1580158
/
kohya_ss
mirror of https://github.com/bmaltais/kohya_ss
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Update installation instructions

pull/3174/head
bmaltais 2025-03-29 10:58:54 -04:00
parent 7b527e303e
commit bb5492850a
9 changed files with 72 additions and 541 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
README.md
View File

@ -13,10 +13,13 @@ The GUI allows you to set the training parameters and generate and run the requi
- [Windows](#windows)
- [Windows Pre-requirements](#windows-pre-requirements)
- [Setup Windows](#setup-windows)
- [Optional: CUDNN 8.9.6.50](#optional-cudnn-89650)
- [Using uv based package manager](#using-uv-based-package-manager)
- [Using the pip package manager](#using-the-pip-package-manager)
- [Linux and macOS](#linux-and-macos)
- [Linux Pre-requirements](#linux-pre-requirements)
- [Setup Linux](#setup-linux)
- [Using uv based package manager](#using-uv-based-package-manager-1)
- [Using pip based package manager](#using-pip-based-package-manager)
- [Install Location](#install-location)
- [Runpod](#runpod)
- [Manual installation](#manual-installation)
@ -91,6 +94,8 @@ To install the necessary dependencies on a Windows system, follow these steps:
#### Setup Windows
##### Using uv based package manager
To set up the project, follow these steps:
1. Open a terminal and navigate to the desired installation directory.
@ -107,9 +112,25 @@ To set up the project, follow these steps:
cd kohya_ss
```
4. If you want to use the new uv based version of the script to run the GUI, you do not need to follow this step. On the other hand, if you want to use the legacy "pip" based method, please follow this next step.
##### Using the pip package manager
Run one of the following setup script by executing the following command:
To set up the project, follow these steps:
1. Open a terminal and navigate to the desired installation directory.
2. Clone the repository by running the following command:
```shell
git clone --recursive https://github.com/bmaltais/kohya_ss.git
```
3. Change into the `kohya_ss` directory:
```shell
cd kohya_ss
```
4. Run one of the following setup script by executing the following command:
For systems with only python 3.10.11 installed:
@ -125,11 +146,11 @@ To set up the project, follow these steps:
During the accelerate config step, use the default values as proposed during the configuration unless you know your hardware demands otherwise. The amount of VRAM on your GPU does not impact the values used.
#### Optional: CUDNN 8.9.6.50
5. Optional: CUDNN 8.9.6.50
The following steps are optional but will improve the learning speed for owners of NVIDIA 30X0/40X0 GPUs. These steps enable larger training batch sizes and faster training speeds.
1. Run `.\setup.bat` and select `2. (Optional) Install cudnn files (if you want to use the latest supported cudnn version)`.
Run `.\setup.bat` and select `2. (Optional) Install cudnn files (if you want to use the latest supported cudnn version)`.
### Linux and macOS
@ -149,6 +170,26 @@ To install the necessary dependencies on a Linux system, ensure that you fulfill
#### Setup Linux
##### Using uv based package manager
To set up the project on Linux or macOS, perform the following steps:
1. Open a terminal and navigate to the desired installation directory.
2. Clone the repository by running the following command:
```shell
git clone --recursive https://github.com/bmaltais/kohya_ss.git
```
3. Change into the `kohya_ss` directory:
```shell
cd kohya_ss
```
##### Using pip based package manager
To set up the project on Linux or macOS, perform the following steps:
1. Open a terminal and navigate to the desired installation directory.

110
deprecated/dreambooth_gui.py
View File

@ -1,110 +0,0 @@
import argparse
import gradio as gr
import os
from kohya_gui.dreambooth_gui import dreambooth_tab
from kohya_gui.utilities import utilities_tab
from kohya_gui.custom_logging import setup_logging
from kohya_gui.localization_ext import add_javascript
# Set up logging
log = setup_logging()
def UI(**kwargs):
add_javascript(kwargs.get("language"))
css = ""
headless = kwargs.get("headless", False)
log.info(f"headless: {headless}")
if os.path.exists("./assets/style.css"):
with open(os.path.join("./assets/style.css"), "r", encoding="utf8") as file:
log.info("Load CSS...")
css += file.read() + "\n"
interface = gr.Blocks(css=css, title="Kohya_ss GUI", theme=gr.themes.Default())
with interface:
with gr.Tab("Dreambooth"):
(
train_data_dir_input,
reg_data_dir_input,
output_dir_input,
logging_dir_input,
) = dreambooth_tab(headless=headless)
with gr.Tab("Utilities"):
utilities_tab(
train_data_dir_input=train_data_dir_input,
reg_data_dir_input=reg_data_dir_input,
output_dir_input=output_dir_input,
logging_dir_input=logging_dir_input,
enable_copy_info_button=True,
headless=headless,
)
# Show the interface
launch_kwargs = {}
username = kwargs.get("username")
password = kwargs.get("password")
server_port = kwargs.get("server_port", 0)
inbrowser = kwargs.get("inbrowser", False)
share = kwargs.get("share", False)
server_name = kwargs.get("listen")
launch_kwargs["server_name"] = server_name
if username and password:
launch_kwargs["auth"] = (username, password)
if server_port > 0:
launch_kwargs["server_port"] = server_port
if inbrowser:
launch_kwargs["inbrowser"] = inbrowser
if share:
launch_kwargs["share"] = share
interface.launch(**launch_kwargs)
if __name__ == "__main__":
# torch.cuda.set_per_process_memory_fraction(0.48)
parser = argparse.ArgumentParser()
parser.add_argument(
"--listen",
type=str,
default="127.0.0.1",
help="IP to listen on for connections to Gradio",
)
parser.add_argument(
"--username", type=str, default="", help="Username for authentication"
)
parser.add_argument(
"--password", type=str, default="", help="Password for authentication"
)
parser.add_argument(
"--server_port",
type=int,
default=0,
help="Port to run the server listener on",
)
parser.add_argument("--inbrowser", action="store_true", help="Open in browser")
parser.add_argument("--share", action="store_true", help="Share the gradio UI")
parser.add_argument(
"--headless", action="store_true", help="Is the server headless"
)
parser.add_argument(
"--language", type=str, default=None, help="Set custom language"
)
args = parser.parse_args()
UI(
username=args.username,
password=args.password,
inbrowser=args.inbrowser,
server_port=args.server_port,
share=args.share,
listen=args.listen,
headless=args.headless,
language=args.language,
)

97
deprecated/finetune_gui.py
View File

@ -1,97 +0,0 @@
import argparse
import gradio as gr
import os
from kohya_gui.utilities import utilities_tab
from kohya_gui.finetune_gui import finetune_tab
from kohya_gui.custom_logging import setup_logging
from kohya_gui.localization_ext import add_javascript
# Set up logging
log = setup_logging()
def UI(**kwargs):
add_javascript(kwargs.get("language"))
css = ""
headless = kwargs.get("headless", False)
log.info(f"headless: {headless}")
if os.path.exists("./assets/style.css"):
with open(os.path.join("./assets/style.css"), "r", encoding="utf8") as file:
log.info("Load CSS...")
css += file.read() + "\n"
interface = gr.Blocks(css=css, title="Kohya_ss GUI", theme=gr.themes.Default())
with interface:
with gr.Tab("Finetune"):
finetune_tab(headless=headless)
with gr.Tab("Utilities"):
utilities_tab(enable_dreambooth_tab=False, headless=headless)
# Show the interface
launch_kwargs = {}
username = kwargs.get("username")
password = kwargs.get("password")
server_port = kwargs.get("server_port", 0)
inbrowser = kwargs.get("inbrowser", False)
share = kwargs.get("share", False)
server_name = kwargs.get("listen")
launch_kwargs["server_name"] = server_name
if username and password:
launch_kwargs["auth"] = (username, password)
if server_port > 0:
launch_kwargs["server_port"] = server_port
if inbrowser:
launch_kwargs["inbrowser"] = inbrowser
if share:
launch_kwargs["share"] = share
interface.launch(**launch_kwargs)
if __name__ == "__main__":
# torch.cuda.set_per_process_memory_fraction(0.48)
parser = argparse.ArgumentParser()
parser.add_argument(
"--listen",
type=str,
default="127.0.0.1",
help="IP to listen on for connections to Gradio",
)
parser.add_argument(
"--username", type=str, default="", help="Username for authentication"
)
parser.add_argument(
"--password", type=str, default="", help="Password for authentication"
)
parser.add_argument(
"--server_port",
type=int,
default=0,
help="Port to run the server listener on",
)
parser.add_argument("--inbrowser", action="store_true", help="Open in browser")
parser.add_argument("--share", action="store_true", help="Share the gradio UI")
parser.add_argument(
"--headless", action="store_true", help="Is the server headless"
)
parser.add_argument(
"--language", type=str, default=None, help="Set custom language"
)
args = parser.parse_args()
UI(
username=args.username,
password=args.password,
inbrowser=args.inbrowser,
server_port=args.server_port,
share=args.share,
listen=args.listen,
headless=args.headless,
language=args.language,
)

118
deprecated/lora_gui.py
View File

@ -1,118 +0,0 @@
import argparse
import gradio as gr
import os
from kohya_gui.utilities import utilities_tab
from kohya_gui.lora_gui import lora_tab
from kohya_gui.custom_logging import setup_logging
from kohya_gui.localization_ext import add_javascript
# Set up logging
log = setup_logging()
def UI(**kwargs):
try:
# Your main code goes here
while True:
add_javascript(kwargs.get("language"))
css = ""
headless = kwargs.get("headless", False)
log.info(f"headless: {headless}")
if os.path.exists("./assets/style.css"):
with open(os.path.join("./assets/style.css"), "r", encoding="utf8") as file:
log.info("Load CSS...")
css += file.read() + "\n"
interface = gr.Blocks(
css=css, title="Kohya_ss GUI", theme=gr.themes.Default()
)
with interface:
with gr.Tab("LoRA"):
(
train_data_dir_input,
reg_data_dir_input,
output_dir_input,
logging_dir_input,
) = lora_tab(headless=headless)
with gr.Tab("Utilities"):
utilities_tab(
train_data_dir_input=train_data_dir_input,
reg_data_dir_input=reg_data_dir_input,
output_dir_input=output_dir_input,
logging_dir_input=logging_dir_input,
enable_copy_info_button=True,
headless=headless,
)
# Show the interface
launch_kwargs = {}
username = kwargs.get("username")
password = kwargs.get("password")
server_port = kwargs.get("server_port", 0)
inbrowser = kwargs.get("inbrowser", False)
share = kwargs.get("share", False)
server_name = kwargs.get("listen")
launch_kwargs["server_name"] = server_name
if username and password:
launch_kwargs["auth"] = (username, password)
if server_port > 0:
launch_kwargs["server_port"] = server_port
if inbrowser:
launch_kwargs["inbrowser"] = inbrowser
if share:
launch_kwargs["share"] = share
log.info(launch_kwargs)
interface.launch(**launch_kwargs)
except KeyboardInterrupt:
# Code to execute when Ctrl+C is pressed
print("You pressed Ctrl+C!")
if __name__ == "__main__":
# torch.cuda.set_per_process_memory_fraction(0.48)
parser = argparse.ArgumentParser()
parser.add_argument(
"--listen",
type=str,
default="127.0.0.1",
help="IP to listen on for connections to Gradio",
)
parser.add_argument(
"--username", type=str, default="", help="Username for authentication"
)
parser.add_argument(
"--password", type=str, default="", help="Password for authentication"
)
parser.add_argument(
"--server_port",
type=int,
default=0,
help="Port to run the server listener on",
)
parser.add_argument("--inbrowser", action="store_true", help="Open in browser")
parser.add_argument("--share", action="store_true", help="Share the gradio UI")
parser.add_argument(
"--headless", action="store_true", help="Is the server headless"
)
parser.add_argument(
"--language", type=str, default=None, help="Set custom language"
)
args = parser.parse_args()
UI(
username=args.username,
password=args.password,
inbrowser=args.inbrowser,
server_port=args.server_port,
share=args.share,
listen=args.listen,
headless=args.headless,
language=args.language,
)

110
deprecated/textual_inversion_gui.py
View File

@ -1,110 +0,0 @@
import argparse
import gradio as gr
import os
from kohya_gui.textual_inversion_gui import ti_tab
from kohya_gui.utilities import utilities_tab
from kohya_gui.custom_logging import setup_logging
from kohya_gui.localization_ext import add_javascript
# Set up logging
log = setup_logging()
def UI(**kwargs):
add_javascript(kwargs.get("language"))
css = ""
headless = kwargs.get("headless", False)
log.info(f"headless: {headless}")
if os.path.exists("./assets/style.css"):
with open(os.path.join("./assets/style.css"), "r", encoding="utf8") as file:
log.info("Load CSS...")
css += file.read() + "\n"
interface = gr.Blocks(css=css, title="Kohya_ss GUI", theme=gr.themes.Default())
with interface:
with gr.Tab("Dreambooth TI"):
(
train_data_dir_input,
reg_data_dir_input,
output_dir_input,
logging_dir_input,
) = ti_tab(headless=headless)
with gr.Tab("Utilities"):
utilities_tab(
train_data_dir_input=train_data_dir_input,
reg_data_dir_input=reg_data_dir_input,
output_dir_input=output_dir_input,
logging_dir_input=logging_dir_input,
enable_copy_info_button=True,
headless=headless,
)
# Show the interface
launch_kwargs = {}
username = kwargs.get("username")
password = kwargs.get("password")
server_port = kwargs.get("server_port", 0)
inbrowser = kwargs.get("inbrowser", False)
share = kwargs.get("share", False)
server_name = kwargs.get("listen")
launch_kwargs["server_name"] = server_name
if username and password:
launch_kwargs["auth"] = (username, password)
if server_port > 0:
launch_kwargs["server_port"] = server_port
if inbrowser:
launch_kwargs["inbrowser"] = inbrowser
if share:
launch_kwargs["share"] = share
interface.launch(**launch_kwargs)
if __name__ == "__main__":
# torch.cuda.set_per_process_memory_fraction(0.48)
parser = argparse.ArgumentParser()
parser.add_argument(
"--listen",
type=str,
default="127.0.0.1",
help="IP to listen on for connections to Gradio",
)
parser.add_argument(
"--username", type=str, default="", help="Username for authentication"
)
parser.add_argument(
"--password", type=str, default="", help="Password for authentication"
)
parser.add_argument(
"--server_port",
type=int,
default=0,
help="Port to run the server listener on",
)
parser.add_argument("--inbrowser", action="store_true", help="Open in browser")
parser.add_argument("--share", action="store_true", help="Share the gradio UI")
parser.add_argument(
"--headless", action="store_true", help="Is the server headless"
)
parser.add_argument(
"--language", type=str, default=None, help="Set custom language"
)
args = parser.parse_args()
UI(
username=args.username,
password=args.password,
inbrowser=args.inbrowser,
server_port=args.server_port,
share=args.share,
listen=args.listen,
headless=args.headless,
language=args.language,
)

69
deprecated/utilities_gui.py
View File

@ -1,69 +0,0 @@
import argparse
import gradio as gr
import os
from kohya_gui.utilities import utilities_tab
from kohya_gui.custom_logging import setup_logging
from kohya_gui.localization_ext import add_javascript
# Set up logging
log = setup_logging()
def UI(**kwargs):
css = ''
if os.path.exists('./assets/style.css'):
with open(os.path.join('./assets/style.css'), 'r', encoding='utf8') as file:
print('Load CSS...')
css += file.read() + '\n'
interface = gr.Blocks(css=css)
with interface:
utilities_tab()
# Show the interface
launch_kwargs = {}
if not kwargs.get('username', None) == '':
launch_kwargs['auth'] = (
kwargs.get('username', None),
kwargs.get('password', None),
)
if kwargs.get('server_port', 0) > 0:
launch_kwargs['server_port'] = kwargs.get('server_port', 0)
if kwargs.get('inbrowser', False):
launch_kwargs['inbrowser'] = kwargs.get('inbrowser', False)
print(launch_kwargs)
interface.launch(**launch_kwargs)
if __name__ == '__main__':
# torch.cuda.set_per_process_memory_fraction(0.48)
parser = argparse.ArgumentParser()
parser.add_argument(
'--username', type=str, default='', help='Username for authentication'
)
parser.add_argument(
'--password', type=str, default='', help='Password for authentication'
)
parser.add_argument(
'--server_port',
type=int,
default=0,
help='Port to run the server listener on',
)
parser.add_argument(
'--inbrowser', action='store_true', help='Open in browser'
)
args = parser.parse_args()
UI(
username=args.username,
password=args.password,
inbrowser=args.inbrowser,
server_port=args.server_port,
)

1
pyproject.toml
View File

@ -22,6 +22,7 @@ dependencies = [
"library",
"lion-pytorch==0.0.6",
"lycoris-lora==3.1.0",
"nvidia-cudnn-cu11>=8.9.5.29",
"omegaconf==2.3.0",
"onnx==1.16.1",
"onnxruntime-gpu==1.19.2",

32
setup-uv.bat
View File

@ -1,32 +0,0 @@
@echo off
IF NOT EXIST venv (
echo Creating venv...
python -m venv venv
)
:: Create the directory if it doesn't exist
mkdir ".\logs\setup" > nul 2>&1
:: Deactivate the virtual environment to prevent error
call .\venv\Scripts\deactivate.bat
call .\venv\Scripts\activate.bat
REM first make sure we have setuptools and uv available in the venv
python -m pip install --require-virtualenv --no-input -q -q setuptools uv
REM upgrade pip if needed
python -m pip install --upgrade pip -q
REM Check if the batch was started via double-click
IF /i "%comspec% /c %~0 " equ "%cmdcmdline:"=%" (
REM echo This script was started by double clicking.
cmd /k python .\setup\setup_windows.py
) ELSE (
REM echo This script was started from a command prompt.
python .\setup\setup_windows.py %*
)
:: Deactivate the virtual environment
call .\venv\Scripts\deactivate.bat

25
uv.lock
View File

@ -772,6 +772,7 @@ dependencies = [
{ name = "library" },
{ name = "lion-pytorch" },
{ name = "lycoris-lora" },
{ name = "nvidia-cudnn-cu11" },
{ name = "omegaconf" },
{ name = "onnx" },
{ name = "onnxruntime-gpu" },
@ -822,6 +823,7 @@ requires-dist = [
{ name = "library", directory = "sd-scripts" },
{ name = "lion-pytorch", specifier = "==0.0.6" },
{ name = "lycoris-lora", specifier = "==3.1.0" },
{ name = "nvidia-cudnn-cu11", specifier = ">=8.9.5.29" },
{ name = "omegaconf", specifier = "==2.3.0" },
{ name = "onnx", specifier = "==1.16.1" },
{ name = "onnxruntime-gpu", specifier = "==1.19.2" },
@ -1041,6 +1043,17 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/19/77/538f202862b9183f54108557bfda67e17603fc560c384559e769321c9d92/numpy-1.26.4-cp310-cp310-win_amd64.whl", hash = "sha256:b97fe8060236edf3662adfc2c633f56a08ae30560c56310562cb4f95500022d5", size = 15808905 },
]
[[package]]
name = "nvidia-cublas-cu11"
version = "11.11.3.6"
source = { registry = "https://pypi.org/simple" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/46/be/c222e33e60d28ecd496a46fc4d78ccae0ee28e1fd7dc705b6288b4cad27e/nvidia_cublas_cu11-11.11.3.6-py3-none-manylinux1_x86_64.whl", hash = "sha256:39fb40e8f486dd8a2ddb8fdeefe1d5b28f5b99df01c87ab3676f057a74a5a6f3", size = 417870452 },
{ url = "https://files.pythonhosted.org/packages/96/df/c5ac9ac5096355c47c606e613ecc7aa50fbccf5e0145df857d11da6464b1/nvidia_cublas_cu11-11.11.3.6-py3-none-manylinux2014_aarch64.whl", hash = "sha256:5ccae9e069a2c6be9af9cb5a0b0c6928c19c7915e390d15f598a1eead2a01a7a", size = 291428448 },
{ url = "https://files.pythonhosted.org/packages/ea/2e/9d99c60771d275ecf6c914a612e9a577f740a615bc826bec132368e1d3ae/nvidia_cublas_cu11-11.11.3.6-py3-none-manylinux2014_x86_64.whl", hash = "sha256:60252822adea5d0b10cd990a7dc7bedf7435f30ae40083c7a624a85a43225abc", size = 417870460 },
{ url = "https://files.pythonhosted.org/packages/0b/1d/7a78cd36fd5e3da4021b3ac2c2c8b2651dd72345b7c3ecc0d3e051884f50/nvidia_cublas_cu11-11.11.3.6-py3-none-win_amd64.whl", hash = "sha256:6ab12b1302bef8ac1ff4414edd1c059e57f4833abef9151683fb8f4de25900be", size = 427234740 },
]
[[package]]
name = "nvidia-cublas-cu12"
version = "12.4.5.8"
@ -1073,6 +1086,18 @@ wheels = [
{ url = "https://download.pytorch.org/whl/cu124/nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:64403288fa2136ee8e467cdc9c9427e0434110899d07c779f25b5c068934faa5" },
]
[[package]]
name = "nvidia-cudnn-cu11"
version = "9.8.0.87"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "nvidia-cublas-cu11" },
]
wheels = [
{ url = "https://files.pythonhosted.org/packages/22/32/6385ef0da5e01553e3b8ad55428fd4824cbff29ff941185082b17f030c9e/nvidia_cudnn_cu11-9.8.0.87-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:11aa6d2d6bb3aaa0ce15d06557c729c79b9ecae05679538ef2afc47b8d02bce9", size = 434538620 },
{ url = "https://files.pythonhosted.org/packages/74/2e/357359964ab4b369e060a39643e7a82fa68ffde74dabfe118654a156c2e6/nvidia_cudnn_cu11-9.8.0.87-py3-none-win_amd64.whl", hash = "sha256:fbf7bfb3a8a250f852ca49b1158bac0cf4d134af84cb3dbdf6085b6fad936632", size = 428351602 },
]
[[package]]
name = "nvidia-cudnn-cu12"
version = "9.1.0.70"