You're looking at a specific version of this model. Jump to the model overview.

andreasjansson /wan-1.3b-inpaint:e1357540

Input

*string
Shift + Return to add a new line

Prompt for inpainting the masked area

*file

Original video to be inpainted

file

Mask video (white areas will be inpainted). Leave blank for video-to-video

string
Shift + Return to add a new line

Negative prompt

Default: ""

number
(minimum: 0, maximum: 1)

Strength of inpainting effect, 1.0 is full regeneration

Default: 0.8

number
(minimum: 1, maximum: 15)

Guidance scale for prompt adherence

Default: 5

integer
(minimum: 20, maximum: 100)

Number of sampling steps

Default: 50

integer
(minimum: 0, maximum: 10)

Number of steps for final inpaint fixup. Ignored when in video-to-video mode (when mask_video is empty)

Default: 0

integer
(minimum: 0, maximum: 100)

Expand the mask by a number of pixels

Default: 10

integer
(minimum: 5, maximum: 30)

Output video FPS

Default: 16

integer

Random seed. Leave blank for random

Default: -1

Output

No output yet! Press "Submit" to start a prediction.