For a tool for training diffusion model LoRAs, the first results are bmaltais/kohya_ss (Kohya's GUI is a dedicated LoRA training workbench for Stable Diffusion including SDXL that combines dataset preparation, a graphical training interface, model export, sample generation, optimizer tuning, and progress monitoring—exactly the all-in-one tool this search is after), kohya-ss/sd-scripts and automatic1111/stable-diffusion-webui (Stable Diffusion WebUI is a browser-based interface that includes a built-in training tab for LoRAs, supporting dataset preparation, captioning, model export, and progress monitoring, making it the go-to tool for training LoRA adapters on custom image styles). camenduru/stable-diffusion-webui-colab and huggingface/diffusers round out the shortlist. Compare the match explanations and check the project documentation against your requirements.
Open-source software for training custom LoRA models to replicate specific artistic styles and visual aesthetics.
kohya_ss is a graphical user interface and workbench for fine-tuning diffusion models, specifically designed for Stable Diffusion. It provides a suite of tools for training generative AI models, including specialized interfaces for creating Low-Rank Adaptation weights and training ControlNet spatial control networks. The project distinguishes itself through integrated VRAM usage optimization and hardware acceleration, featuring specific support for Intel GPUs via XPU-accelerated libraries. It implements parameter-efficient training methods and memory-saving techniques like gradient checkpoint
Kohya's GUI is a dedicated LoRA training workbench for Stable Diffusion (including SDXL) that combines dataset preparation, a graphical training interface, model export, sample generation, optimizer tuning, and progress monitoring—exactly the all-in-one tool this search is after.
sd-scripts is a suite of utilities designed for fine-tuning generative models, preprocessing datasets, and converting model weights. It provides a collection of scripts for executing Stable Diffusion training through methods such as DreamBooth, textual inversion, and full fine-tuning, alongside a framework for creating and managing Low-Rank Adaptation weights. The project features specialized capabilities for model weight conversion between different architectures and precision formats. It includes tools for merging adaptation weights into base models, extracting weights from trained models,
kohya-ss/sd-scripts is a dedicated suite of scripts for training LoRA adapters on Stable Diffusion models, covering dataset preparation, training with configurable hyperparameters, model export, and progress monitoring — it is the most widely used open-source tool for this purpose and matches the search squarely.
Stable Diffusion Web UI is a browser-based interface designed for managing text-to-image generation tasks. It provides a centralized dashboard for controlling generative processes, including native support for multi-stage model architectures to facilitate high-quality image refinement. The platform distinguishes itself through granular control over the generation process, offering tools for precise parameter management and advanced prompt engineering. Users can customize generation styles and capabilities by integrating external model-extension formats, such as textual inversions, low-rank ad
Stable Diffusion WebUI is a browser-based interface that includes a built-in training tab for LoRAs, supporting dataset preparation, captioning, model export, and progress monitoring, making it the go-to tool for training LoRA adapters on custom image styles.
This project provides a cloud-based notebook configuration for deploying a Stable Diffusion web interface. It functions as a specialized environment for image generation, incorporating a model trainer for fine-tuning weights and creating training datasets. The system emphasizes infrastructure persistence by saving software installations and model files to cloud storage, avoiding repetitive setups between sessions. It uses a tunnel-based interface to expose the web dashboard to a public URL for remote interaction. The project covers end-to-end AI workflows, including dataset preparation and t
This Colab notebook provides a complete Stable Diffusion web interface with built-in dataset preparation and LoRA training, giving you a cloud-based environment to fine‑tune adapters on custom image styles without local hardware constraints.
Diffusers is a PyTorch-based library and generative AI framework used to build, train, and deploy diffusion pipelines for producing multi-modal media. It provides a suite of tools for generating images, video, and audio from natural language descriptions, as well as specialized systems for text-to-image generation. The project differentiates itself through a modular architecture that separates noise schedulers, pretrained model blocks, and pipeline compositions. This structure allows for the construction of custom generation workflows and the ability to swap individual components of the diffu
Hugging Face Diffusers is a complete PyTorch framework for building, training, and fine‑tuning diffusion pipelines — it includes official training scripts for LoRA adapters, supports multiple backbones (Stable Diffusion, SDXL, Flux), handles dataset preparation, checkpoint resume, TensorBoard logging, and inference preview, making it the go‑to tool for training custom style LoRAs even though it is code‑first rather than GUI‑driven.
This project is a toolkit for fine-tuning and managing text-to-image diffusion models. It focuses on low-rank adaptation to create small, portable weight files that customize model styles and behaviors without modifying the entire base model. The project provides specialized utilities for model distillation using singular value decomposition to extract adapters from fully trained models, as well as tools for blending and merging multiple adapters through weight interpolation. It includes capabilities for subject inversion and pivotal tuning to increase the visual fidelity of specific identiti
This is the original LoRA implementation for Stable Diffusion, providing command-line training scripts and tools for fine-tuning with low-rank adaptation, directly matching the need for training LoRA adapters on custom image styles.
This project is a cloud-based AI deployment system and latent diffusion model trainer. It provides a framework for launching image generation interfaces and training pipelines on remote GPU infrastructure, specifically serving as a text-to-image model fine-tuner. The system features a specialized training interface for fine-tuning Stable Diffusion models on custom image datasets. It allows for the creation of personalized visual outputs by training models on specific subjects or artistic styles using a small set of reference images. The software covers generative AI deployment, custom style
Fast Stable Diffusion is a training and deployment system that supports fine-tuning Stable Diffusion models on custom image datasets, including LoRA adapters, making it a valid tool for the visitor's goal of training LoRA adapters on custom styles.
LoRA Easy Training Scripts is a desktop-based graphical interface designed to manage the end-to-end workflow of training custom machine learning models. The application serves as a centralized dashboard for preparing datasets, configuring neural network parameters, and orchestrating the execution of complex training jobs. The tool distinguishes itself by providing a visual environment that abstracts the command-line requirements of model fine-tuning. It enables users to manage training queues, allowing for the automated sequencing of multiple tasks to maximize hardware utilization. By maintai
This repository provides a graphical interface built with Pyside6 to simplify training LoRA models using the well-known sd-scripts toolchain, making it a practical fit for training adapters on custom image styles with diffusion models.
Skorch is a library that wraps PyTorch neural networks in a scikit-learn compatible interface, allowing deep learning models to be used within standard machine learning pipelines and hyperparameter optimization tools. It functions as a data adapter, training manager, and optimization tool that bridges the gap between deep learning modules and conventional machine learning workflows. The project distinguishes itself by providing a toolkit for automating the PyTorch training lifecycle, including integrated checkpointing, early stopping, and learning rate scheduling. It further enables transfer
Skorch is a general-purpose PyTorch training wrapper for scikit-learn workflows, not a dedicated LoRA training tool for diffusion models, so it lacks the specialized adapter training and diffusion model support this search targets.
Lightning is a PyTorch training framework and distributed AI training orchestrator designed to decouple core research logic from the engineering boilerplate required for model training. It functions as a deep learning workflow manager that automates the process of pretraining and finetuning models across diverse compute environments. The project distinguishes itself by providing a hardware-agnostic training wrapper, allowing the same model code to execute on CPUs, GPUs, or TPUs without modification. It further manages the scaling of workloads from single devices to multi-node clusters and ser
Lightning is a general-purpose PyTorch training framework that automates model training across hardware, but it is not a dedicated tool for LoRA adapter training on diffusion models—you would need to build that workflow on top of it, making it a building block rather than the specific tool this search aims for.
This project is a fine-tuning framework and training pipeline designed to optimize and adapt large language and vision models. It provides a specialized toolkit for parameter-efficient tuning and supervised learning, serving as both a trainer for multimodal models and a deployment tool for serving fine-tuned models via high-performance inference engines. The framework focuses on reducing memory and compute requirements by updating a small subset of model parameters. It supports a wide range of adaptation strategies, including vision-language model training to align text, image, video, and aud
This is a parameter-efficient fine-tuning framework for large language and vision-language models, not specifically designed for training LoRA adapters on diffusion models for image style customization.
Wandb is a centralized platform for machine learning experiment tracking, model registry management, and workflow orchestration. It provides a comprehensive suite of tools for logging, visualizing, and versioning training metrics, model artifacts, and hyperparameter sweeps to ensure reproducibility across development cycles. The platform also functions as an observability tool for large language model applications, enabling the tracing of execution steps, token usage, and reasoning processes. The project distinguishes itself through its event-driven automation capabilities, which allow users
Wandb is an experiment tracking and ML platform, not a LoRA training tool; it logs metrics from training runs but does not perform the actual LoRA adapter training or model export this search requires.
| Repository | Stars | Language | License | Last push |
|---|---|---|---|---|
| bmaltais/kohya_ss | 12.7K | Python | Apache-2.0 | |
| kohya-ss/sd-scripts | 7.3K | Python | Apache-2.0 | |
| 165.3K |
| Python |
| AGPL-3.0 |
| camenduru/stable-diffusion-webui-colab | 15.9K | Jupyter Notebook | Unlicense |
| huggingface/diffusers | 34.9K | Python | Apache-2.0 |
| cloneofsimo/lora | 7.5K | Jupyter Notebook | Apache-2.0 |
| thelastben/fast-stable-diffusion | 7.9K | Python | MIT |
| derrian-distro/lora_easy_training_scripts | 1.3K | Python | GPL-3.0 |
| skorch-dev/skorch | 6.2K | Jupyter Notebook | BSD-3-Clause |
| lightning-ai/lightning | 31.2K | Python | Apache-2.0 |