You're looking at a specific version of this model. Jump to the model overview.
littletry /video-nsfw-filter:5c1059f9
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
|
Video file to check for visual NSFW content.
|
|
| num_frames |
integer
|
8
Min: 1 |
Uniform samples across the declared frame range; 2+ samples include both ends. One sample selects the middle. Short videos are deduplicated.
|
| threshold_offset |
number
|
0.02
Max: 0.1 |
Additional NSFW similarity margin. Higher values are less strict; this is not a probability threshold.
|
| strict_special_care |
boolean
|
True
|
Preserve the original stricter normal-concept matching when special-care concepts match.
|
| batch_size |
integer
|
8
Min: 1 |
Maximum sampled frames per inference batch; reduce for large-resolution videos.
|
| return_frames |
None
|
none
|
Return no screenshots, only NSFW-matched samples, or all sampled frames as JPEG file outputs.
|
| include_details |
boolean
|
False
|
Include diagnostic scores, detector settings and video metadata in the report. Default returns a compact result.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array'}