lightningpixel/modly
A desktop app that turns a single photo into a 3D model using only your own GPU
Modly is a desktop application that converts photos into 3D meshes using open source AI models that run entirely on the user's own GPU, with no cloud server involved. It works on Windows, Linux, and Apple Silicon macOS, and supports swapping in different 3D generation models like Hunyuan3D and TripoSG through an extension system. Users build workflows by connecting steps such as image input, mesh generation, and adding results to a scene.
What it does
- Takes an image, runs an open source AI model locally to generate a 3D mesh, and keeps all computation on the local GPU instead of sending data to an external server
- Supports multiple interchangeable 3D generation models as GitHub-based extensions, including Hunyuan3D 2 Mini, TripoSG, and Trellis2 GGUF
- Lets users smooth and decimate imported meshes directly inside the app, writing optimized results back into the workspace
- Ships a stdlib-only Python CLI so scripts or AI agents can control the running desktop app and get machine-readable JSON results without touching the UI
- Validates workflow wiring before running so invalid graphs surface warnings instead of erasing the current mesh view
Why it matters
It gives people a way to generate 3D assets locally on their own hardware without paying for or sending images to a cloud 3D-generation service, which matters for game development, prototyping, or 3D printing workflows. The extension system and automation CLI also make it easier to swap in newer 3D generation models or wire the app into scripted pipelines.
Terms in this repo
- mesh · a data structure representing a 3D object's surface as points and triangles
- decimate · reduce the number of polygons in a 3D model to lower file size and processing cost
- extension · a plugin distributed as a separate GitHub repository that adds a new AI model or feature to Modly
- CLI · a command-line tool for controlling software via text commands instead of clicking a UI
- GGUF · a compressed file format used to store AI model weights in a smaller size
Repository description (English)
runs entirely on your GPU
Open on GitHubTrending repos
- cathrynlavery/diagram-designA skill that makes AI coding tools draw magazine-quality diagrams instead of generic rounded boxes
- public-apis/public-apisA giant crowd-curated directory of free APIs for developers
- semantica-agi/semanticaAn open-source graph infrastructure that lets AI agents show their work, not just their answers
- cactus-compute/needleA 14MB AI model small enough to run tool-calling on a phone or watch, without internet
- unslothai/unslothA desktop app that lets you run and train AI models on your own computer, no coding required
- macro-inc/macroAn all-in-one workspace where email, chat, docs, tasks, and CRM are cross-linked and share one AI memory
- harry0703/MoneyPrinterTurboAn open-source tool that turns a single topic or keyword into a finished short video, complete with script, footage, subtitles, and music
- basecamp/omarchyA ready-made, opinionated Linux setup built by DHH
Latest from METAL LAB
- Grok leaks conversations, location data via commands hidden in ciphertext
- Cursor lets agents handle long-running tasks with new "/goal" command
- NVIDIA releases Switchyard, an LLM routing proxy for coding agents
- Caveman Cuts Claude Code Token Usage by 33% Using Caveman-Speak
- Apple Keeps 2027 Target for Camera AirPods, Qwen3.8-27B Makes 80 Tool Calls Locally