jkukul/minimax-remover
Run jkukul/minimax-remover 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 |
|---|---|---|---|
| video |
string
|
Input video file with objects to be removed
|
|
| mask |
string
|
Mask video file where white areas indicate objects to remove. See examples: https://replicate.com/ayushunleashed/minimax-remover/readme
|
|
| num_frames |
integer
|
-1
Min: -1 |
Number of frames to process (-1 = same as original video)
|
| height |
integer
|
-1
Min: -1 |
Output video height (-1 = same as original video, auto-scaled to max 1920px if needed)
|
| width |
integer
|
-1
Min: -1 |
Output video width (-1 = same as original video, auto-scaled to max 1920px if needed)
|
| fps |
integer
|
-1
Min: -1 |
Output video FPS (-1 = same as original video)
|
| num_inference_steps |
integer
|
6
Min: 1 Max: 50 |
Number of denoising steps (higher = better quality, slower. 6=fast, 8=balanced, 12=high quality)
|
| mask_dilation_iterations |
integer
|
8
Min: 1 Max: 20 |
Mask expansion iterations for robust removal (higher = more thorough removal)
|
| seed |
integer
|
Random seed for reproducible results (leave blank for random)
|
{
"type": "object",
"title": "Input",
"required": [
"video",
"mask"
],
"properties": {
"fps": {
"type": "integer",
"title": "Fps",
"default": -1,
"minimum": -1,
"x-order": 5,
"description": "Output video FPS (-1 = same as original video)"
},
"mask": {
"type": "string",
"title": "Mask",
"format": "uri",
"x-order": 1,
"description": "Mask video file where white areas indicate objects to remove. See examples: https://replicate.com/ayushunleashed/minimax-remover/readme"
},
"seed": {
"type": "integer",
"title": "Seed",
"x-order": 8,
"nullable": true,
"description": "Random seed for reproducible results (leave blank for random)"
},
"video": {
"type": "string",
"title": "Video",
"format": "uri",
"x-order": 0,
"description": "Input video file with objects to be removed"
},
"width": {
"type": "integer",
"title": "Width",
"default": -1,
"minimum": -1,
"x-order": 4,
"description": "Output video width (-1 = same as original video, auto-scaled to max 1920px if needed)"
},
"height": {
"type": "integer",
"title": "Height",
"default": -1,
"minimum": -1,
"x-order": 3,
"description": "Output video height (-1 = same as original video, auto-scaled to max 1920px if needed)"
},
"num_frames": {
"type": "integer",
"title": "Num Frames",
"default": -1,
"minimum": -1,
"x-order": 2,
"description": "Number of frames to process (-1 = same as original video)"
},
"num_inference_steps": {
"type": "integer",
"title": "Num Inference Steps",
"default": 6,
"maximum": 50,
"minimum": 1,
"x-order": 6,
"description": "Number of denoising steps (higher = better quality, slower. 6=fast, 8=balanced, 12=high quality)"
},
"mask_dilation_iterations": {
"type": "integer",
"title": "Mask Dilation Iterations",
"default": 8,
"maximum": 20,
"minimum": 1,
"x-order": 7,
"description": "Mask expansion iterations for robust removal (higher = more thorough removal)"
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
{
"type": "string",
"title": "Output",
"format": "uri"
}