You're looking at a specific version of this model. Jump to the model overview.
patternbreakai /hunyuancustom:8b59fc59
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_image |
string
|
Input image to use as a reference for video generation
|
|
| positive_prompt |
string
|
Realistic, High-quality. A woman in a garden.
|
Positive text prompt to guide video generation
|
| negative_prompt |
string
|
Aerial view, overexposed, low quality, deformation, a poor composition, bad hands, bad teeth, bad eyes, bad limbs, distortion, blurring, text, subtitles, static, picture, black border.
|
Negative text prompt to avoid in video generation
|
| video_width |
integer
|
896
Min: 256 Max: 1280 |
Width of the output video. Recommended to keep width >= height * 1.7
|
| video_height |
integer
|
512
Min: 256 Max: 720 |
Height of the output video
|
| num_frames |
integer
|
129
Min: 16 Max: 256 |
Number of frames to generate
|
| inference_steps |
integer
|
30
Min: 10 Max: 50 |
Number of denoising steps
|
| seed |
integer
|
-1
Min: -1 |
Random seed for generation. Set to -1 for random seed.
|
| flow_shift |
number
|
13
Max: 20 |
Flow shift parameter for video generation
|
| use_fp8 |
boolean
|
True
|
Whether to use FP8 precision for inference. Helps with low VRAM.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'format': 'uri', 'title': 'Output', 'type': 'string'}