Turn one photo into a textured 3D mesh
Open this ready-to-run workflow on Floyo. No install needed.
HOW IT WORKS
Step 1. Upload your photo. Any single image showing a clear scene or environment. Anything wider than 2048px is resized for you. Works great with: interiors · landscapes · streets · architecture
Step 2. Hit run. No prompt needed. MoGe 2 estimates the depth and geometry of your scene and builds a 3D mesh from it.
Step 3. Check your maps. You get five previews: colored depth, raw depth, OpenGL normals, DirectX normals, and a mask. Use them to check the geometry before you download.
Step 4. Download your GLB. The textured mesh saves as a standard GLB file. Ready for: Blender · Unity · Unreal · any GLB viewer
First time? Leave every setting as-is. The defaults (resolution level 9 · full mesh detail · texture on) are the right starting point for almost everyone.
Overview
This workflow turns a single photo into a textured 3D mesh using MoGe 2, an open-source geometry model from Microsoft Research (CVPR 2025 Oral). It reads one image and predicts the full 3D structure of the scene in a single pass: metric-scale depth, surface normals, and a point cloud. The workflow then converts that point cloud into a mesh and saves it as a GLB. Metric scale means the geometry comes back at real-world proportions, not just relative distance. You need one photo, not a 360 scan or a photogrammetry shoot. Upload it, hit run, and the mesh comes back in about 3 seconds. No prompt, no nodes to wire.
Who it's for: architects, game developers, and 3D artists who want single-image mesh extraction in ComfyUI without wiring the inference and mesh nodes from scratch. Not for: full 360 reconstruction. This builds geometry from one viewpoint, so what the camera cannot see is not in the mesh. Use photogrammetry if you need all sides.
Why Floyo
Floyo is the only ComfyUI platform built for teams in the browser.
Made for teams. Share run history, files, and models across your whole team. A teammate opens your exact run and picks up where you left off. No file handoffs, no version confusion.
No install, no setup. Every workflow and model is preloaded. Open it in your browser and run. Nothing to download, nothing to configure.
No local hardware. Workflows run on H100 NVL GPUs, so heavy models run fast without a card of your own. Your VRAM stops being the limit.
Open and closed models in one place. Floyo runs open-source workflows and API models side by side.
How to use (in your browser on Floyo)
Upload your photo.
Hit run. No prompt needed.
Check the depth and normal previews, then download the GLB, ready for any 3D app or engine.
Expectations The models are preloaded, so there is nothing to download. Running it needs a free Floyo account. Each run comes back in about 3 seconds, so trying several photos stays quick. Scenes with clear depth (rooms, streets, landscapes) give the cleanest meshes, while flat subjects, macro close-ups, and heavy motion blur produce softer geometry. Two settings worth knowing when you go past the defaults: raise decimation for a lighter mesh in a game engine, and adjust the discontinuity threshold if faces break at depth edges. MoGe is MIT licensed, so meshes from your own images are yours to use commercially.
Use Cases
Architecture & Interiors. Turn a photo of a room or building into a mesh you can walk through, measure, or drop into a presentation.
Game Development. Generate environment meshes from reference photos for blockouts, skybox anchors, or level design starting points.
3D & Motion Design. Pull depth and normal maps from a photo for lighting reference, displacement, or projection in Blender, Maya, or C4D.
VFX & Previz. Build rough 3D scenes from location photos for camera matching and set extension, no photogrammetry shoot needed.
What can MoGe 2 turn into a 3D mesh?
