← 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

1:14:33:416:99:162:33:2Seed

Cost

Community model (estimated from hardware time)

Input Parameters

videorequiredstring

Input video file.

crfinteger

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

Default: 19min: 0, max: 51
custom_heightinteger

Custom height if force_size is not 'Disabled'.

Default: 512min: 64, max: 2048
custom_widthinteger

Custom width if force_size is not 'Disabled'.

Default: 512min: 64, max: 2048
denoise_strengthnumber

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

Default: 0.85min: 0, max: 1
flow_shiftinteger

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

Default: 9min: 1, max: 20
force_rateinteger

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

Default: 0min: 0, max: 240
force_sizestring

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

Default: "Disabled"
frame_load_capinteger

Max frames to load from input video.

Default: 101min: 1
frame_rateinteger

Frame rate of the output video.

Default: 24min: 1, max: 120
guidance_scalenumber

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

Default: 6min: 1, max: 20
heightinteger

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

Default: 768min: 64, max: 2048
keep_proportionboolean

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

Default: true
promptstring

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"
seedinteger

Set a seed for reproducibility. Random by default.

select_every_nthinteger

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

Default: 1min: 1
skip_first_framesinteger

Number of initial frames to skip from the input video.

Default: 0min: 0
stepsinteger

Number of sampling (denoising) steps.

Default: 30min: 1, max: 150
widthinteger

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

Default: 768min: 64, max: 2048
Version: d550f226f28bUpdated: 7/25/20263.0K runs