You're looking at a specific version of this model. Jump to the model overview.
zsxkib /stable-video-face-restoration:63512c77
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 (e.g. MP4).
|
|
| tasks |
string
(enum)
|
face-restoration
Options: face-restoration, face-restoration-and-colorization, face-restoration-and-colorization-and-inpainting |
Which restoration tasks to apply.
|
| mask |
string
|
An inpainting mask image (white areas will be restored). Only required when tasks includes inpainting.
|
|
| num_inference_steps |
integer
|
30
|
Number of diffusion steps.
|
| decode_chunk_size |
integer
|
16
|
Chunk size for decoding long videos.
|
| overlap |
integer
|
3
|
Number of overlapping frames between segments.
|
| noise_aug_strength |
number
|
0
|
Noise augmentation strength.
|
| min_appearance_guidance_scale |
number
|
2
|
Minimum guidance scale for restoration.
|
| max_appearance_guidance_scale |
number
|
2
|
Maximum guidance scale for restoration.
|
| i2i_noise_strength |
number
|
1
|
Image-to-image noise strength.
|
| seed |
integer
|
Random seed. Leave blank to randomize.
|
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'}