jasonod888/moge2v2

Outputs Depth, Normal & Point Cloud for a Given Input Image

Public
147 runs

Run jasonod888/moge2v2 with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field Type Default value Description
fp16
boolean
True
Use FP16 for faster inference (GPU recommended).
fov_x
number
Optional horizontal FoV in degrees. If omitted, MoGe estimates it.
image
string
Input image (jpg/png).
resize_to
integer
Optional resize long-side to this value (keeps aspect). 0/None = no resize.
threshold
number
0.04
Threshold for removing depth edges before meshing. Use a very large number to disable.
num_tokens
integer
Optional token override (suggested 1200-2500). If set, overrides resolution_level.
resolution_level
integer
9
Inference resolution level [0-9]. Higher captures finer detail but slower.
debug_write_local
boolean
True
If true, write outputs to /src/output (visible locally). Keep true for local dev.

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{
  "title": "Output"
}