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 urllib.parse
import gc
from diffusers import StableDiffusionPipeline
from huggingface_hub import snapshot_download
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 even if we don't use it here
model_to_load = snapshot_download(repo_id="multimodalart/sd-fine-tunable")
safety_checker = snapshot_download(repo_id="multimodalart/sd-sc")
def zipdir(path, ziph):
# ziph is zipfile handle
for root, dirs, files in os.walk(path):
for file in files:
ziph.write(os.path.join(root, file),
os.path.relpath(os.path.join(root, file),
os.path.join(path, '..')))
def swap_text(option):
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 = 50
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. {mandatory_liability}:", '''''', 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 512x512.", freeze_for]
elif(option == "person"):
instance_prompt_example = "julcto"
freeze_for = 100
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. {mandatory_liability}:", '''
''', f"You should name the files with a unique word that represent your concept (e.g.: `{instance_prompt_example}` here). Images will be automatically cropped to 512x512.", freeze_for]
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. Name the files with the words you would like {mandatory_liability}:", '''
''', f"You should name your files with a unique word that represent your concept (e.g.: `{instance_prompt_example}` here). Images will be automatically cropped to 512x512.", freeze_for]
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]
if(uses_custom):
Training_Steps = int(inputs[-3])
else:
if(type_of_thing == "person"):
Training_Steps = file_counter*200*2
else:
Training_Steps = file_counter*200
return([gr.update(visible=True), gr.update(visible=True, value=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/1.1, 2)} seconds, or {round((Training_Steps/1.1)/60, 2)} minutes.
The setup, compression and uploading the model can take up to 20 minutes.
As the T4-Small GPU costs US$0.60 for 1h, the estimated cost for this training is US${round((((Training_Steps/1.1)/3600)+0.3+0.1)*0.60, 2)}.
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.
''')])
def train(*inputs):
torch.cuda.empty_cache()
if 'pipe' in globals():
del pipe
gc.collect()
if "IS_SHARED_UI" in os.environ:
raise gr.Error("This Space only works in duplicated instances")
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.zip"): os.remove("diffusers_model.zip")
if os.path.exists("model.ckpt"): os.remove("model.ckpt")
if os.path.exists("hastrained.success"): os.remove("hastrained.success")
file_counter = 0
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)
width, height = file.size
side_length = min(width, height)
left = (width - side_length)/2
top = (height - side_length)/2
right = (width + side_length)/2
bottom = (height + side_length)/2
image = file.crop((left, top, right, bottom))
image = image.resize((512, 512))
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]
model_name = inputs[-7]
remove_attribution_after = inputs[-6]
hf_token = inputs[-5]
if(uses_custom):
Training_Steps = int(inputs[-3])
Train_text_encoder_for = int(inputs[-2])
else:
Training_Steps = file_counter*200
if(type_of_thing == "object"):
Train_text_encoder_for=30
elif(type_of_thing == "person"):
Train_text_encoder_for=60
elif(type_of_thing == "style"):
Train_text_encoder_for=15
class_data_dir = None
stptxt = int((Training_Steps*Train_text_encoder_for)/100)
args_general = argparse.Namespace(
image_captions_filename = True,
train_text_encoder = True,
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=class_data_dir,
output_dir="output_model",
instance_prompt="",
seed=42,
resolution=512,
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,
)
print("Starting training...")
lock_file = open("intraining.lock", "w")
lock_file.close()
run_training(args_general)
gc.collect()
torch.cuda.empty_cache()
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")
print("Zipping model file...")
with zipfile.ZipFile('diffusers_model.zip', 'w', zipfile.ZIP_DEFLATED) as zipf:
zipdir('output_model/', zipf)
print("Training completed!")
if os.path.exists("intraining.lock"): os.remove("intraining.lock")
trained_file = open("hastrained.success", "w")
trained_file.close()
if(remove_attribution_after):
push(model_name, "My personal profile", hf_token, 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)
return [
gr.update(visible=True, value=["diffusers_model.zip"]), #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
]
def generate(prompt):
torch.cuda.empty_cache()
from diffusers import StableDiffusionPipeline
global pipe
pipe = StableDiffusionPipeline.from_pretrained("./output_model", torch_dtype=torch.float16)
pipe = pipe.to("cuda")
image = pipe(prompt).images[0]
return(image)
def push(model_name, where_to_upload, hf_token, 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)
{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
---
### {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)
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()
create_repo(model_id,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(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}",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.zip", "model.ckpt"])]
def convert_to_ckpt():
convert("output_model", "model.ckpt")
return gr.update(visible=True, value=["diffusers_model.zip", "model.ckpt"])
def check_status(top_description):
if os.path.exists("hastrained.success"):
update_top_tag = gr.update(value=f'''
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 settings page and downgrade your Space to a CPU Basic
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
For it to work, you have to 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 a model with less than 100 images using default settings!
If you haven't already, attribute a T4 GPU to it (via the Settings tab) and run the training below. You will be billed by the minute from when you activate the GPU until when it is turned it off.