or directly reach us out at <b>[email protected]</b>.
"""

tips = r"""
### Usage tips of InstantID
1. If you're unsatisfied with the similarity, increase the weight of controlnet_conditioning_scale (IdentityNet) and ip_adapter_scale (Adapter).
2. If the generated image is over-saturated, decrease the ip_adapter_scale. If not work, decrease controlnet_conditioning_scale.
3. If text control is not as expected, decrease ip_adapter_scale.
4. Find a good base model always makes a difference.
"""

css = '''
.gradio-container {width: 85% !important}
'''
with gr.Blocks(css=css) as demo:

    # description
    gr.Markdown(title)
    gr.Markdown(description)

    with gr.Row():
        with gr.Column():
            
            # upload face image
            face_files = gr.Files(
                        label="Upload a photo of your face",
                        file_types=["image"]
                    )
            uploaded_faces = gr.Gallery(label="Your images", visible=False, columns=1, rows=1, height=512)
            with gr.Column(visible=False) as clear_button_face:
                remove_and_reupload_faces = gr.ClearButton(value="Remove and upload new ones", components=face_files, size="sm")
            
            # optional: upload a reference pose image
            pose_files = gr.Files(
                        label="Upload a reference pose image (optional)",
                        file_types=["image"]
                    )
            uploaded_poses = gr.Gallery(label="Your images", visible=False, columns=1, rows=1, height=512)
            with gr.Column(visible=False) as clear_button_pose:
                remove_and_reupload_poses = gr.ClearButton(value="Remove and upload new ones", components=pose_files, size="sm")
            
            # prompt
            prompt = gr.Textbox(label="Prompt",
                       info="Give simple prompt is enough to achieve good face fedility",
                       placeholder="A photo of a person",
                       value="")
            
            submit = gr.Button("Submit", variant="primary")
            
            style = gr.Dropdown(label="Style template", choices=STYLE_NAMES, value=DEFAULT_STYLE_NAME)
            
            # strength
            identitynet_strength_ratio = gr.Slider(
                label="IdentityNet strength (for fedility)",
                minimum=0,
                maximum=1.5,
                step=0.05,
                value=0.80,
            )
            adapter_strength_ratio = gr.Slider(
                label="Image adapter strength (for detail)",
                minimum=0,
                maximum=1.5,
                step=0.05,
                value=0.80,
            )
            
            with gr.Accordion(open=False, label="Advanced Options"):
                negative_prompt = gr.Textbox(
                    label="Negative Prompt", 
                    placeholder="low quality",
                    value="(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
                )
                num_steps = gr.Slider( 
                    label="Number of sample steps",
                    minimum=20,
                    maximum=100,
                    step=1,
                    value=30,
                )
                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=42,
                )
                randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
                enhance_face_region = gr.Checkbox(label="Enhance non-face region", value=True)

        with gr.Column():
            gallery = gr.Gallery(label="Generated Images")
            usage_tips = gr.Markdown(label="Usage tips of InstantID", value=tips ,visible=False)

        face_files.upload(fn=swap_to_gallery, inputs=face_files, outputs=[uploaded_faces, clear_button_face, face_files])
        pose_files.upload(fn=swap_to_gallery, inputs=pose_files, outputs=[uploaded_poses, clear_button_pose, pose_files])

        remove_and_reupload_faces.click(fn=remove_back_to_files, outputs=[uploaded_faces, clear_button_face, face_files])
        remove_and_reupload_poses.click(fn=remove_back_to_files, outputs=[uploaded_poses, clear_button_pose, pose_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=[face_files, pose_files, prompt, negative_prompt, style, enhance_face_region, num_steps, identitynet_strength_ratio, adapter_strength_ratio, guidance_scale, seed],
            outputs=[gallery, usage_tips]
        )
    
    gr.Examples(
        examples=get_example(),
        inputs=[face_files, prompt, style, negative_prompt],
        run_on_click=True,
        fn=upload_example_to_gallery,
        outputs=[uploaded_faces, clear_button_face, face_files],
    )
    
    gr.Markdown(article)

demo.launch()