You're looking at a specific version of this model. Jump to the model overview.
chenxwh /depthcrafter:1c9bfc62
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 |
|---|---|---|---|
| video |
string
|
Input video
|
|
| num_denoising_steps |
integer
|
10
Min: 1 Max: 25 |
Number of denoising steps
|
| guidance_scale |
number
|
1.2
Min: 1 Max: 1.2 |
Scale for classifier-free guidance
|
| max_res |
integer
(enum)
|
1024
Options: 512, 576, 640, 704, 768, 832, 896, 960, 1024, 1088, 1152, 1216, 1280, 1344, 1408, 1472, 1536, 1600, 1664, 1728, 1792, 1856, 1920, 1984, 2048 |
Maximum resolution
|
| process_length |
integer
|
60
Min: 1 Max: 280 |
Number of frames to process
|
| target_fps |
integer
|
15
|
fps of the output video
|
| window_size |
integer
|
110
|
Window size
|
| overlap |
integer
|
15
|
Overlap size
|
| save_npz |
boolean
|
False
|
Save npz file
|
| datast |
string
(enum)
|
open
Options: open, sintel, scannet, kitti, bonn, nyu |
Assigned resolution for specific dataset evaluation
|
| seed |
integer
|
Random seed. Leave blank to randomize the seed
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'properties': {'depth_video': {'format': 'uri',
'title': 'Depth Video',
'type': 'string'},
'npz': {'format': 'uri', 'title': 'Npz', 'type': 'string'}},
'required': ['depth_video'],
'title': 'ModelOutput',
'type': 'object'}