You're looking at a specific version of this model. Jump to the model overview.
andreasjansson /wan-1.3b-inpaint:206b0591
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 |
|---|---|---|---|
| prompt |
string
|
Prompt for inpainting the masked area
|
|
| input_video |
string
|
Original video to be inpainted
|
|
| mask_video |
string
|
Mask video (white areas will be inpainted). Leave blank for video-to-video
|
|
| negative_prompt |
string
|
|
Negative prompt
|
| strength |
number
|
0.8
Max: 1 |
Strength of inpainting effect, 1.0 is full regeneration
|
| guide_scale |
number
|
5
Min: 1 Max: 15 |
Guidance scale for prompt adherence
|
| sampling_steps |
integer
|
50
Min: 20 Max: 100 |
Number of sampling steps
|
| inpaint_fixup_steps |
integer
|
0
Max: 10 |
Number of steps for final inpaint fixup. Ignored when in video-to-video mode (when mask_video is empty)
|
| expand_mask |
integer
|
10
Max: 100 |
Expand the mask by a number of pixels
|
| frames_per_second |
integer
|
16
Min: 5 Max: 30 |
Output video FPS
|
| seed |
integer
|
-1
|
Random seed. Leave blank for random
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}