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 point cloud.

microsoft/moge-2

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 point cloud.

Inference

Commercial use

Schema

Playground API Examples

Input

Prompt*

Additional Settings

Customize your input with more control.

1 megapixel = 1,000,000 pixels, so a 1024×1024 image counts as 2 megapixels.

Result

Idle

What would you like to do next?

1 megapixel = 1,000,000 pixels, so a 1024×1024 image counts as 2 megapixels.

microsoft/moge-2

Schema

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

Input

Image Url

Hint: Drag and drop image files from your computer, images from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: jpg, jpeg, png, webp, gif, avif, heic, heif

Additional Settings

Customize your input with more control.

Sign in to run

Result

Idle

What would you like to do next?

{
  "model_mesh": {
    "url": "https://v3b.fal.media/files/b/0ab1429d/nr00Ur3TnqhQ14-Vfty-E_tmpcl3n1a7l.glb",
    "content_type": "model/gltf-binary",
    "file_name": "tmpcl3n1a7l.glb",
    "file_size": 51374636
  },
  "point_cloud": {
    "url": "https://v3b.fal.media/files/b/0ab1429e/YceO0GhOeAKr6kq1ePtM4_tmpyq5svewh.ply",
    "content_type": "model/ply",
    "file_name": "tmpyq5svewh.ply",
    "file_size": 25444539
  },
  "depth_map": {
    "url": "https://v3b.fal.media/files/b/0ab1429d/Y7fXzx3zGJFmZ2un2wqTg_acbca3d5a0d749aa9b5afb4e0c1c2158.png",
    "content_type": "image/png",
    "file_name": "acbca3d5a0d749aa9b5afb4e0c1c2158.png",
    "file_size": 113112,
    "width": 1024,
    "height": 904
  },
  "normal_map": {
    "url": "https://v3b.fal.media/files/b/0ab1429d/h-sZHbNBh54z3BuiMpgmd_5cc25b6cdeea4bbc95d72fed7fa4f308.png",
    "content_type": "image/png",
    "file_name": "5cc25b6cdeea4bbc95d72fed7fa4f308.png",
    "file_size": 605096,
    "width": 1024,
    "height": 904
  },
  "mask": {
    "url": "https://v3b.fal.media/files/b/0ab1429d/lH_1hcyVrogzGSmv55h7m_726558fc39224225ad852b342f2f6a74.png",
    "content_type": "image/png",
    "file_name": "726558fc39224225ad852b342f2f6a74.png",
    "file_size": 5677,
    "width": 1024,
    "height": 904
  },
  "fov_x": 49.82,
  "fov_y": 44.59,
  "intrinsics": [
    [
      1.076629400253296,
      0,
      0.5
    ],
    [
      0,
      1.219544768333435,
      0.5
    ],
    [
      0,
      0,
      1
    ]
  ]
}

Billing is calculated per megapixel of the input image, rounded up to the next whole megapixel, with a minimum of 1 megapixel per request. Each megapixel costs $0.01. A 1600×1067 image (1.7 MP) costs $0.02, a 1920×1080 image (2.1 MP) costs $0.03, and the largest supported input, 2048×2048 (4.2 MP), costs $0.05. The checkpoint choice does not change the price. Depth, normal and mask maps, camera intrinsics and the optional GLB mesh and PLY point cloud are included. For $1 you can process about 50 images at 1600×1067.

Input

Prompt*

Additional Settings

Customize your input with more control.

1 megapixel = 1,000,000 pixels, so a 1024×1024 image counts as 2 megapixels.

Result

Idle

What would you like to do next?

1 megapixel = 1,000,000 pixels, so a 1024×1024 image counts as 2 megapixels.

Input

Image Url

Hint: Drag and drop image files from your computer, images from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: jpg, jpeg, png, webp, gif, avif, heic, heif

Additional Settings

Customize your input with more control.

Sign in to run

Result

Idle

What would you like to do next?

{
  "model_mesh": {
    "url": "https://v3b.fal.media/files/b/0ab1429d/nr00Ur3TnqhQ14-Vfty-E_tmpcl3n1a7l.glb",
    "content_type": "model/gltf-binary",
    "file_name": "tmpcl3n1a7l.glb",
    "file_size": 51374636
  },
  "point_cloud": {
    "url": "https://v3b.fal.media/files/b/0ab1429e/YceO0GhOeAKr6kq1ePtM4_tmpyq5svewh.ply",
    "content_type": "model/ply",
    "file_name": "tmpyq5svewh.ply",
    "file_size": 25444539
  },
  "depth_map": {
    "url": "https://v3b.fal.media/files/b/0ab1429d/Y7fXzx3zGJFmZ2un2wqTg_acbca3d5a0d749aa9b5afb4e0c1c2158.png",
    "content_type": "image/png",
    "file_name": "acbca3d5a0d749aa9b5afb4e0c1c2158.png",
    "file_size": 113112,
    "width": 1024,
    "height": 904
  },
  "normal_map": {
    "url": "https://v3b.fal.media/files/b/0ab1429d/h-sZHbNBh54z3BuiMpgmd_5cc25b6cdeea4bbc95d72fed7fa4f308.png",
    "content_type": "image/png",
    "file_name": "5cc25b6cdeea4bbc95d72fed7fa4f308.png",
    "file_size": 605096,
    "width": 1024,
    "height": 904
  },
  "mask": {
    "url": "https://v3b.fal.media/files/b/0ab1429d/lH_1hcyVrogzGSmv55h7m_726558fc39224225ad852b342f2f6a74.png",
    "content_type": "image/png",
    "file_name": "726558fc39224225ad852b342f2f6a74.png",
    "file_size": 5677,
    "width": 1024,
    "height": 904
  },
  "fov_x": 49.82,
  "fov_y": 44.59,
  "intrinsics": [
    [
      1.076629400253296,
      0,
      0.5
    ],
    [
      0,
      1.219544768333435,
      0.5
    ],
    [
      0,
      0,
      1
    ]
  ]
}

Billing is calculated per megapixel of the input image, rounded up to the next whole megapixel, with a minimum of 1 megapixel per request. Each megapixel costs $0.01. A 1600×1067 image (1.7 MP) costs $0.02, a 1920×1080 image (2.1 MP) costs $0.03, and the largest supported input, 2048×2048 (4.2 MP), costs $0.05. The checkpoint choice does not change the price. Depth, normal and mask maps, camera intrinsics and the optional GLB mesh and PLY point cloud are included. For $1 you can process about 50 images at 1600×1067.

MoGe-2 (Image to 3D) API on fal