This repository provides a Windows-focused Gradio GUI for [Kohya's Stable Diffusion trainers](https://github.com/kohya-ss/sd-scripts). The GUI allows you to set the training parameters and generate and run the required CLI commands to train the model.
If you run on Linux and would like to use the GUI, there is now a port of it as a docker container. You can find the project [here](https://github.com/P2Enjoy/kohya_ss-docker).
This step is optional but can improve the learning speed for NVIDIA 30X0/40X0 owners. It allows for larger training batch size and faster training speed.
Due to the file size, I can't host the DLLs needed for CUDNN 8.6 on Github. I strongly advise you download them for a speed boost in sample generation (almost 50% on 4090 GPU) you can download them [here](https://b1.thefileditch.ch/mwxKTEtelILoIbMbruuM.zip).
--listen: the IP address to listen on for connections to Gradio.
--username: a username for authentication.
--password: a password for authentication.
--server_port: the port to run the server listener on.
--inbrowser: opens the Gradio UI in a web browser.
--share: shares the Gradio UI.
These command line arguments can be passed to the UI function as keyword arguments. To launch the Gradio UI, run the script in a terminal with the desired command line arguments, for example:
Training a LoRA currently uses the `train_network.py` code. You can create a LoRA network by using the all-in-one `gui.cmd` or by running the dedicated LoRA training GUI with:
Once you have created the LoRA network, you can generate images via auto1111 by installing [this extension](https://github.com/kohya-ss/sd-webui-additional-networks).
This is usually related to an installation issue. Make sure you do not have any python modules installed locally that could conflict with the ones installed in the venv:
This will store your a backup file with your current locally installed pip packages and then uninstall them. Then, redo the installation instructions within the kohya_ss venv.
- Add a function to load training config with `.toml` to each training script. Thanks to Linaqruf for this great contribution!
- Specify `.toml` file with `--config_file`. `.toml` file has `key=value` entries. Keys are same as command line options. See [#241](https://github.com/kohya-ss/sd-scripts/pull/241) for details.
- All sub-sections are combined to a single dictionary (the section names are ignored.)
- Omitted arguments are the default values for command line arguments.
- Command line args override the arguments in `.toml`.
- With `--output_config` option, you can output current command line options to the `.toml` specified with`--config_file`. Please use as a template.
- Add `--lr_scheduler_type` and `--lr_scheduler_args` arguments for custom LR scheduler to each training script. Thanks to Isotr0py! [#271](https://github.com/kohya-ss/sd-scripts/pull/271)
- Same as the optimizer.
- Add sample image generation with weight and no length limit. Thanks to mio2333! [#288](https://github.com/kohya-ss/sd-scripts/pull/288)
-`( )`, `(xxxx:1.2)` and `[ ]` can be used.
- Fix exception on training model in diffusers format with `train_network.py` Thanks to orenwang! [#290](https://github.com/kohya-ss/sd-scripts/pull/290)
- Add warning if you are about to overwrite an existing model: https://github.com/bmaltais/kohya_ss/issues/404
- Add option to print LoRA trainer command without executing it
- Add support for samples during trainin via a new `Sample images config` accordion in the `Training parameters` tab.
- Added new `Additional parameters` under the `Advanced Configuration` section of the `Training parameters` tab to allow for the specifications of parameters not handles by the GUI.
- Added support for sample as a new Accordion under the `Training parameters` tab. More info about the prompt options can be found here: https://github.com/kohya-ss/sd-scripts/issues/256#issuecomment-1455005709
- There may be problems due to major changes. If you cannot revert back to the previous version when problems occur, please do not update for a while.
- Minimum metadata (module name, dim, alpha and network_args) is recorded even with `--no_metadata`, issue https://github.com/kohya-ss/sd-scripts/issues/254
-`train_network.py` supports LoRA for Conv2d-3x3 (extended to conv2d with a kernel size not 1x1).
- Same as a current version of [LoCon](https://github.com/KohakuBlueleaf/LoCon). __Thank you very much KohakuBlueleaf for your help!__
- LoCon will be enhanced in the future. Compatibility for future versions is not guaranteed.
- [Additional Networks extension](https://github.com/kohya-ss/sd-webui-additional-networks) version 0.5.0 or later is required to use 'LoRA for Conv2d-3x3' in Stable Diffusion web UI.
- __Stable Diffusion web UI built-in LoRA does not support 'LoRA for Conv2d-3x3' now. Consider carefully whether or not to use it.__
- Merging/extracting scripts also support LoRA for Conv2d-3x3.
- Free CUDA memory after sample generation to reduce VRAM usage, issue https://github.com/kohya-ss/sd-scripts/issues/260
- Empty caption doesn't cause error now, issue https://github.com/kohya-ss/sd-scripts/issues/258
- Fix sample generation is crashing in Textual Inversion training when using templates, or if height/width is not divisible by 8.
masterpiece, best quality, 1girl, in white shirts, upper body, looking at viewer, simple background --n low quality, worst quality, bad anatomy,bad composition, poor, low effort --w 768 --h 768 --d 1 --l 7.5 --s 28
# prompt 2
masterpiece, best quality, 1boy, in business suit, standing at street, looking back --n low quality, worst quality, bad anatomy,bad composition, poor, low effort --w 576 --h 832 --d 2 --l 5.5 --s 40
```
Lines beginning with `#` are comments. You can specify options for the generated image with options like `--n` after the prompt. The following can be used.
*`--n` Negative prompt up to the next option.
*`--w` Specifies the width of the generated image.
*`--h` Specifies the height of the generated image.
*`--d` Specifies the seed of the generated image.
*`--l` Specifies the CFG scale of the generated image.
*`--s` Specifies the number of steps in the generation.
The prompt weighting such as `( )` and `[ ]` are not working.
Please read [Releases](https://github.com/kohya-ss/sd-scripts/releases) for recent updates.
- Add support for `--listen` argument. This allow gradio to listen for connections from other devices on the network (or internet). For example: `gui.ps1 --listen "0.0.0.0"` will allow anyone to connect to the gradio webui.
- Removing legacy and confusing use 8bit adam chackbox. It is now configured using the Optimiser drop down list. It will be set properly based on legacy config files.
- Fix issue https://github.com/bmaltais/kohya_ss/issues/278 introduce by LoCon project switching to pip module. Make sure to run upgrade.ps1 to install the latest pip requirements for LoCon support.
- Add LoCon support (https://github.com/KohakuBlueleaf/LoCon.git) to the Dreambooth LoRA tab. This will allow to create a new type of LoRA that include conv layers as part of the LoRA... hence the name LoCon. LoCon will work with the native Auto1111 implementation of LoRA. If you want to use it with the Kohya_ss additionalNetwork you will need to install this other extension... until Kohya_ss support it natively: https://github.com/KohakuBlueleaf/a1111-sd-webui-locon
- Add support for --share argument to `kohya_gui.py` and `gui.ps1`
- Implement 8bit adam login to help with the legacy `Use 8bit adam` checkbox that is now superceided by the `Optimizer` dropdown selection. This field will be eventually removed. Kept for now for backward compatibility.
- Add `--optimizer_type` option for each training script. Please see help. Japanese documentation is [here](https://github-com.translate.goog/kohya-ss/sd-scripts/blob/main/train_network_README-ja.md?_x_tr_sl=fr&_x_tr_tl=en&_x_tr_hl=en-US&_x_tr_pto=wapp#%E3%82%AA%E3%83%97%E3%83%86%E3%82%A3%E3%83%9E%E3%82%A4%E3%82%B6%E3%81%AE%E6%8C%87%E5%AE%9A%E3%81%AB%E3%81%A4%E3%81%84%E3%81%A6).
