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

zsxkib /hunyuan-video2video:d550f226

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.
prompt
string
high quality nature video of a excited brown bear walking through the grass, masterpiece, best quality
Text prompt describing the desired output video style. Be descriptive.
width
integer
768

Min: 64

Max: 2048

Output video width (divisible by 16 for best performance).
height
integer
768

Min: 64

Max: 2048

Output video height (divisible by 16 for best performance).
keep_proportion
boolean
True
Keep aspect ratio when resizing. If true, will adjust dimensions proportionally.
steps
integer
30

Min: 1

Max: 150

Number of sampling (denoising) steps.
guidance_scale
number
6

Min: 1

Max: 20

Embedded guidance scale. Higher values follow the prompt more strictly.
denoise_strength
number
0.85

Max: 1

Denoise strength (0.0 to 1.0). Higher = more deviation from input content.
flow_shift
integer
9

Min: 1

Max: 20

Flow shift for temporal consistency. Adjust to tweak video smoothness.
seed
integer
Set a seed for reproducibility. Random by default.
frame_rate
integer
24

Min: 1

Max: 120

Frame rate of the output video.
crf
integer
19

Max: 51

CRF value for output video quality (0-51). Lower values = better quality.
force_rate
integer
0

Max: 240

Force a new frame rate on the input video. 0 means no change.
force_size
string
Disabled
Force resize method. 'Disabled' means original size. Otherwise applies custom_width/height.
custom_width
integer
512

Min: 64

Max: 2048

Custom width if force_size is not 'Disabled'.
custom_height
integer
512

Min: 64

Max: 2048

Custom height if force_size is not 'Disabled'.
frame_load_cap
integer
101

Min: 1

Max frames to load from input video.
skip_first_frames
integer
0
Number of initial frames to skip from the input video.
select_every_nth
integer
1

Min: 1

Use every nth frame (1 = every frame, 2 = every second frame, etc.).

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'}