Open-source desktop app that generates 3D meshes from images using AI models running locally on your GPU.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
Modly is a desktop application, created by Lightning Pixel, that turns photos into 3D meshes using open-source AI models that run entirely on the user's own GPU. It is aimed at asset creation and 3D printing workflows. Builds exist for Windows, Linux and Apple Silicon macOS, and AMD GPUs are supported through ROCm.
The app is built around an extension system. Each extension is a GitHub repository with a manifest.json that adds a model or process node. Official extensions cover Hunyuan3D 2 Mini (including Turbo and Fast variants), TripoSG and Trellis2 GGUF. Model weights are downloaded from Hugging Face, and a model node can pull from several repositories or share weights across nodes. The app also includes workflow graph validation before runs, and in-app smoothing and decimation of imported meshes.
Installers are on the GitHub Releases page, or the repository can be cloned and run from source (Electron/Node front end with a Python backend). Quality and hardware requirements depend on the model extension chosen. The GitHub license is reported as NOASSERTION, so the license terms should be checked in the repository, and each extension's model has its own license.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Local open-source image-to-3D mesh generator for asset creation or 3D printing. It runs entirely locally on a desktop GPU, supports Windows, Linux and Mac, and has just under 6,000 stars.
Closest neighbours by meaning, not just by category.
Model · Hi3D
Open-source image-to-3D and text-to-3D generation model from Hi3D, formerly Sparc3D, trained on ~2M curated 3D assets.
Model
Image-to-3D generator from Tsinghua and Tencent ARC Lab that builds meshes pixel-aligned to the input view.
App
Open-source local web app for running video, image, audio, music and 3D generative models on low-VRAM GPUs.
Model · Nvidia
Nvidia platform for generating character animations from text prompts, used as a source of reference motion.
Model · Apple
Apple research model that generates 3D assets with view-dependent appearance from a single input image.
Library · World Labs
World Labs tooling that turns a single image into an editable 3D environment with meshes, splats, physics and lighting.
