modly is an open source desktop application that generates 3D models from images using AI models running entirely on the user's own GPU. It supports workflows that turn photos into 3D meshes locally, without cloud-based generation services.
Project overview
By running open source AI models entirely on the user's GPU, modly removes the need for cloud services in the image-to-3D workflow — an uncommon approach for this task category, offered through both a desktop GUI and a CLI.
Project type
Model Runtime
Deployment
Refer to project documentation
License
License pending
Best for
Creators and developers who want AI image-to-3D mesh generation running on their own GPU instead of cloud services
Users comfortable installing and running a desktop application, with no coding required
Key capabilities
Turns any photo into a 3D model using open source AI models running entirely on the user's GPU.
Limitations and risks
On macOS, the application targets Apple Silicon machines.
The software is at beta version v0.4.3; expect beta-level maturity when adopting it.
Getting started
Download the latest installer for your platform from the Releases page — desktop installers are provided per platform. Then install a model extension via the Models page's 'Install from GitHub' option; note that extension model weights are downloaded from Hugging Face repositories, the only supported provider. Finally, run the Image → Generate Mesh workflow and click 'Generate 3D Model'.
Evidence and sources
GitHub project description: Desktop app to generate 3D models from images or prompt using local AI — runs entirely on your GPU
README: **Local, open source, AI-powered image-to-3D mesh generation.** Turn any photo into a 3D model using open source AI models running entirely on your GPU. Modly is a desktop applica…
Release: Modly Beta v0.4.3
README: Modly supports external model and process extensions. Each extension is a GitHub repository containing a `manifest.json` plus the runtime entry files required by its type.
README: Start with a basic workflow first. For example, on the "Workflows" tab, try: Image -> Generate Mesh -> Add to Scene. Make sure there is a connection between each of the steps. Go…