liyangbing/wan-2.1 | API reference

Public

5 runs

Run liyangbing/wan-2.1 with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

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
task	None	t2v-1.3B	Task type
prompt	string	Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage.	Input prompt
image	string		Input image for image-to-video task
size	None	832*480	Output size
sample_steps	integer	Min: 30 Max: 50	Number of sampling steps (30-50, default is 40 for i2v and 50 for t2v)
sample_shift	number	Min: 2 Max: 5	Sample shift parameter (2.0-5.0, use 2.0-3.0 for 480p)
cfg_scale	number	7.5 Min: 1 Max: 15	Classifier-free guidance scale (1.0-15.0)
seed	integer		Random seed

{
  "type": "object",
  "title": "Input",
  "properties": {
    "seed": {
      "type": "integer",
      "title": "Seed",
      "x-order": 7,
      "description": "Random seed"
    },
    "size": {
      "enum": [
        "720*1280",
        "1280*720",
        "480*832",
        "832*480",
        "1024*1024"
      ],
      "type": "string",
      "title": "size",
      "description": "Output size",
      "default": "832*480",
      "x-order": 3
    },
    "task": {
      "enum": [
        "t2v-1.3B",
        "t2v-14B",
        "t2i-14B",
        "i2v-14B"
      ],
      "type": "string",
      "title": "task",
      "description": "Task type",
      "default": "t2v-1.3B",
      "x-order": 0
    },
    "image": {
      "type": "string",
      "title": "Image",
      "format": "uri",
      "x-order": 2,
      "description": "Input image for image-to-video task"
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "default": "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage.",
      "x-order": 1,
      "description": "Input prompt"
    },
    "cfg_scale": {
      "type": "number",
      "title": "Cfg Scale",
      "default": 7.5,
      "maximum": 15,
      "minimum": 1,
      "x-order": 6,
      "description": "Classifier-free guidance scale (1.0-15.0)"
    },
    "sample_shift": {
      "type": "number",
      "title": "Sample Shift",
      "maximum": 5,
      "minimum": 2,
      "x-order": 5,
      "description": "Sample shift parameter (2.0-5.0, use 2.0-3.0 for 480p)"
    },
    "sample_steps": {
      "type": "integer",
      "title": "Sample Steps",
      "maximum": 50,
      "minimum": 30,
      "x-order": 4,
      "description": "Number of sampling steps (30-50, default is 40 for i2v and 50 for t2v)"
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "string",
  "title": "Output",
  "format": "uri"
}