Train LoRAs and Image Models Locally

PixArt-Sigma generates images from text prompts on your own machine or a self-hosted server. It's for developers and researchers who want downloadable image models and the code to train their own.

StarDist detects individual cells and nuclei in crowded 2D microscopy images and 3D volumes. It's for researchers and bioimage analysts who need separate outlines for closely packed objects. Its shape-based approach suits objects that can be represented by star-convex polygons in 2D or polyhedra in 3D.

Cellpose is local AI software for biologists and microscopy researchers who need to identify individual cells and nuclei in images. It runs on Windows, Linux and macOS, with a graphical interface for automatic segmentation, manual annotation and correcting model results.

DeepTrack2 is an open-source Python library for researchers building image data pipelines for machine learning and digital microscopy. It brings image generation, manipulation and analysis into a modular framework that runs in your own Python environment. Its focus is scientific imaging, with applications in microscopy, optics and biophysics.

sd-scripts is a collection of Python scripts for people who want to train image models on their own hardware. It suits users comfortable working with scripts who need to adapt a model to their own images or subjects.

Musubi Tuner provides training scripts for people who want to adapt image and video generation models with their own datasets. It's aimed at users comfortable with a script-based workflow.

UNO is a local AI image generation framework for researchers and creators who want to preserve subjects from reference images in generated scenes. One model handles both single-subject images and compositions with several subjects.

ControlNet adds visual guidance to Stable Diffusion for artists and developers who need generated images to follow a reference's layout or shape. It lets a sketch, pose or scene map guide the result alongside a text prompt.

ilastik is a desktop tool for researchers who need to identify, classify or count cells and other objects in experimental images. It runs on Linux, macOS and Windows. Its main draw is interactive training: you mark examples in an image with brush strokes and see predictions as you work, without needing machine learning expertise.

BasicSR is an image and video restoration toolkit for researchers and developers building software to recover detail or reduce visual defects. It provides restoration models and pipelines for training, testing and inference.

NeMo Automodel is a Python library for researchers and developers who want to train or adapt AI models on their own GPU workstations or clusters. Its PyTorch-based training works with Hugging Face models without converting checkpoints.

Sana is a local AI image and video generation framework for creators and developers who want to generate media on their own hardware. It includes training and inference tools for working with its diffusion models.

VideoHighlighter is a desktop app for finding useful moments in long recordings without uploading footage for analysis. It helps creators cut highlights, reviewers inspect camera recordings, and interview editors locate material worth keeping.

BrushNet fills selected areas of an image using a text prompt while retaining the surrounding content. It's for developers and researchers who want local image editing with pretrained diffusion models.

FluxGym is a browser interface for training FLUX LoRAs on your own images. It's for people who want to customize image models locally, with support for GPUs with 12GB, 16GB or 20GB of VRAM.

Phosphene is a generative media studio for people creating videos on their own Mac. It combines video, still images, music and character training in one interface, with generation running on-device.

VAR is an image generation research toolkit for researchers and developers studying autoregressive models as an alternative to diffusion. It generates images through next-scale prediction, building finer detail across successive image scales.

IP-Adapter adds reference-image prompting to Stable Diffusion for artists and developers who want to guide generation with an image rather than describe every detail in words. It works with an existing text-to-image model and can combine image references with text prompts.

OneTrainer trains diffusion models on your own machine for people adapting image or video models to their own datasets. Its graphical interface brings dataset preparation, training and output previews into one application.

BiRefNet is an AI image segmentation model for developers and image workflow builders who need to separate subjects from backgrounds. It produces foreground masks for cutouts and has dedicated models for matting, where edges can include partial transparency.

Segment Anything for Microscopy adapts Meta AI's Segment Anything to biomedical images, with models fine-tuned on microscopy data. It's for researchers who need to label cells or structures such as mitochondria in electron microscopy volumes. The software runs locally on Windows, macOS and Linux and is open source under the MIT license.

Step1X Edit edits existing images from written requests. It's for developers and researchers who want to run image editing on their own hardware, with control over the model and specialized training.

Real-ESRGAN is a local AI upscaler for people enlarging images or restoring degraded images and video. It builds on ESRGAN, with dedicated models for general images, anime illustrations and animated video.

PEFT is a library for developers adapting pretrained AI models on their own hardware. It trains a small portion of a model's parameters to reduce the compute and storage costs of full fine-tuning.

Kohya's GUI is a browser interface for training image generation models, aimed at artists and model makers who want to teach a model a style or subject. It builds on Kohya's Stable Diffusion training scripts and also provides a command-line interface.

Trainable Weka Segmentation is a local image segmentation plugin and Java library for Fiji. It's for researchers and image analysts who want to teach a classifier which image regions belong to each class, then apply that model to other images or stacks. It's free and open source under GPL-3.0.

MFLUX is a Python toolkit for creators and developers who want to generate and edit images on an Apple Silicon Mac. It provides a command-line interface for working with models locally.

SimpleTuner is a diffusion model training toolkit for creators and researchers adapting image, video or audio models to their own datasets. Its web dashboard also supports teams sharing GPU workers.

Kolors generates photorealistic images from text for creators and developers who want to run image generation on their own hardware. Developed by Kuaishou, it supports Chinese and English prompts, including descriptions of Chinese cultural content.

AI Toolkit (ostris) is a training suite for people fine-tuning image and video generation models on their own hardware or rented servers. It provides a browser interface and command-line access to training jobs.

diffusion-pipe trains image and video diffusion models on your own GPU hardware. It's for people fine-tuning models that are too large to fit on a single GPU or who want to distribute training across several GPUs.

HAT Super Resolution is a local AI image upscaling project for developers, researchers, and people working with low-resolution images. It provides pretrained Hybrid Attention Transformer models and code for training your own.

MedSAM is an open-source model for medical image segmentation that runs locally, aimed at researchers and developers working with medical scans. It builds on Meta's Segment Anything model and uses bounding boxes to identify the region you want to segment. The project uses the Apache 2.0 license and supports macOS.

StyleGAN3 is NVIDIA's local AI image generation and training software for researchers and developers. Its architecture addresses generated detail that stays fixed to pixel positions instead of following the depicted objects as they move.