You're looking at a specific version of this model. Jump to the model overview.
sczhou /upscale-a-video:bf85b880
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 |
|---|---|---|---|
| input_video |
string
|
Low-resolution video
|
|
| video_caption |
string
|
|
Optionally provide the video caption.
|
| use_llava |
boolean
|
False
|
Use LLaVA to generate video caption. Ignored if video_caption is provided.
|
| a_prompt |
string
|
best quality, extremely detailed
|
Additional prompt
|
| n_prompt |
string
|
blur, worst quality
|
Negative prompt
|
| noise_level |
integer
|
150
Max: 200 |
Noise level applied to the input video. A higher noise level typically results in better video quality but lower fidelity.
|
| guidance_scale |
number
|
6
Max: 20 |
Classifier-free guidance scale for prompts. A higher guidance scale encourages the model to generate more details.
|
| inference_steps |
integer
|
30
Max: 100 |
The number of denoising steps. More steps usually lead to a higher quality video.
|
| propagation_steps |
string
|
|
Optional. Propagation steps after performing denoising. Separate the steps woth comma.
|
| color_fix |
string
(enum)
|
None
Options: None, AdaIn, Wavelet |
An enumeration.
|
| seed |
integer
|
Random seed. Leave blank to randomize the seed
|
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'}