You're looking at a specific version of this model. Jump to the model overview.
zsxkib /hunyuan-video-lora:b7f81117
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 |
|---|---|---|---|
| prompt |
string
|
A modern lounge in lush greenery.
|
The text prompt describing your video scene.
|
| lora_url |
string
|
|
A URL pointing to your LoRA .safetensors file or a Hugging Face repo (e.g. 'user/repo' - will use first .safetensors found).
|
| replicate_weights |
string
|
A tar file containing LoRA weights from replicate. (Optional)
|
|
| lora_strength |
number
|
1
|
Scale/strength for your LoRA.
|
| width |
integer
|
640
Min: 64 Max: 1536 |
Width for the generated video.
|
| height |
integer
|
360
Min: 64 Max: 1024 |
Height for the generated video.
|
| steps |
integer
|
50
Min: 1 Max: 150 |
Number of diffusion steps.
|
| guidance_scale |
number
|
6
|
Overall influence of text vs. model.
|
| flow_shift |
integer
|
9
Max: 20 |
Video continuity factor (flow).
|
| force_offload |
boolean
|
True
|
Whether to force model layers offloaded to CPU.
|
| denoise_strength |
number
|
1
|
Controls how strongly noise is applied each step.
|
| num_frames |
integer
|
85
Min: 1 Max: 300 |
How many frames (duration) in the resulting video.
|
| frame_rate |
integer
|
24
Min: 1 Max: 60 |
Video frame rate.
|
| crf |
integer
|
19
Max: 51 |
CRF (quality) for h264 video encoding, lower=better.
|
| seed |
integer
|
Set a seed for reproducibility. Random by default.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'format': 'uri', 'title': 'Output', 'type': 'string'}