Spaces:
Running
Running
File size: 10,817 Bytes
78b8f5f 72164ba 78b8f5f 72164ba |
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 |
import random
import numpy as np
from style_template import styles
import gradio as gr
# global variable
MAX_SEED = np.iinfo(np.int32).max
STYLE_NAMES = list(styles.keys())
DEFAULT_STYLE_NAME = "Spring Festival"
enable_lcm_arg = False
# Path to InstantID models
face_adapter = f"./checkpoints/ip-adapter.bin"
controlnet_path = f"./checkpoints/ControlNetModel"
# controlnet-pose/canny/depth
controlnet_pose_model = "thibaud/controlnet-openpose-sdxl-1.0"
controlnet_canny_model = "diffusers/controlnet-canny-sdxl-1.0"
controlnet_depth_model = "diffusers/controlnet-depth-sdxl-1.0-small"
def toggle_lcm_ui (value):
if value:
return (
gr.update(minimum=0, maximum=100, step=1, value=5),
gr.update(minimum=0.1, maximum=20.0, step=0.1, value=1.5),
)
else:
return (
gr.update(minimum=5, maximum=100, step=1, value=30),
gr.update(minimum=0.1, maximum=20.0, step=0.1, value=5),
)
def randomize_seed_fn (seed: int, randomize_seed: bool) -> int:
if randomize_seed:
seed = random.randint(0, MAX_SEED)
return seed
def remove_tips ():
return gr.update(visible=False)
def get_example ():
case = [
[
"./examples/yann-lecun_resize.jpg",
None,
"a man",
"Spring Festival",
"(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",
"./examples/poses/pose2.jpg",
"a man flying in the sky in Mars",
"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",
"./examples/poses/pose4.jpg",
"a man doing a silly pose wearing a suite",
"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",
"./examples/poses/pose3.jpg",
"a man sit on a chair",
"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",
"./examples/poses/pose.jpg",
"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 run_for_examples (face_file, pose_file, prompt, style, negative_prompt):
return generate_image(
face_file,
pose_file,
prompt,
negative_prompt,
style,
20, # num_steps
0.8, # identitynet_strength_ratio
0.8, # adapter_strength_ratio
0.4, # pose_strength
0.3, # canny_strength
0.5, # depth_strength
["pose", "canny"], # controlnet_selection
5.0, # guidance_scale
42, # seed
"EulerDiscreteScheduler", # scheduler
False, # enable_LCM
True, # enable_Face_Region
)
def generate_image (
face_image_path,
pose_image_path,
prompt,
negative_prompt,
style_name,
num_steps,
identitynet_strength_ratio,
adapter_strength_ratio,
pose_strength,
canny_strength,
depth_strength,
controlnet_selection,
guidance_scale,
seed,
scheduler,
enable_LCM,
enhance_face_region,
progress=gr.Progress(track_tqdm=True),
):
return None, 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>
We are organizing a Spring Festival event with HuggingFace from 2.7 to 2.25, and you can now generate pictures of Spring Festival costumes. Happy Dragon Year 🐲 ! Share the joy with your family.<br>
How to use:<br>
1. Upload an image with a face. For images with multiple faces, we will only detect the largest face. Ensure the face is not too small and is clearly visible without significant obstructions or blurring.
2. (Optional) You can upload another image as a reference for the face pose. If you don't, we will use the first detected face image to extract facial landmarks. If you use a cropped face at step 1, it is recommended to upload it to define a new face pose.
3. (Optional) You can select multiple ControlNet models to control the generation process. The default is to use the IdentityNet only. The ControlNet models include pose skeleton, canny, and depth. You can adjust the strength of each ControlNet model to control the generation process.
4. Enter a text prompt, as done in normal text-to-image models.
5. Click the <b>Submit</b> button to begin customization.
6. Share your customized photo with your friends and enjoy! 😊"""
article = r"""
---
"""
tips = r"""
### Usage tips of InstantID
1. If you're not satisfied with the similarity, try increasing the weight of "IdentityNet Strength" and "Adapter Strength."
2. If you feel that the saturation is too high, first decrease the Adapter strength. If it remains too high, then decrease the IdentityNet strength.
3. If you find that text control is not as expected, decrease Adapter strength.
4. If you find that realistic style is not good enough, go for our Github repo and use a more realistic base model.
"""
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():
with gr.Row(equal_height=True):
# upload face image
face_file = gr.Image(
label="Upload a photo of your face", type="filepath"
)
# optional: upload a reference pose image
pose_file = gr.Image(
label="Upload a reference pose image (Optional)",
type="filepath",
)
# prompt
prompt = gr.Textbox(
label="Prompt",
info="Give simple prompt is enough to achieve good face fidelity",
placeholder="A photo of a person",
value="",
)
submit = gr.Button("Submit", variant="primary")
enable_LCM = gr.Checkbox(
label="Enable Fast Inference with LCM", value=enable_lcm_arg,
info="LCM speeds up the inference step, the trade-off is the quality of the generated image. It performs better with portrait face images rather than distant faces",
)
style = gr.Dropdown(
label="Style template",
choices=STYLE_NAMES,
value=DEFAULT_STYLE_NAME,
)
# strength
identitynet_strength_ratio = gr.Slider(
label="IdentityNet strength (for fidelity)",
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("Controlnet"):
controlnet_selection = gr.CheckboxGroup(
["pose", "canny", "depth"], label="Controlnet", value=["pose"],
info="Use pose for skeleton inference, canny for edge detection, and depth for depth map estimation. You can try all three to control the generation process"
)
pose_strength = gr.Slider(
label="Pose strength",
minimum=0,
maximum=1.5,
step=0.05,
value=0.40,
)
canny_strength = gr.Slider(
label="Canny strength",
minimum=0,
maximum=1.5,
step=0.05,
value=0.40,
)
depth_strength = gr.Slider(
label="Depth strength",
minimum=0,
maximum=1.5,
step=0.05,
value=0.40,
)
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=1,
maximum=100,
step=1,
value=5 if enable_lcm_arg else 30,
)
guidance_scale = gr.Slider(
label="Guidance scale",
minimum=0.1,
maximum=20.0,
step=0.1,
value=0.0 if enable_lcm_arg else 5.0,
)
seed = gr.Slider(
label="Seed",
minimum=0,
maximum=MAX_SEED,
step=1,
value=42,
)
schedulers = [
"DEISMultistepScheduler",
"HeunDiscreteScheduler",
"EulerDiscreteScheduler",
"DPMSolverMultistepScheduler",
"DPMSolverMultistepScheduler-Karras",
"DPMSolverMultistepScheduler-Karras-SDE",
]
scheduler = gr.Dropdown(
label="Schedulers",
choices=schedulers,
value="EulerDiscreteScheduler",
)
randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
enhance_face_region = gr.Checkbox(label="Enhance non-face region", value=True)
with gr.Column(scale=1):
gallery = gr.Image(label="Generated Images")
usage_tips = gr.Markdown(
label="InstantID Usage Tips", value=tips, visible=False
)
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_file,
pose_file,
prompt,
negative_prompt,
style,
num_steps,
identitynet_strength_ratio,
adapter_strength_ratio,
pose_strength,
canny_strength,
depth_strength,
controlnet_selection,
guidance_scale,
seed,
scheduler,
enable_LCM,
enhance_face_region,
],
outputs=[gallery, usage_tips],
)
enable_LCM.input(
fn=toggle_lcm_ui,
inputs=[enable_LCM],
outputs=[num_steps, guidance_scale],
queue=False,
)
gr.Examples(
examples=get_example(),
inputs=[face_file, pose_file, prompt, style, negative_prompt],
fn=run_for_examples,
outputs=[gallery, usage_tips],
cache_examples=True,
)
gr.Markdown(article)
demo.queue(api_open=False)
demo.launch()
|