You're looking at a specific version of this model. Jump to the model overview.
bluematter /basedlabs-watermark-remover:e3e29ec8
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
|
|
| mask |
string
|
Mask for video inpainting. Can be a static image (jpg, png) or a video (avi, mp4). If not provided, will auto-select based on video aspect ratio (16:9 landscape or 9:16 portrait).
|
|
| return_input_video |
boolean
|
False
|
Return the input video in the output.
|
| resize_ratio |
number
|
1
|
Resize scale for processing video.
|
| height |
integer
|
-1
|
Height of the processing video.
|
| width |
integer
|
-1
|
Width of the processing video.
|
| mask_dilation |
integer
|
4
|
Mask dilation for video and flow masking.
|
| ref_stride |
integer
|
10
|
Stride of global reference frames.
|
| neighbor_length |
integer
|
10
|
Length of local neighboring frames. Reduce to 5 if running out of memory.
|
| subvideo_length |
integer
|
30
|
Length of sub-video for long video inference. Lower values use less memory.
|
| raft_iter |
integer
|
20
|
Iterations for RAFT inference.
|
| mode |
None
|
video_inpainting
|
Modes: video inpainting / video outpainting. If you want to do video inpainting, you need a mask. For video outpainting, you need to set scale_h and scale_w, and mask is ignored.
|
| scale_h |
number
|
1
|
Outpainting scale of height for video_outpainting mode.
|
| scale_w |
number
|
1
|
Outpainting scale of width for video_outpainting mode.
|
| save_fps |
integer
|
24
|
Frames per second.
|
| fp16 |
boolean
|
True
|
Use fp16 (half precision) during inference. Enabled by default to save memory.
|
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'}