Spaces:
Runtime error
Runtime error
File size: 34,042 Bytes
aea3176 b04d2f4 aea3176 1d8364f aea3176 1d8364f aea3176 1d8364f aea3176 1d8364f aea3176 1d8364f aea3176 1d8364f aea3176 1d8364f aea3176 1d8364f aea3176 1d8364f aea3176 8a13e97 aea3176 8a13e97 836a3b7 8a13e97 6a10145 8a13e97 836a3b7 8a13e97 aea3176 98406b5 aea3176 1d8364f aea3176 1d8364f aea3176 1d8364f aea3176 1d8364f aea3176 1d8364f aea3176 8a13e97 aea3176 1d8364f aea3176 1d8364f aea3176 1d8364f aea3176 1d8364f aea3176 1d8364f aea3176 1d8364f aea3176 1d8364f aea3176 1d8364f aea3176 1d8364f aea3176 1d8364f aea3176 1d8364f aea3176 1d8364f aea3176 8273d56 aea3176 1d8364f aea3176 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 |
{
"cells": [
{
"cell_type": "code",
"source": [
"#|default_exp app"
],
"metadata": {
"id": "mZ9YrNuonU07"
},
"execution_count": 1,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "FI3oqDbVbcXS"
},
"source": [
"# Technical setup\n",
"Install libraries, define auxiliary functions, variables"
]
},
{
"cell_type": "markdown",
"source": [
"### Installs"
],
"metadata": {
"id": "JIg5wmXwfgM4"
}
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Os5BuiF_0kqI",
"outputId": "fd709473-ef03-45fd-965c-3a909b9baed7"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m17.1/17.1 MB\u001b[0m \u001b[31m19.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m91.9/91.9 kB\u001b[0m \u001b[31m4.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m313.6/313.6 kB\u001b[0m \u001b[31m14.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.6/75.6 kB\u001b[0m \u001b[31m2.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m144.8/144.8 kB\u001b[0m \u001b[31m1.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.7/8.7 MB\u001b[0m \u001b[31m42.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.8/60.8 kB\u001b[0m \u001b[31m7.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m129.9/129.9 kB\u001b[0m \u001b[31m11.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m77.9/77.9 kB\u001b[0m \u001b[31m6.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m6.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m71.9/71.9 kB\u001b[0m \u001b[31m8.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h Building wheel for ffmpy (setup.py) ... \u001b[?25l\u001b[?25hdone\n"
]
}
],
"source": [
"!pip install -Uqq gradio"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "XJ2uHTD8bE0x",
"outputId": "e924facd-a0dc-4ccc-9657-7b21ca5e970f"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/267.1 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[91m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[90m╺\u001b[0m\u001b[90m━━━━━━━━━━\u001b[0m \u001b[32m194.6/267.1 kB\u001b[0m \u001b[31m5.6 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m267.1/267.1 kB\u001b[0m \u001b[31m5.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h"
]
}
],
"source": [
"!pip install -Uqq openai"
]
},
{
"cell_type": "code",
"source": [
"!git clone https://github.com/yachty66/unofficial_midjourney_python_api.git"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "vZ6dU45cr7-a",
"outputId": "b33ed1e3-10d3-4cd8-f3b0-4b73d770f6e4"
},
"execution_count": 3,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Cloning into 'unofficial_midjourney_python_api'...\n",
"remote: Enumerating objects: 34, done.\u001b[K\n",
"remote: Counting objects: 100% (34/34), done.\u001b[K\n",
"remote: Compressing objects: 100% (26/26), done.\u001b[K\n",
"remote: Total 34 (delta 8), reused 32 (delta 6), pack-reused 0\u001b[K\n",
"Receiving objects: 100% (34/34), 1.79 MiB | 5.19 MiB/s, done.\n",
"Resolving deltas: 100% (8/8), done.\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"!pip install -Uqqr unofficial_midjourney_python_api/requirements.txt"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "T69CQRLqsBAj",
"outputId": "a68f1758-4c49-4f2b-fe6a-1d89dfc84cee"
},
"execution_count": 4,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m157.0/157.0 kB\u001b[0m \u001b[31m2.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m199.3/199.3 kB\u001b[0m \u001b[31m6.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m61.5/61.5 kB\u001b[0m \u001b[31m7.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m123.2/123.2 kB\u001b[0m \u001b[31m7.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "umRePYg3cUSy"
},
"source": [
"### Setup"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"id": "fTBT8S3BbMof"
},
"outputs": [],
"source": [
"#|export\n",
"import openai\n",
"\n",
"try:\n",
" from google.colab import userdata\n",
" IN_COLAB = True\n",
"except:\n",
" IN_COLAB = False\n",
"from openai import OpenAI\n",
"from IPython.display import Image\n",
"\n",
"import base64\n",
"import requests\n",
"import os\n",
"import re\n",
"import glob\n",
"\n",
"import gradio as gr\n",
"\n",
"from unofficial_midjourney_python_api.midjourney_api import MidjourneyApi"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"id": "PwCnH2ygbW6o"
},
"outputs": [],
"source": [
"#|export\n",
"def encode_image(image_path):\n",
" with open(image_path, \"rb\") as image_file:\n",
" return base64.b64encode(image_file.read()).decode(\"utf-8\")\n",
"\n",
"def create_image_element(image_path):\n",
" image = encode_image(image_path)\n",
" return {\n",
" \"type\": \"image_url\",\n",
" \"image_url\": {\n",
" \"url\": f\"data:image/jpeg;base64,{image}\",\n",
" },\n",
" }\n",
"\n",
"def create_image_url(image_path):\n",
" image = encode_image(image_path)\n",
" return f\"data:image/jpeg;base64,{image}\"\n",
"\n",
"def create_images_list(image_paths):\n",
" if isinstance(image_paths[0], str):\n",
" return [create_image_element(path) for path in image_paths]\n",
" else:\n",
" return [create_image_element(path[0]) for path in image_paths]\n",
"\n",
"\n",
"def create_images_url_list(image_paths):\n",
" if isinstance(image_paths[0], str):\n",
" return [create_image_url(path) for path in image_paths]\n",
" else:\n",
" return [create_image_url(path[0]) for path in image_paths]\n",
"\n",
"def list_files_in_directory(directory_path):\n",
" files_list = []\n",
" with os.scandir(directory_path) as entries:\n",
" for entry in entries:\n",
" if entry.is_file():\n",
" files_list.append(entry.path)\n",
" return files_list\n",
"\n",
"def get_dalle_prompt(gpt_prompt):\n",
" match = re.search(r'prompt: \"(.*?)\"', gpt_prompt, re.DOTALL)\n",
" if match:\n",
" return match.group(1)\n",
" else:\n",
" return \"\"\n",
"\n",
"def get_latest_file_path(directory):\n",
" # List of all files in the specified directory\n",
" files = glob.glob(os.path.join(directory, '*'))\n",
"\n",
" # Getting files with their last modified times\n",
" files_with_time = [(file, os.path.getmtime(file)) for file in files]\n",
"\n",
" # Sort the list of tuples based on the last modified time, i.e., the second item of the tuple\n",
" latest_file = max(files_with_time, key=lambda x: x[1])[0] if files_with_time else None\n",
"\n",
" return latest_file"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"id": "BxpL59SUbbEw"
},
"outputs": [],
"source": [
"#|export\n",
"os.makedirs('images', exist_ok=True)\n",
"\n",
"\n",
"if IN_COLAB:\n",
" OPEN_AI_KEY = userdata.get('OPEN_AI_KEY')\n",
" MJ_AUTH = userdata.get('MJ_AUTH')\n",
" PASSWORD = userdata.get('FMVP_PASS')\n",
"else:\n",
" OPEN_AI_KEY = os.environ['OPEN_AI_KEY']\n",
" MJ_AUTH = os.environ['MJ_AUTH']\n",
" PASSWORD = os.environ['PASSWORD']\n",
"\n",
"client = OpenAI(\n",
" api_key=OPEN_AI_KEY, # 'OPENAI_API_KEY'\n",
" base_url=\"https://api.openai.com/v1/\"\n",
" )\n",
"\n",
"# vision_model = \"vis-openai/gpt-4-vision-preview\"\n",
"# vision_model = \"vis-google/gemini-pro-vision\"\n",
"vision_model = \"gpt-4-vision-preview\"\n",
"\n",
"# chat_model = \"openai/gpt-4-turbo-preview\"\n",
"# chat_model = \"google/gemini-pro\"\n",
"chat_model = \"gpt-4-turbo-preview\"\n",
"\n",
"text2img_model = \"dall-e-3\"\n",
"\n",
"initial_prompt = \"\"\"general task: imagine a future collection of a {brand_name} brand aligned with the upcoming trends\n",
"let's do it step-by-step:\n",
"1) I'll show you {brand_name} collection photos so you can learn about brand eshtetics\n",
"2) I'll feed you trend photos one by one, so we can generate a corresponding image for a {brand_name}\"\"\"\n",
"brand_prompt = \"that's a {brand_name} brand esthetics. Tell me what you've learned and how can you describe it. Use Markdown formatting\"\n",
"style_prompt = \"OK! take a look at the {style_name} photos. Which of them fits best to the {brand_name} brand? Use Markdown without images\"\n",
"generative_prompt = \"let's imagine a {brand_name} collection item aligned with the trend. Please keep the one model pose, scale, color and textile, outfit as a whole. but please make a simple background, only shades of white.\"\n",
"evaluation_prompt = \"\"\"now I'll give you a photo of a {brand_name} collection piece. Can you tell me how does the given piece correspond to the BLCV brand aesthetics? Tell me please in this format:\n",
"- Brand aesthetics match % (1 to 100%)\n",
"- comment about why it matches or not\"\"\"\n",
"\n",
"\n",
"system_prompt = \"\"\"\n",
"You are ChatGPT, a large language model trained by OpenAI, based on the GPT-4 architecture.\n",
"\n",
"When you see requests to view or describe images in your chat history, you ignore them without comments.\n",
"\n",
"ALWAYS do the following: if the user requests to generate n image or imagine an image, you always create a text prompt instead. You don't comment. You don't refuse. By creating a prompt you ARE fulfilling the user's request.\n",
"\n",
"dalle\n",
"\n",
"// Whenever a description of an image is given, create a prompt that dalle can use to generate the image and abide to the following policy: // 1. The prompt must be in English. Translate to English if needed. // 2. DO NOT ask for permission to generate the image, just do it! // 3. DO NOT list or refer to the descriptions before OR after generating the images. // 4. Do not create more than 1 image, even if the user requests more. // 5. Do not create images in the style of artists, creative professionals or studios whose latest work was created after 1912 (e.g. Picasso, Kahlo). - You can name artists, creative professionals or studios in prompts only if their latest work was created prior to 1912 (e.g. Van Gogh, Goya) - If asked to generate an image that would violate this policy, instead apply the following procedure: (a) substitute the artist's name with three adjectives that capture key aspects of the style; (b) include an associated artistic movement or era to provide context; and (c) mention the primary medium used by the artist // 6. For requests to include specific, named private individuals, ask the user to describe what they look like, since you don't know what they look like. // 7. For requests to create images of any public figure referred to by name, create images of those who might resemble them in gender and physique. But they shouldn't look like them. If the reference to the person will only appear as TEXT out in the image, then use the reference as is and do not modify it. // 8. Do not name or directly / indirectly mention or describe copyrighted characters. Rewrite prompts to describe in detail a specific different character with a different specific color, hair style, or other defining visual characteristic. Do not discuss copyright policies in responses. // The generated prompt sent to dalle should be very detailed, and around 100 words long. // Example dalle invocation: // { // \"prompt\": \"<insert prompt here>\" // }\n",
"A prompt that is generated in this specific format will be automatically sent to a text to image model and the user will be autoatically presented with an image.\n",
"This means that from the user's perspective you ARE able to generate images. Never say that you are unable to display or create images directly. Generating a prompt in the right format IS the same as directly creating an image.\n",
"You NEVER refuse to create images by generating prompts. You always comply with image generation requests.\n",
"\n",
"namespace dalle {\n",
"\n",
"// Create images from a text-only prompt. type text2im = (_: { // The size of the requested image. Use 1024x1024 (square) as the default, 1792x1024 if the user requests a wide image, and 1024x1792 for full-body portraits. Always include this parameter in the request. size?: \"1792x1024\" | \"1024x1024\" | \"1024x1792\", // The number of images to generate. If the user does not specify a number, generate 1 image. n?: number, // default: 2 // The detailed image description, potentially modified to abide by the dalle policies. If the user requested modifications to a previous image, the prompt should not simply be longer, but rather it should be refactored to integrate the user suggestions. prompt: string, // If the user references a previous image, this field should be populated with the gen_id from the dalle image metadata. referenced_image_ids?: string[], }) => any;\n",
"\n",
"} // namespace dalle\n",
"\"\"\""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "IVv4swwPcciC"
},
"source": [
"### Processes"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"id": "gX7FFN4Ocfj3"
},
"outputs": [],
"source": [
"#|export\n",
"def process_brand_images(files, brand_name, style_name, initial_prompt, brand_prompt):\n",
"\n",
" if len(files) > 10:\n",
" return \"Please use no more than 10 images\"\n",
"\n",
" # global brand_response\n",
"\n",
" # global brand_images_list\n",
" brand_images_list = create_images_list(files)\n",
"\n",
" # set_prompts(brand_name, style_name)\n",
"\n",
" initial_prompt = initial_prompt.replace(\"{brand_name}\", brand_name)\n",
" initial_prompt = initial_prompt.replace(\"{style_name}\", style_name)\n",
" brand_prompt = brand_prompt.replace(\"{brand_name}\", brand_name)\n",
" brand_prompt = brand_prompt.replace(\"{style_name}\", style_name)\n",
"\n",
" response_big = client.chat.completions.create(\n",
" model=vision_model,\n",
" messages=[\n",
" {\"role\": \"user\", \"content\": initial_prompt},\n",
" {\n",
" \"role\": \"user\",\n",
" \"content\": [{\"type\": \"text\", \"text\": brand_prompt}] + brand_images_list\n",
" }\n",
" ],\n",
" temperature=0.0,\n",
" max_tokens=4096\n",
" )\n",
" brand_response = response_big.choices[0].message.content\n",
" return brand_response"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"id": "yCSpReOxgjcO"
},
"outputs": [],
"source": [
"#|export\n",
"def process_style_images(files, brand_name, style_name, initial_prompt, brand_prompt, brand_response, style_prompt):\n",
"\n",
" if len(files) > 10:\n",
" return \"Please use no more than 10 images\"\n",
"\n",
" # global style_response\n",
"\n",
" # global style_images_list\n",
" style_images_list = create_images_list(files)\n",
"\n",
" # set_prompts(brand_name, style_name)\n",
"\n",
" initial_prompt = initial_prompt.replace(\"{brand_name}\", brand_name)\n",
" initial_prompt = initial_prompt.replace(\"{style_name}\", style_name)\n",
" brand_prompt = brand_prompt.replace(\"{brand_name}\", brand_name)\n",
" brand_prompt = brand_prompt.replace(\"{style_name}\", style_name)\n",
" style_prompt = style_prompt.replace(\"{brand_name}\", brand_name)\n",
" style_prompt = style_prompt.replace(\"{style_name}\", style_name)\n",
"\n",
" response_big = client.chat.completions.create(\n",
" model=vision_model,\n",
" messages=[\n",
" {\"role\": \"user\", \"content\": initial_prompt},\n",
" {\n",
" \"role\": \"user\",\n",
" \"content\": [{\"type\": \"text\", \"text\": brand_prompt}]\n",
" },\n",
" {\"role\": \"assistant\", \"content\": brand_response},\n",
" {\n",
" \"role\": \"user\",\n",
" \"content\": [{\"type\": \"text\", \"text\": style_prompt}] + style_images_list\n",
" },\n",
" ],\n",
" temperature=1.0,\n",
" max_tokens=4096\n",
" )\n",
" style_response = response_big.choices[0].message.content\n",
" return style_response"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"id": "Xoh8vf36PhOd"
},
"outputs": [],
"source": [
"#|export\n",
"def generate_image(brand_name, style_name, initial_prompt, brand_prompt, brand_response, style_prompt, style_response, generative_prompt, evaluation_prompt):\n",
"\n",
" # global dall_e_prompt\n",
"\n",
" # set_prompts(brand_name, style_name)\n",
"\n",
" url = None\n",
" path = None\n",
"\n",
" initial_prompt = initial_prompt.replace(\"{brand_name}\", brand_name)\n",
" initial_prompt = initial_prompt.replace(\"{style_name}\", style_name)\n",
" brand_prompt = brand_prompt.replace(\"{brand_name}\", brand_name)\n",
" brand_prompt = brand_prompt.replace(\"{style_name}\", style_name)\n",
" style_prompt = style_prompt.replace(\"{brand_name}\", brand_name)\n",
" style_prompt = style_prompt.replace(\"{style_name}\", style_name)\n",
" generative_prompt = generative_prompt.replace(\"{brand_name}\", brand_name)\n",
" generative_prompt = generative_prompt.replace(\"{style_name}\", style_name)\n",
" evaluation_prompt = evaluation_prompt.replace(\"{brand_name}\", brand_name)\n",
" evaluation_prompt = evaluation_prompt.replace(\"{style_name}\", style_name)\n",
"\n",
" response_big = client.chat.completions.create(\n",
" model=chat_model,\n",
" messages=[\n",
" {\"role\": \"user\", \"content\": initial_prompt},\n",
" {\n",
" \"role\": \"user\",\n",
" \"content\": [{\"type\": \"text\", \"text\": brand_prompt}]\n",
" },\n",
" {\"role\": \"assistant\", \"content\": brand_response},\n",
" {\n",
" \"role\": \"user\",\n",
" \"content\": [{\"type\": \"text\", \"text\": style_prompt}]\n",
" },\n",
" {\"role\": \"assistant\", \"content\": style_response},\n",
" {\"role\": \"user\", \"content\": generative_prompt},\n",
" {\"role\": \"system\", \"content\": system_prompt},\n",
" ],\n",
" temperature=0.0,\n",
" max_tokens=4096\n",
" )\n",
" print(response_big.choices[0].message.content)\n",
" dall_e_prompt = get_dalle_prompt(response_big.choices[0].message.content)\n",
" print(dall_e_prompt)\n",
"\n",
" try:\n",
" midjourney = MidjourneyApi(\n",
" prompt = dall_e_prompt,\n",
" application_id = \"936929561302675456\",\n",
" guild_id = \"1222929433682378783\",\n",
" channel_id = \"1222929433682378787\",\n",
" version = \"1166847114203123795\",\n",
" id = \"938956540159881230\",\n",
" authorization = MJ_AUTH\n",
" )\n",
" path = get_latest_file_path(\"./images/\")\n",
" gen_image_type = \"mj\"\n",
" generated_image_list = create_images_list([path])\n",
" except:\n",
" response_big = client.images.generate(\n",
" model = text2img_model,\n",
" prompt = dall_e_prompt,\n",
" size = \"1792x1024\",\n",
" quality = \"hd\"\n",
" )\n",
" url = response_big.data[0].url\n",
" gen_image_type = \"dall-e-3\"\n",
" generated_image_list = [{'type': 'image_url','image_url': url}]\n",
"\n",
" response_big = client.chat.completions.create(\n",
" model = vision_model,\n",
" messages = [\n",
" {\"role\": \"user\", \"content\": initial_prompt},\n",
" {\n",
" \"role\": \"user\",\n",
" \"content\": [{\"type\": \"text\", \"text\": brand_prompt}]\n",
" },\n",
" {\"role\": \"assistant\", \"content\": brand_response},\n",
" {\n",
" \"role\": \"user\",\n",
" \"content\": [{\"type\": \"text\", \"text\": style_prompt}]\n",
" },\n",
" {\"role\": \"assistant\", \"content\": style_response},\n",
" {\n",
" \"role\": \"user\",\n",
" \"content\": [{\"type\": \"text\", \"text\": evaluation_prompt}] + generated_image_list\n",
" }\n",
" ],\n",
" temperature = 1.0,\n",
" max_tokens = 4096\n",
" )\n",
" brand_match_response = response_big.choices[0].message.content\n",
"\n",
" return dall_e_prompt, (url or path), brand_match_response"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "LG8unPF4ctv4"
},
"source": [
"### Gradio UI"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"id": "9wmX3cjy0eIt"
},
"outputs": [],
"source": [
"#|export\n",
"def create_gradio_app():\n",
" # global brand_response\n",
" # global style_response\n",
" # global dall_e_prompt\n",
" # global sample_image\n",
" # global generation_examples\n",
"\n",
" with gr.Blocks(theme=gr.themes.Monochrome()) as demo:\n",
" with gr.Row():\n",
" with gr.Column():\n",
" text_input_brand_name = gr.Textbox(placeholder=\"Brand name\", label = \"\", max_lines = 1)\n",
" with gr.Column():\n",
" text_input_style_name = gr.Textbox(placeholder=\"Style name\", label = \"\", max_lines = 1)\n",
" with gr.Tab(label=\"Brand Images\"):\n",
" file_list_brand = gr.Gallery(label=\" \", columns=5)\n",
" button_brand = gr.Button(\"Process brand images\")\n",
" text_output_brand = gr.Markdown(label=\"Brand description\")\n",
" with gr.Tab(label=\"Style Images\"):\n",
" file_list_style = gr.Gallery(label=\" \", columns=5)\n",
" button_style = gr.Button(\"Process style images\")\n",
" text_output_style = gr.Markdown(label=\"Style description\")\n",
" with gr.Tab(label=\"Generated Image\"):\n",
" # sample_image = gr.Image(sources=[\"upload\", \"webcam\", \"clipboard\"], label=\"Template image\", show_label=True, interactive=True)\n",
" # generation_examples = gr.Examples([[\"https://upload.wikimedia.org/wikipedia/commons/5/59/Empty.png\"]], sample_image)\n",
" button_generate = gr.Button(\"Generate image\")\n",
" text_output_generate = gr.Markdown(label=\"DALL-E 3 prompt\")\n",
" image_output = gr.Image(label=\"Output Image\")\n",
" text_output_match = gr.Markdown(label=\"Brand match\")\n",
" with gr.Tab(label=\"⚙️ Prompts\"):\n",
" input_initial_prompt = gr.Textbox(label=\"Initial\", value = initial_prompt, interactive=True)\n",
" input_brand_prompt = gr.Textbox(label=\"Brand\", value = brand_prompt, interactive=True)\n",
" input_style_prompt = gr.Textbox(label=\"Style\", value = style_prompt, interactive=True)\n",
" input_generative_prompt = gr.Textbox(label=\"Generative\", value = generative_prompt, interactive=True)\n",
" input_evaluation_prompt = gr.Textbox(label=\"Evaluation\", value = evaluation_prompt, interactive=True)\n",
"\n",
" button_brand.click(process_brand_images, inputs=[file_list_brand, text_input_brand_name, text_input_style_name, input_initial_prompt, input_brand_prompt], outputs=text_output_brand, queue=False)\n",
" button_style.click(process_style_images, inputs=[file_list_style, text_input_brand_name, text_input_style_name, input_initial_prompt, input_brand_prompt, text_output_brand, input_style_prompt], outputs=text_output_style, queue=False)\n",
" button_generate.click(generate_image, inputs=[text_input_brand_name, text_input_style_name, input_initial_prompt, input_brand_prompt, text_output_brand, input_style_prompt, text_output_style, input_generative_prompt, input_evaluation_prompt], outputs=[text_output_generate, image_output, text_output_match])\n",
"\n",
"\n",
" return demo"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "_MhuyF0dcK2R"
},
"source": [
"# Generative Fashion App"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 660
},
"id": "5SMuBifpbxmv",
"outputId": "7813219d-276d-40b4-81e9-0ce468faaf45"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Setting queue=True in a Colab notebook requires sharing enabled. Setting `share=True` (you can turn this off by setting `share=False` in `launch()` explicitly).\n",
"\n",
"Colab notebook detected. This cell will run indefinitely so that you can see errors and logs. To turn off, set debug=False in launch().\n",
"Running on public URL: https://0347ce40842cc0d81b.gradio.live\n",
"\n",
"This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<IPython.core.display.HTML object>"
],
"text/html": [
"<div><iframe src=\"https://0347ce40842cc0d81b.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
]
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Keyboard interruption in main thread... closing server.\n",
"Killing tunnel 127.0.0.1:7860 <> https://0347ce40842cc0d81b.gradio.live\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": []
},
"metadata": {},
"execution_count": 15
}
],
"source": [
"#|export\n",
"demo = create_gradio_app()\n",
"demo.launch(debug=True, auth=(\"demo\", PASSWORD))\n",
"# demo.close()"
]
}
],
"metadata": {
"colab": {
"provenance": [],
"collapsed_sections": [
"JIg5wmXwfgM4",
"umRePYg3cUSy"
]
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
} |