Spaces:
Configuration error
Configuration error
File size: 39,282 Bytes
ca20311 f052712 ca20311 5fc2e96 ca20311 908a76c 68f4997 ca20311 d1c0e9f ca20311 d1c0e9f ca20311 f76cb2b f052712 ca20311 8e82a6c ca20311 f052712 ca20311 f052712 ca20311 c4c177a 8b41e01 8e9a88c c4c177a 772668c 4df454a 772668c 4df454a fa7c456 8e9a88c c4c177a 8fe6d83 c4c177a ca20311 c4c177a ca20311 c4c177a ca20311 c4c177a ca20311 c4c177a 0ea1b17 772668c 0ea1b17 ca20311 0ea1b17 ca20311 f9009d9 908a76c ca20311 908a76c ca20311 f9009d9 ca20311 f9009d9 ca20311 f9009d9 ca20311 |
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 |
import gradio as gr
import os
from pathlib import Path
import argparse
import shutil
from train_dreambooth import run_training
from convertosd import convert
from PIL import Image
from slugify import slugify
import requests
import torch
import zipfile
import tarfile
import urllib.parse
import gc
# from diffusers import StableDiffusionPipeline
from huggingface_hub import snapshot_download
is_spaces = True if "SPACE_ID" in os.environ else False
if(is_spaces):
is_shared_ui = True if "BAAI/dreambooth-altdiffusion" in os.environ['SPACE_ID'] else False
else:
is_shared_ui = False
is_gpu_associated = torch.cuda.is_available()
css = '''
.instruction{position: absolute; top: 0;right: 0;margin-top: 0px !important}
.arrow{position: absolute;top: 0;right: -110px;margin-top: -8px !important}
#component-4, #component-3, #component-10{min-height: 0}
.duplicate-button img{margin: 0}
'''
maximum_concepts = 3
#Pre download the files
if(is_gpu_associated):
model_v1 = snapshot_download(repo_id="multimodalart/sd-fine-tunable")
model_v2 = snapshot_download(repo_id="stabilityai/stable-diffusion-2")
model_v2_512 = snapshot_download(repo_id="stabilityai/stable-diffusion-2-base")
model_alt = snapshot_download(repo_id="BAAI/AltDiffusion")
model_alt_m9 = snapshot_download(repo_id="BAAI/AltDiffusion-m9")
safety_checker = snapshot_download(repo_id="multimodalart/sd-sc")
model_to_load = model_alt_m9
with zipfile.ZipFile("mix.zip", 'r') as zip_ref:
zip_ref.extractall(".")
def swap_text(option, base):
resize_width = 768 if base == "v2-768" else 512
mandatory_liability = "You must have the right to do so and you are liable for the images you use, example:"
if(option == "object"):
instance_prompt_example = "cttoy"
freeze_for = 30
return [f"You are going to train `object`(s), upload 5-10 images of each object you are planning on training on from different angles/perspectives. You can use services like <a style='text-decoration: underline' target='_blank' href='https://www.birme.net/?target_width={resize_width}&target_height={resize_width}'>birme</a> for smart cropping. {mandatory_liability}:", '''<img src="https://raw.githubusercontent.com/superhero-7/img_bank/main/Naruto.png" />''', f"You should name your concept with a unique made up word that has low chance of the model already knowing it (e.g.: `{instance_prompt_example}` here). Images will be automatically cropped to {resize_width}x{resize_width}.", freeze_for, gr.update(visible=False)]
elif(option == "person"):
instance_prompt_example = "julcto"
freeze_for = 70
#show_prior_preservation = True if base != "v2-768" else False
show_prior_preservation=False
if(show_prior_preservation):
prior_preservation_box_update = gr.update(visible=show_prior_preservation)
else:
prior_preservation_box_update = gr.update(visible=show_prior_preservation, value=False)
return [f"You are going to train a `person`(s), upload 10-20 images of each person you are planning on training on from different angles/perspectives. You can use services like <a style='text-decoration: underline' target='_blank' href='https://www.birme.net/?target_width={resize_width}&target_height={resize_width}'>birme</a> for smart cropping. {mandatory_liability}:", '''<img src="https://raw.githubusercontent.com/superhero-7/img_bank/main/cxk.png" />''', f"You should name your concept with a unique made up word that has low chance of the model already knowing it (e.g.: `{instance_prompt_example}` here). Images will be automatically cropped to {resize_width}x{resize_width}.", freeze_for, prior_preservation_box_update]
elif(option == "style"):
instance_prompt_example = "trsldamrl"
freeze_for = 10
return [f"You are going to train a `style`, upload 10-20 images of the style you are planning on training on. You can use services like <a style='text-decoration: underline' target='_blank' href='https://www.birme.net/?target_width={resize_width}&target_height={resize_width}'>birme</a> for smart cropping. Name the files with the words you would like {mandatory_liability}:", '''<img src="file/trsl_style.png" />''', f"You should name your concept with a unique made up word that has low chance of the model already knowing it (e.g.: `{instance_prompt_example}` here). Images will be automatically cropped to {resize_width}x{resize_width}", freeze_for, gr.update(visible=False)]
def swap_base_model(selected_model):
if(is_gpu_associated):
global model_to_load
# if(selected_model == "v1-5"):
# model_to_load = model_v1
# elif(selected_model == "v2-768"):
# model_to_load = model_v2
# elif(selected_model == "alt"):
# model_to_load = model_alt
# elif(selected_model == "alt_m9"):
# model_to_load = model_alt_m9
# else:
# model_to_load = model_v2_512
if(selected_model == "alt"):
model_to_load = model_alt
def count_files(*inputs):
file_counter = 0
concept_counter = 0
for i, input in enumerate(inputs):
if(i < maximum_concepts-1):
files = inputs[i]
if(files):
concept_counter+=1
file_counter+=len(files)
uses_custom = inputs[-1]
type_of_thing = inputs[-4]
selected_model = inputs[-5]
experimental_faces = inputs[-6]
if(uses_custom):
Training_Steps = int(inputs[-3])
else:
Training_Steps = file_counter*150
if(type_of_thing == "person" and Training_Steps > 2400):
Training_Steps = 2400 #Avoid overfitting on person faces
if(is_spaces):
if(selected_model == "v1-5" or selected_model == "alt" or selected_model == "alt_m9"):
its = 1.1
if(experimental_faces):
its = 1
elif(selected_model == "v2-512"):
its = 0.8
if(experimental_faces):
its = 0.7
elif(selected_model == "v2-768"):
its = 0.5
summary_sentence = f'''You are going to train {concept_counter} {type_of_thing}(s), with {file_counter} images for {Training_Steps} steps. The training should take around {round(Training_Steps/its, 2)} seconds, or {round((Training_Steps/its)/60, 2)} minutes.
The setup, compression and uploading the model can take up to 20 minutes.<br>As the T4-Small GPU costs US$0.60 for 1h, <span style="font-size: 120%"><b>the estimated cost for this training is below US${round((((Training_Steps/its)/3600)+0.3+0.1)*0.60, 2)}.</b></span><br><br>
If you check the box below the GPU attribution will automatically removed after training is done and the model is uploaded. If not, don't forget to come back here and swap the hardware back to CPU.<br><br>'''
else:
summary_sentence = f'''You are going to train {concept_counter} {type_of_thing}(s), with {file_counter} images for {Training_Steps} steps.<br><br>'''
return([gr.update(visible=True), gr.update(visible=True, value=summary_sentence)])
def update_steps(*files_list):
file_counter = 0
for i, files in enumerate(files_list):
if(files):
file_counter+=len(files)
return(gr.update(value=file_counter*200))
def pad_image(image):
w, h = image.size
if w == h:
return image
elif w > h:
new_image = Image.new(image.mode, (w, w), (0, 0, 0))
new_image.paste(image, (0, (w - h) // 2))
return new_image
else:
new_image = Image.new(image.mode, (h, h), (0, 0, 0))
new_image.paste(image, ((h - w) // 2, 0))
return new_image
def train(*inputs):
if is_shared_ui:
raise gr.Error("This Space only works in duplicated instances")
if not is_gpu_associated:
raise gr.Error("Please associate a T4 GPU for this Space")
torch.cuda.empty_cache()
if 'pipe' in globals():
global pipe, pipe_is_set
del pipe
pipe_is_set = False
gc.collect()
if os.path.exists("output_model"): shutil.rmtree('output_model')
if os.path.exists("instance_images"): shutil.rmtree('instance_images')
if os.path.exists("diffusers_model.tar"): os.remove("diffusers_model.tar")
if os.path.exists("model.ckpt"): os.remove("model.ckpt")
if os.path.exists("hastrained.success"): os.remove("hastrained.success")
file_counter = 0
which_model = inputs[-10]
resolution = 512 if which_model != "v2-768" else 768
for i, input in enumerate(inputs):
if(i < maximum_concepts-1):
if(input):
os.makedirs('instance_images',exist_ok=True)
files = inputs[i+(maximum_concepts*2)]
prompt = inputs[i+maximum_concepts]
if(prompt == "" or prompt == None):
raise gr.Error("You forgot to define your concept prompt")
for j, file_temp in enumerate(files):
file = Image.open(file_temp.name)
image = pad_image(file)
image = image.resize((resolution, resolution))
extension = file_temp.name.split(".")[1]
image = image.convert('RGB')
image.save(f'instance_images/{prompt}_({j+1}).jpg', format="JPEG", quality = 100)
file_counter += 1
os.makedirs('output_model',exist_ok=True)
uses_custom = inputs[-1]
type_of_thing = inputs[-4]
remove_attribution_after = inputs[-6]
experimental_face_improvement = inputs[-9]
if(uses_custom):
Training_Steps = int(inputs[-3])
Train_text_encoder_for = int(inputs[-2])
else:
if(type_of_thing == "object"):
Train_text_encoder_for=30
elif(type_of_thing == "style"):
Train_text_encoder_for=15
elif(type_of_thing == "person"):
Train_text_encoder_for=70
Training_Steps = file_counter*150
if(type_of_thing == "person" and Training_Steps > 2600):
Training_Steps = 2600 #Avoid overfitting on people's faces
stptxt = int((Training_Steps*Train_text_encoder_for)/100)
gradient_checkpointing = True if (experimental_face_improvement or which_model != "v1-5") else False
cache_latents = True if which_model != "v1-5" else False
if (type_of_thing == "object" or type_of_thing == "style" or (type_of_thing == "person" and not experimental_face_improvement)):
args_general = argparse.Namespace(
image_captions_filename = True,
train_text_encoder = True if stptxt > 0 else False,
stop_text_encoder_training = stptxt,
save_n_steps = 0,
pretrained_model_name_or_path = model_to_load,
instance_data_dir="instance_images",
class_data_dir=None,
output_dir="output_model",
instance_prompt="",
seed=42,
resolution=resolution,
mixed_precision="fp16",
train_batch_size=1,
gradient_accumulation_steps=1,
use_8bit_adam=True,
learning_rate=2e-6,
lr_scheduler="polynomial",
lr_warmup_steps = 0,
max_train_steps=Training_Steps,
gradient_checkpointing=gradient_checkpointing,
cache_latents=cache_latents,
)
print("Starting single training...")
lock_file = open("intraining.lock", "w")
lock_file.close()
run_training(args_general)
else:
args_general = argparse.Namespace(
image_captions_filename = True,
train_text_encoder = True if stptxt > 0 else False,
stop_text_encoder_training = stptxt,
save_n_steps = 0,
pretrained_model_name_or_path = model_to_load,
instance_data_dir="instance_images",
class_data_dir="Mix",
output_dir="output_model",
with_prior_preservation=True,
prior_loss_weight=1.0,
instance_prompt="",
seed=42,
resolution=resolution,
mixed_precision="fp16",
train_batch_size=1,
gradient_accumulation_steps=1,
use_8bit_adam=True,
learning_rate=2e-6,
lr_scheduler="polynomial",
lr_warmup_steps = 0,
max_train_steps=Training_Steps,
num_class_images=200,
gradient_checkpointing=gradient_checkpointing,
cache_latents=cache_latents,
)
print("Starting multi-training...")
lock_file = open("intraining.lock", "w")
lock_file.close()
run_training(args_general)
gc.collect()
torch.cuda.empty_cache()
if(which_model == "v1-5"):
print("Adding Safety Checker to the model...")
shutil.copytree(f"{safety_checker}/feature_extractor", "output_model/feature_extractor")
shutil.copytree(f"{safety_checker}/safety_checker", "output_model/safety_checker")
shutil.copy(f"model_index.json", "output_model/model_index.json")
if(not remove_attribution_after):
print("Archiving model file...")
with tarfile.open("diffusers_model.tar", "w") as tar:
tar.add("output_model", arcname=os.path.basename("output_model"))
if os.path.exists("intraining.lock"): os.remove("intraining.lock")
trained_file = open("hastrained.success", "w")
trained_file.close()
print("Training completed!")
return [
gr.update(visible=True, value=["diffusers_model.tar"]), #result
gr.update(visible=True), #try_your_model
gr.update(visible=True), #push_to_hub
gr.update(visible=True), #convert_button
gr.update(visible=False), #training_ongoing
gr.update(visible=True) #completed_training
]
else:
hf_token = inputs[-5]
model_name = inputs[-7]
where_to_upload = inputs[-8]
push(model_name, where_to_upload, hf_token, which_model, True)
hardware_url = f"https://huggingface.co/spaces/{os.environ['SPACE_ID']}/hardware"
headers = { "authorization" : f"Bearer {hf_token}"}
body = {'flavor': 'cpu-basic'}
requests.post(hardware_url, json = body, headers=headers)
pipe_is_set = False
def generate(prompt, steps):
torch.cuda.empty_cache()
# from diffusers import StableDiffusionPipeline
from diffusers import DiffusionPipeline
global pipe_is_set
if(not pipe_is_set):
global pipe
# pipe = StableDiffusionPipeline.from_pretrained("./output_model", torch_dtype=torch.float16)
pipe = DiffusionPipeline.from_pretrained("./output_model", torch_dtype=torch.float16)
pipe = pipe.to("cuda")
pipe_is_set = True
image = pipe(prompt, num_inference_steps=steps).images[0]
return(image)
def push(model_name, where_to_upload, hf_token, which_model, comes_from_automated=False):
if(not os.path.exists("model.ckpt")):
convert("output_model", "model.ckpt")
from huggingface_hub import HfApi, HfFolder, CommitOperationAdd
from huggingface_hub import create_repo
model_name_slug = slugify(model_name)
api = HfApi()
your_username = api.whoami(token=hf_token)["name"]
if(where_to_upload == "My personal profile"):
model_id = f"{your_username}/{model_name_slug}"
else:
model_id = f"sd-dreambooth-library/{model_name_slug}"
headers = {"Authorization" : f"Bearer: {hf_token}", "Content-Type": "application/json"}
response = requests.post("https://huggingface.co/organizations/sd-dreambooth-library/share/SSeOwppVCscfTEzFGQaqpfcjukVeNrKNHX", headers=headers)
images_upload = os.listdir("instance_images")
image_string = ""
instance_prompt_list = []
previous_instance_prompt = ''
for i, image in enumerate(images_upload):
instance_prompt = image.split("_")[0]
if(instance_prompt != previous_instance_prompt):
title_instance_prompt_string = instance_prompt
instance_prompt_list.append(instance_prompt)
else:
title_instance_prompt_string = ''
previous_instance_prompt = instance_prompt
image_string = f'''{title_instance_prompt_string} {"(use that on your prompt)" if title_instance_prompt_string != "" else ""}
{image_string}![{instance_prompt} {i}](https://huggingface.co/{model_id}/resolve/main/concept_images/{urllib.parse.quote(image)})'''
readme_text = f'''---
license: creativeml-openrail-m
tags:
- text-to-image
widget:
- text: {instance_prompt_list[0]}
---
### {model_name} Dreambooth model trained by {api.whoami(token=hf_token)["name"]} with [Hugging Face Dreambooth Training Space](https://huggingface.co/spaces/multimodalart/dreambooth-training) with the {which_model} base model
You run your new concept via `diffusers` [Colab Notebook for Inference](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_inference.ipynb). Don't forget to use the concept prompts!
Sample pictures of:
{image_string}
'''
#Save the readme to a file
readme_file = open("model.README.md", "w")
readme_file.write(readme_text)
readme_file.close()
#Save the token identifier to a file
text_file = open("token_identifier.txt", "w")
text_file.write(', '.join(instance_prompt_list))
text_file.close()
try:
create_repo(model_id,private=True, token=hf_token)
except:
import time
epoch_time = str(int(time.time()))
create_repo(f"{model_id}-{epoch_time}", private=True,token=hf_token)
operations = [
CommitOperationAdd(path_in_repo="token_identifier.txt", path_or_fileobj="token_identifier.txt"),
CommitOperationAdd(path_in_repo="README.md", path_or_fileobj="model.README.md"),
CommitOperationAdd(path_in_repo=f"model.ckpt",path_or_fileobj="model.ckpt")
]
api.create_commit(
repo_id=model_id,
operations=operations,
commit_message=f"Upload the model {model_name}",
token=hf_token
)
api.upload_folder(
folder_path="output_model",
repo_id=model_id,
token=hf_token
)
api.upload_folder(
folder_path="instance_images",
path_in_repo="concept_images",
repo_id=model_id,
token=hf_token
)
if is_spaces:
if(not comes_from_automated):
extra_message = "Don't forget to remove the GPU attribution after you play with it."
else:
extra_message = "The GPU has been removed automatically as requested, and you can try the model via the model page"
api.create_discussion(repo_id=os.environ['SPACE_ID'], title=f"Your model {model_name} has finished trained from the Dreambooth Train Spaces!", description=f"Your model has been successfully uploaded to: https://huggingface.co/{model_id}. {extra_message}",repo_type="space", token=hf_token)
return [gr.update(visible=True, value=f"Successfully uploaded your model. Access it [here](https://huggingface.co/{model_id})"), gr.update(visible=True, value=["diffusers_model.tar", "model.ckpt"])]
def convert_to_ckpt():
if 'pipe' in globals():
global pipe, pipe_is_set
del pipe
pipe_is_set = False
gc.collect()
convert("output_model", "model.ckpt")
return gr.update(visible=True, value=["diffusers_model.tar", "model.ckpt"])
def check_status(top_description):
if os.path.exists("hastrained.success"):
if is_spaces:
update_top_tag = gr.update(value=f'''
<div class="gr-prose" style="max-width: 80%">
<h2>Your model has finished training ✅</h2>
<p>Yay, congratulations on training your model. Scroll down to play with with it, save it (either downloading it or on the Hugging Face Hub). Once you are done, your model is safe, and you don't want to train a new one, go to the <a href="https://huggingface.co/spaces/{os.environ['SPACE_ID']}" target="_blank">settings page</a> and downgrade your Space to a CPU Basic</p>
</div>
''')
else:
update_top_tag = gr.update(value=f'''
<div class="gr-prose" style="max-width: 80%">
<h2>Your model has finished training ✅</h2>
<p>Yay, congratulations on training your model. Scroll down to play with with it, save it (either downloading it or on the Hugging Face Hub).</p>
</div>
''')
show_outputs = True
elif os.path.exists("intraining.lock"):
update_top_tag = gr.update(value='''
<div class="gr-prose" style="max-width: 80%">
<h2>Don't worry, your model is still training! ⌛</h2>
<p>You closed the tab while your model was training, but it's all good! It is still training right now. You can click the "Open logs" button above here to check the training status. Once training is done, reload this tab to interact with your model</p>
</div>
''')
show_outputs = False
else:
update_top_tag = gr.update(value=top_description)
show_outputs = False
if os.path.exists("diffusers_model.tar"):
update_files_tag = gr.update(visible=show_outputs, value=["diffusers_model.tar"])
else:
update_files_tag = gr.update(visible=show_outputs)
return [
update_top_tag, #top_description
gr.update(visible=show_outputs), #try_your_model
gr.update(visible=show_outputs), #push_to_hub
update_files_tag, #result
gr.update(visible=show_outputs), #convert_button
]
def checkbox_swap(checkbox):
return [gr.update(visible=checkbox), gr.update(visible=checkbox), gr.update(visible=checkbox), gr.update(visible=checkbox)]
with gr.Blocks(css=css) as demo:
with gr.Box():
gr.HTML(f'''
<div style="text-align: center; max-width: 650px; margin: 0 auto;">
<div
style="
display: inline-flex;
gap: 1.2rem;
font-size: 1.75rem;
margin-bottom: 40px;
width: 150px;
margin: 0 auto;
justify-content: center;
">
<a href="https://github.com/FlagAI-Open/FlagAI"><img src="https://raw.githubusercontent.com/FlagAI-Open/FlagAI/master/logo.png" alt="FlagAI" width="80%" style="margin: 0 auto;"></a>
</div>
<br />
<h1 style="font-weight: 2200; margin-bottom: 15px; margin-top: 15px; font-size: 2.7rem;">
Dreambooth Web UI
</h1>
<br />
<a class="duplicate-button" style="display:inline-block" target="_blank" href="https://huggingface.co/spaces/{os.environ['SPACE_ID']}?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a>
<p style="margin-bottom: 15px; margin-top: 15px; font-size: 94%">
This is a dreambooth Training UI for <a href="https://huggingface.co/BAAI/AltDiffusion-m9" style="text-decoration: underline;">AltDiffusion-m9 model</a>,which is a multilingual image-to-text model supported 9 languages.
You can duplicate this space to your own!
</p>
</div>
''')
with gr.Box():
if is_shared_ui:
top_description = gr.HTML(f'''
<div class="gr-prose" style="max-width: 80%">
<h2>Attention - This Space doesn't work in this shared UI</h2>
<p>For it to work, you can either run locally or duplicate the Space and run it on your own profile using a (paid) private T4 GPU for training. As each T4 costs US$0.60/h, it should cost < US$1 to train most models using default settings! <a class="duplicate-button" style="display:inline-block" target="_blank" href="https://huggingface.co/spaces/{os.environ['SPACE_ID']}?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a></p>
<img class="instruction" src="file/duplicate.png">
<img class="arrow" src="file/arrow.png" />
</div>
''')
elif(is_spaces):
if(is_gpu_associated):
top_description = gr.HTML(f'''
<div class="gr-prose" style="max-width: 80%">
<h2>You have successfully associated a GPU to the Dreambooth Training Space 🎉</h2>
<p>Certify that you got a T4. You can now train your model! You will be billed by the minute from when you activated the GPU until when it is turned it off.</p>
</div>
''')
else:
top_description = gr.HTML(f'''
<div class="gr-prose" style="max-width: 80%">
<h2>You have successfully duplicated the Dreambooth Training Space 🎉</h2>
<p>There's only one step left before you can train your model: <a href="https://huggingface.co/spaces/{os.environ['SPACE_ID']}/settings" style="text-decoration: underline" target="_blank">attribute a <b>T4 GPU</b> to it (via the Settings tab)</a> and run the training below. Other GPUs are not compatible for now. You will be billed by the minute from when you activate the GPU until when it is turned it off.</p>
</div>
''')
else:
top_description = gr.HTML(f'''
<div class="gr-prose" style="max-width: 80%">
<h2>You have successfully cloned the Dreambooth Training Space locally 🎉</h2>
<p>Do a <code>pip install requirements-local.txt</code></p>
</div>
''')
# gr.Markdown("# Dreambooth Training UI 💭")
gr.Markdown("Customize AltDiffusion and AltDiffusion-m9(ⁿᵉʷ!) by giving it a few examples of a concept. Based on the [🧨 diffusers](https://github.com/huggingface/diffusers) implementation, additional techniques from [TheLastBen](https://github.com/TheLastBen/diffusers) and [ShivamShrirao](https://github.com/ShivamShrirao/diffusers)")
with gr.Row() as what_are_you_training:
type_of_thing = gr.Dropdown(label="What would you like to train?", choices=["object", "person", "style"], value="object", interactive=True)
base_model_to_use = gr.Dropdown(label="Which base model would you like to use?", choices=["alt", "alt_m9"], value="alt_m9", interactive=True)
#Very hacky approach to emulate dynamically created Gradio components
with gr.Column() as upload_your_concept:
with gr.Box():
thing_description = gr.Markdown("You are going to train an `object`, please upload 5-10 images of the object you are planning on training on from different angles/perspectives. You must have the right to do so and you are liable for the images you use, example")
thing_experimental = gr.Checkbox(label="Improve faces (prior preservation) - can take longer training but can improve faces", visible=False, value=False)
thing_image_example = gr.HTML('''<img src="https://raw.githubusercontent.com/superhero-7/img_bank/main/Naruto.png" />''')
things_naming = gr.Markdown("You should name your concept with a unique made up word that has low chance of the model already knowing it (e.g.: `UzNrto` here). Images will be automatically cropped to 512x512.")
# with gr.Column():
file_collection = []
concept_collection = []
buttons_collection = []
delete_collection = []
is_visible = []
row = [None] * maximum_concepts
for x in range(maximum_concepts):
ordinal = lambda n: "%d%s" % (n, "tsnrhtdd"[(n // 10 % 10 != 1) * (n % 10 < 4) * n % 10::4])
if(x == 0):
visible = True
is_visible.append(gr.State(value=True))
else:
visible = False
is_visible.append(gr.State(value=False))
file_collection.append(gr.File(label=f'''Upload the images for your {ordinal(x+1) if (x>0) else ""} concept''', file_count="multiple", interactive=True, visible=visible))
with gr.Column(visible=visible) as row[x]:
concept_collection.append(gr.Textbox(label=f'''{ordinal(x+1) if (x>0) else ""} concept prompt - use a unique, made up word to avoid collisions'''))
with gr.Row():
if(x < maximum_concepts-1):
buttons_collection.append(gr.Button(value="Add +1 concept", visible=visible))
if(x > 0):
delete_collection.append(gr.Button(value=f"Delete {ordinal(x+1)} concept"))
counter_add = 1
for button in buttons_collection:
if(counter_add < len(buttons_collection)):
button.click(lambda:
[gr.update(visible=True),gr.update(visible=True), gr.update(visible=False), gr.update(visible=True), True, None],
None,
[row[counter_add], file_collection[counter_add], buttons_collection[counter_add-1], buttons_collection[counter_add], is_visible[counter_add], file_collection[counter_add]], queue=False)
else:
button.click(lambda:[gr.update(visible=True),gr.update(visible=True), gr.update(visible=False), True], None, [row[counter_add], file_collection[counter_add], buttons_collection[counter_add-1], is_visible[counter_add]], queue=False)
counter_add += 1
counter_delete = 1
for delete_button in delete_collection:
if(counter_delete < len(delete_collection)+1):
delete_button.click(lambda:[gr.update(visible=False),gr.update(visible=False), gr.update(visible=True), False], None, [file_collection[counter_delete], row[counter_delete], buttons_collection[counter_delete-1], is_visible[counter_delete]], queue=False)
counter_delete += 1
with gr.Accordion("Custom Settings", open=False):
swap_auto_calculated = gr.Checkbox(label="Use custom settings")
gr.Markdown("If not checked, the % of frozen encoder will be tuned automatically to whether you are training an `object`, `person` or `style`. The text-encoder is frozen after 10% of the steps for a style, 30% of the steps for an object and 75% trained for persons. The number of steps varies between 1400 and 2400 depending on how many images uploaded. If you see too many artifacts in your output, it means it may have overfit and you need less steps. If your results aren't really what you wanted, it may be underfitting and you need more steps.")
steps = gr.Number(label="How many steps", value=2400)
perc_txt_encoder = gr.Number(label="Percentage of the training steps the text-encoder should be trained as well", value=30)
with gr.Box(visible=False) as training_summary:
training_summary_text = gr.HTML("", visible=True, label="Training Summary")
is_advanced_visible = True if is_spaces else False
training_summary_checkbox = gr.Checkbox(label="Automatically remove paid GPU attribution and upload model to the Hugging Face Hub after training", value=True, visible=is_advanced_visible)
training_summary_model_name = gr.Textbox(label="Name of your model", visible=True)
training_summary_where_to_upload = gr.Dropdown(["My personal profile", "Public Library"], value="My personal profile", label="Upload to", visible=True)
training_summary_token_message = gr.Markdown("[A Hugging Face write access token](https://huggingface.co/settings/tokens), go to \"New token\" -> Role : Write. A regular read token won't work here.", visible=True)
training_summary_token = gr.Textbox(label="Hugging Face Write Token", type="password", visible=True)
train_btn = gr.Button("Start Training")
if(is_shared_ui):
training_ongoing = gr.Markdown("## This Space only works in duplicated instances. Please duplicate it and try again!", visible=False)
elif(not is_gpu_associated):
training_ongoing = gr.Markdown("## Oops, you haven't associated your T4 GPU to this Space. Visit the Settings tab, associate and try again.", visible=False)
else:
training_ongoing = gr.Markdown("## Training is ongoing ⌛... You can close this tab if you like or just wait. If you did not check the `Remove GPU After training`, you can come back here to try your model and upload it after training. Don't forget to remove the GPU attribution after you are done. ", visible=False)
#Post-training UI
completed_training = gr.Markdown('''# ✅ Training completed.
### Don't forget to remove the GPU attribution after you are done trying and uploading your model''', visible=False)
with gr.Row():
with gr.Box(visible=False) as try_your_model:
gr.Markdown("## Try your model")
prompt = gr.Textbox(label="Type your prompt")
result_image = gr.Image()
inference_steps = gr.Slider(minimum=1, maximum=150, value=50, step=1)
generate_button = gr.Button("Generate Image")
with gr.Box(visible=False) as push_to_hub:
gr.Markdown("## Push to Hugging Face Hub")
model_name = gr.Textbox(label="Name of your model", placeholder="Tarsila do Amaral Style")
where_to_upload = gr.Dropdown(["My personal profile", "Public Library"], label="Upload to")
gr.Markdown("[A Hugging Face write access token](https://huggingface.co/settings/tokens), go to \"New token\" -> Role : Write. A regular read token won't work here.")
hf_token = gr.Textbox(label="Hugging Face Write Token", type="password")
push_button = gr.Button("Push to the Hub")
result = gr.File(label="Download the uploaded models in the diffusers format", visible=True)
success_message_upload = gr.Markdown(visible=False)
convert_button = gr.Button("Convert to CKPT", visible=False)
#Swap the examples and the % of text encoder trained depending if it is an object, person or style
type_of_thing.change(fn=swap_text, inputs=[type_of_thing, base_model_to_use], outputs=[thing_description, thing_image_example, things_naming, perc_txt_encoder, thing_experimental], queue=False, show_progress=False)
#Swap the base model
base_model_to_use.change(fn=swap_text, inputs=[type_of_thing, base_model_to_use], outputs=[thing_description, thing_image_example, things_naming, perc_txt_encoder, thing_experimental], queue=False, show_progress=False)
base_model_to_use.change(fn=swap_base_model, inputs=base_model_to_use, outputs=[])
#Update the summary box below the UI according to how many images are uploaded and whether users are using custom settings or not
for file in file_collection:
#file.change(fn=update_steps,inputs=file_collection, outputs=steps)
file.change(fn=count_files, inputs=file_collection+[thing_experimental]+[base_model_to_use]+[type_of_thing]+[steps]+[perc_txt_encoder]+[swap_auto_calculated], outputs=[training_summary, training_summary_text], queue=False)
thing_experimental.change(fn=count_files, inputs=file_collection+[thing_experimental]+[base_model_to_use]+[type_of_thing]+[steps]+[perc_txt_encoder]+[swap_auto_calculated], outputs=[training_summary, training_summary_text], queue=False)
base_model_to_use.change(fn=count_files, inputs=file_collection+[thing_experimental]+[base_model_to_use]+[type_of_thing]+[steps]+[perc_txt_encoder]+[swap_auto_calculated], outputs=[training_summary, training_summary_text], queue=False)
steps.change(fn=count_files, inputs=file_collection+[thing_experimental]+[base_model_to_use]+[type_of_thing]+[steps]+[perc_txt_encoder]+[swap_auto_calculated], outputs=[training_summary, training_summary_text], queue=False)
perc_txt_encoder.change(fn=count_files, inputs=file_collection+[thing_experimental]+[base_model_to_use]+[type_of_thing]+[steps]+[perc_txt_encoder]+[swap_auto_calculated], outputs=[training_summary, training_summary_text], queue=False)
#Give more options if the user wants to finish everything after training
if(is_spaces):
training_summary_checkbox.change(fn=checkbox_swap, inputs=training_summary_checkbox, outputs=[training_summary_token_message, training_summary_token, training_summary_model_name, training_summary_where_to_upload],queue=False, show_progress=False)
#Add a message for while it is in training
train_btn.click(lambda:gr.update(visible=True), inputs=None, outputs=training_ongoing)
#The main train function
train_btn.click(fn=train, inputs=is_visible+concept_collection+file_collection+[base_model_to_use]+[thing_experimental]+[training_summary_where_to_upload]+[training_summary_model_name]+[training_summary_checkbox]+[training_summary_token]+[type_of_thing]+[steps]+[perc_txt_encoder]+[swap_auto_calculated], outputs=[result, try_your_model, push_to_hub, convert_button, training_ongoing, completed_training], queue=False)
#Button to generate an image from your trained model after training
generate_button.click(fn=generate, inputs=[prompt, inference_steps], outputs=result_image, queue=False)
#Button to push the model to the Hugging Face Hub
push_button.click(fn=push, inputs=[model_name, where_to_upload, hf_token, base_model_to_use], outputs=[success_message_upload, result], queue=False)
#Button to convert the model to ckpt format
convert_button.click(fn=convert_to_ckpt, inputs=[], outputs=result, queue=False)
#Checks if the training is running
demo.load(fn=check_status, inputs=top_description, outputs=[top_description, try_your_model, push_to_hub, result, convert_button], queue=False, show_progress=False)
demo.queue(default_enabled=False).launch(debug=True) |