Akegarasu/lora-scripts

SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.

What it solves

It simplifies the process of training LoRA and Dreambooth models for Stable Diffusion, providing a user-friendly interface and pre-configured environments to avoid the complexity of manual script configuration.

How it works

The project acts as a comprehensive wrapper and GUI for kohya-ss/sd-scripts. It provides a WebUI that integrates several essential training tools into one place, including a tag editor, a WD 1.4 Tagger for dataset preparation, and Tensorboard for monitoring training progress.

Who it’s for

Artists and AI enthusiasts who want to train their own custom Stable Diffusion models without needing to write scripts or manage complex command-line arguments manually.

Highlights

  • Integrated WebUI for a streamlined training studio experience.
  • Built-in WD 1.4 Tagger and Tag Editor for easier dataset labeling.
  • Native support for both Windows and Linux via dedicated installation scripts.
  • Integrated Tensorboard support for tracking training metrics.

Related

  • Dispatch
    Using LoRA for Efficient Stable Diffusion Fine-Tuning

    Hugging Face has integrated Low-Rank Adaptation (LoRA) into the diffusers library, enabling faster Stable Diffusion fine-tuning with significantly lower VRAM requirements and model weights as small as 3 MB.

  • Project
    hollowstrawberry/kohya-colab

    A collection of Google Colab notebooks for preparing datasets and training Stable Diffusion LoRA models, including support for SDXL.

  • Project
    Nerogar/OneTrainer

    A comprehensive training suite for diffusion models that provides tools for dataset preparation, fine-tuning, and model conversion through a GUI or CLI.

  • Project
    ostris/ai-toolkit

    An all-in-one training suite for diffusion models that allows users to fine-tune image, video, and audio models on consumer-grade hardware via a GUI or CLI.

  • Project
    yolain/ComfyUI-Easy-Use

    ComfyUI‑Easy‑Use is a genuine open‑source extension for the ComfyUI node‑based UI, providing dozens of convenience nodes (loaders, prompt tools, LoRA/ControlNet helpers, noise injection, image utilities, logic/loop nodes, etc.) that streamline building Stable Diffusion and other diffusion model workflows. It supports many models (SD‑1/2, SDXL, SD‑3, Flux, Kolors, Stable Cascade, etc.), offers UI theme tweaks, and includes documentation, video tutorials, and a workflow collection. Installation is a simple git clone into ComfyUI’s `custom_nodes` folder followed by running `install.bat`.