← Back to all generators

zsxkib/hunyuan-video2video

A state-of-the-art text-to-video generation model capable of creating high-quality videos with realistic motion from text descriptions

Capabilities

1:1 4:3 3:4 16:9 9:16 2:3 3:2 Seed

Cost

Community model (estimated from hardware time)

Input Parameters

video required string

Input video file.

crf integer

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

Default: 19 min: 0, max: 51
custom_height integer

Custom height if force_size is not 'Disabled'.

Default: 512 min: 64, max: 2048
custom_width integer

Custom width if force_size is not 'Disabled'.

Default: 512 min: 64, max: 2048
denoise_strength number

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

Default: 0.85 min: 0, max: 1
flow_shift integer

Flow shift for temporal consistency. Adjust to tweak video smoothness.

Default: 9 min: 1, max: 20
force_rate integer

Force a new frame rate on the input video. 0 means no change.

Default: 0 min: 0, max: 240
force_size string

Force resize method. 'Disabled' means original size. Otherwise applies custom_width/height.

Default: "Disabled"
frame_load_cap integer

Max frames to load from input video.

Default: 101 min: 1
frame_rate integer

Frame rate of the output video.

Default: 24 min: 1, max: 120
guidance_scale number

Embedded guidance scale. Higher values follow the prompt more strictly.

Default: 6 min: 1, max: 20
height integer

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

Default: 768 min: 64, max: 2048
keep_proportion boolean

Keep aspect ratio when resizing. If true, will adjust dimensions proportionally.

Default: true
prompt string

Text prompt describing the desired output video style. Be descriptive.

Default: "high quality nature video of a excited brown bear walking through the grass, masterpiece, best quality"
seed integer

Set a seed for reproducibility. Random by default.

select_every_nth integer

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

Default: 1 min: 1
skip_first_frames integer

Number of initial frames to skip from the input video.

Default: 0 min: 0
steps integer

Number of sampling (denoising) steps.

Default: 30 min: 1, max: 150
width integer

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

Default: 768 min: 64, max: 2048
Version: d550f226f28b Updated: 2/26/2026 3.0K runs