Spaces:
AP123
/
Configuration error

ai-avatars / app.py
AP123's picture
Update app.py
c687bcd
raw
history blame
37.6 kB
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
is_shared_ui = True if "IS_SHARED_UI" in os.environ else 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")
safety_checker = snapshot_download(repo_id="multimodalart/sd-sc")
model_to_load = model_v1
with zipfile.ZipFile("mix.zip", 'r') as zip_ref:
zip_ref.extractall(".")
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
else:
model_to_load = model_v2_512
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]
selected_model = inputs[-4]
experimental_faces = inputs[-5]
if(uses_custom):
Training_Steps = int(inputs[-3])
else:
Training_Steps = file_counter*150
if(is_spaces):
if(selected_model == "v1-5"):
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}, 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}, 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]
remove_attribution_after = inputs[-5]
experimental_face_improvement = inputs[-8]
if(uses_custom):
Training_Steps = int(inputs[-3])
Train_text_encoder_for = int(inputs[-2])
else:
Train_text_encoder_for=30
Training_Steps = file_counter*150
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
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[-4]
model_name = inputs[-6]
where_to_upload = inputs[-7]
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
global pipe_is_set
if(not pipe_is_set):
global pipe
pipe = StableDiffusionPipeline.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 style="text-align: center; max-width: 650px; margin: 0 auto;">
<div>
style="margin: auto; max-width: 7rem;">
<br />
<h1 style="font-weight: 900; font-size: 2.5rem;">
Dreambooth Web UI
</h1>
<br />
<a class="duplicate-button" style="display:inline-block" target="_blank" href="https://huggingface.co/spaces/MirageML/dreambooth?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>
</div>
<br />
<br />
<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 style="text-align: center; max-width: 650px; margin: 0 auto;">
<div>
<br />
<h1 style="font-weight: 900; font-size: 2.5rem;">
AI Generated Avatars 🔥
</h1>
<br />
<a class="duplicate-button" style="display:inline-block" target="_blank" href="https://huggingface.co/spaces/MirageML/dreambooth?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>
</div>
<br />
<br />
<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():
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!&nbsp;&nbsp;<a class="duplicate-button" style="display:inline-block" target="_blank" href="https://huggingface.co/spaces/MirageML/dreambooth?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 style="text-align: center; max-width: 650px; margin: 0 auto;">
<div>
style="margin: auto; max-width: 7rem;">
<br />
<h1 style="font-weight: 900; font-size: 2.5rem;">
Dreambooth Web UI
</h1>
<br />
<a class="duplicate-button" style="display:inline-block" target="_blank" href="https://huggingface.co/spaces/MirageML/dreambooth?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>
</div>
<br />
<br />
<p style="margin-bottom: 10px; font-size: 94%">
Customize Stable Diffusion v1 or v2 by giving it a few examples of a concept.
Based on the <a href="https://github.com/huggingface/diffusers">diffusers</a> implementation, additional techniques from <a href="https://github.com/TheLastBen/diffusers">TheLastBen</a> and <a href="https://github.com/ShivamShrirao/diffusers">ShivamShrirao</a>"
</p>
<br />
<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 style="text-align: center; max-width: 650px; margin: 0 auto;">
<div>>
<br />
<h1 style="font-weight: 900; font-size: 2.5rem;">
AI Generated Avatars 🔥
</h1>
<br />
<a class="duplicate-button" style="display:inline-block" target="_blank" href="https://huggingface.co/spaces/MirageML/dreambooth?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>
</div>
<br />
<br />
<p style="margin-bottom: 10px; font-size: 94%">
Customize Stable Diffusion v1 or v2 by giving it a few examples of a concept.
Based on the <a href="https://github.com/huggingface/diffusers">diffusers</a> implementation, additional techniques from <a href="https://github.com/TheLastBen/diffusers">TheLastBen</a> and <a href="https://github.com/ShivamShrirao/diffusers">ShivamShrirao</a>"
</p>
<br />
<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 style="text-align: center; max-width: 650px; margin: 0 auto;">
<div>
<br />
<h1 style="font-weight: 900; font-size: 2.5rem;">
AI Generated Avatars 🔥
</h1>
<br />
<a class="duplicate-button" style="display:inline-block" target="_blank" href="https://huggingface.co/spaces/MirageML/dreambooth?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>
</div>
<br />
<br />
<p style="margin-bottom: 10px; font-size: 94%">
Customize Stable Diffusion v1 or v2 by giving it a few examples of a concept.
Based on the <a href="https://github.com/huggingface/diffusers">diffusers</a> implementation, additional techniques from <a href="https://github.com/TheLastBen/diffusers">TheLastBen</a> and <a href="https://github.com/ShivamShrirao/diffusers">ShivamShrirao</a>"
</p>
</div>
''')
#Very hacky approach to emulate dynamically created Gradio components
with gr.Column() as upload_your_concept:
with gr.Column():
thing_description = gr.Markdown("Choose 10 photos of yourself, your partner, or your pet (e.g. a dog or cat) to use as input for the AI avatar generator. The AI will then create personalized avatars that look like you in any style you prefer!")
thing_description = gr.Markdown("Steps:")
thing_description = gr.Markdown("1) Attribute a GPU in the settings tab ⚙️")
thing_description = gr.Markdown("2) Get 10 photos of yourself with no other people in the background 📷")
thing_description = gr.Markdown("3) Upload those photos below 🎞️")
thing_description = gr.Markdown("4) Set your custom prompt as 'name1' and run the training 🏃‍♀️")
thing_description = gr.Markdown("5) Test your prompts and flex on social media 💪")
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('''<div style="display:flex;justify-content:center"><img src="file/cat-toy.png" /></div>''')
things_naming = gr.Markdown("When naming your custom prompt use a made up word that has low chance of the model already knowing it (e.g.: `name1` here). Images will be automatically cropped to 512x512.")
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):
with gr.Row() as what_are_you_training:
base_model_to_use = gr.Dropdown(label="Which base model would you like to use?", choices=["v1-5", "v2-512", "v2-768"], value="v1-5", interactive=True)
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
#Swap the base model
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]+[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]+[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]+[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]+[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]+[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]+[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)