MoGe-2

Image to 3D

Estimates metric 3D geometry from a single image, returning a point map, depth, a validity mask and the camera field of view, with surface normals on the normal-capable checkpoints. Four ViT checkpoints trade accuracy for speed, and the result can be exported as a textured GLB mesh and a colored PLY

Inference$ Commercial useFrom 1 credit per run

About MoGe-2

depth-estimationmonocular-geometrypoint-cloudsurface-normals3d-reconstruction

Pricing

A run with the default settings costs 1 credits. The exact cost updates in the playground as you change settings, and you're only charged when you press Run. Failed runs are refunded automatically.

Inputs

image_urlfiledefault: "https://storage.googleapis.com/falserverless/example_inputs/dog.png"

Input RGB image to estimate geometry (point map, depth, normals) for.

modelselectdefault: "vitl-normal"

MoGe-2 checkpoint variant. '-normal' variants additionally predict surface normals. 'vitl' is the metric model without normals; the smaller 'vitb-normal'/'vits-normal' variants trade accuracy for speed.

Options: vitl-normal, vitl, vitb-normal, vits-normal

resolution_levelintegerdefault: 9

Processing resolution level (0-9). Higher values use more tokens for finer detail but slower inference. Output size always matches the input.

fov_xnumber

Optional known horizontal field of view in degrees. If provided, MoGe uses it instead of estimating the camera FoV.

apply_maskbooleandefault: true

If true, mask out invalid (sky/background/uncertain) regions in the predicted point map and depth map.

edge_thresholdnumberdefault: 0.04

Relative threshold for removing mesh edges across depth discontinuities. Smaller values remove more edges.

export_glbbooleandefault: true

If true, export a textured .glb mesh of the reconstructed geometry.

export_plybooleandefault: true

If true, export a colored .ply point cloud of the reconstructed geometry.

enable_safety_checkerbooleandefault: true

Enable safety checking of the input image.

Related image to 3d models

Hunyuan 3D Pro Image to 3D

Generate 3D models from images with Hunyuan 3D Pro

3dhunyuan

image-to-3d

Tripo H3.1 Image to 3D

Generate high-quality 3D models from a single image using Tripo H3.1.

3d3d-generation

image-to-3d

Trellis

Generate 3D models from your images using Trellis. A native 3D generative model enabling versatile and high-quality 3D asset creation.

stylized

image-to-3d

Hyper3D - Rodin V2.5 - Image to 3D

Rodin V2.5 by Hyper3D generates realistic and production ready 3D models from text or images.

image-to-3d

Tripo H3.1 Multiview to 3D

Generate 3D models from multiple view images using Tripo H3.1.

3dmultiview-to-3d

image-to-3d

Meshy 7.1 Image to 3D

Meshy 7.1 is the latest standard model from Meshy. It generates 3D models from a single image, with optional textures and PBR maps.

3dtextures

image-to-3d

Hunyuan3d V3

Transform your photos into ultra-high-resolution 3D models in seconds. Film-quality geometry with PBR textures, ready for games, e-commerce, and 3D printing.

image-to-3d

Meshy 7.1 Multi Image to 3D

Meshy 7.1 is the latest standard model from Meshy. It generates 3D models from one to four views of the same object, with optional textures and PBR maps.

3dmulti-image

image-to-3d

Sam 3

SAM 3D enables precise 3D reconstruction of objects from real images, while accurately reconstructing their geometry and texture.

3dobject

image-to-3d

Tripo3D

State of the art Image to 3D Object generation. Generate 3D model from a single image!

stylized

image-to-3d

Tripo P2 Image to 3D

Tripo P2 generates 3D models from a single image, with optional PBR textures, adjustable face counts, and triangle or quad mesh topology.

3d3d-generation

image-to-3d

Meshy 6

Meshy 6 generates 3D models from a single image. It is an earlier standard model from Meshy; Meshy 7.1 is the latest standard model.

image-to-3d