zsxkib/wan-2.2-unified
Unified interface for all Wan 2.2 video generation models with intelligent T2V/I2V switching
Run zsxkib/wan-2.2-unified 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 |
|---|---|---|---|
| prompt |
string
|
Text prompt for video generation
|
|
| image |
string
|
Input image for image-to-video generation (automatically switches to I2V model)
|
|
| resolution |
None
|
480p
|
Output video resolution: '480p' (832x480 or 480x832 pixels) or '720p' (1280x720 or 720x1280 pixels)
|
| aspect_ratio |
None
|
16:9
|
Video aspect ratio: landscape (16:9) or portrait (9:16)
|
| num_frames |
integer
|
81
Min: 81 Max: 100 |
Number of video frames (81 recommended for optimal results)
|
| frames_per_second |
integer
|
16
Min: 5 Max: 24 |
Video frame rate (16fps optimal for Wan 2.2 models)
|
| quality |
None
|
fast
|
Model quality: 'fast' (PrunaAI optimized models) or 'standard' (A14B model, I2V only). Note: go_fast=true will override this to use fast models.
|
| go_fast |
boolean
|
True
|
Processing speed: true (turbo mode) or false (standard processing). When true, always uses fast models regardless of quality setting.
|
| sample_shift |
number
|
12
Min: 1 Max: 20 |
Sampling behavior control. Leave at default for best results (auto-optimized per model).
|
| sample_steps |
integer
|
30
Min: 1 Max: 50 |
Denoising steps for standard quality models only. Higher = better quality but slower. Ignored when using fast models.
|
| seed |
integer
|
Random seed for reproducible generation
|
{
"type": "object",
"title": "Input",
"required": [
"prompt"
],
"properties": {
"seed": {
"type": "integer",
"title": "Seed",
"x-order": 10,
"nullable": true,
"description": "Random seed for reproducible generation"
},
"image": {
"type": "string",
"title": "Image",
"format": "uri",
"x-order": 1,
"nullable": true,
"description": "Input image for image-to-video generation (automatically switches to I2V model)"
},
"prompt": {
"type": "string",
"title": "Prompt",
"x-order": 0,
"description": "Text prompt for video generation"
},
"go_fast": {
"type": "boolean",
"title": "Go Fast",
"default": true,
"x-order": 7,
"description": "Processing speed: true (turbo mode) or false (standard processing). When true, always uses fast models regardless of quality setting."
},
"quality": {
"enum": [
"fast",
"standard"
],
"type": "string",
"title": "quality",
"description": "Model quality: 'fast' (PrunaAI optimized models) or 'standard' (A14B model, I2V only). Note: go_fast=true will override this to use fast models.",
"default": "fast",
"x-order": 6
},
"num_frames": {
"type": "integer",
"title": "Num Frames",
"default": 81,
"maximum": 100,
"minimum": 81,
"x-order": 4,
"description": "Number of video frames (81 recommended for optimal results)"
},
"resolution": {
"enum": [
"480p",
"720p"
],
"type": "string",
"title": "resolution",
"description": "Output video resolution: '480p' (832x480 or 480x832 pixels) or '720p' (1280x720 or 720x1280 pixels)",
"default": "480p",
"x-order": 2
},
"aspect_ratio": {
"enum": [
"16:9",
"9:16"
],
"type": "string",
"title": "aspect_ratio",
"description": "Video aspect ratio: landscape (16:9) or portrait (9:16)",
"default": "16:9",
"x-order": 3
},
"sample_shift": {
"type": "number",
"title": "Sample Shift",
"default": 12,
"maximum": 20,
"minimum": 1,
"x-order": 8,
"description": "Sampling behavior control. Leave at default for best results (auto-optimized per model)."
},
"sample_steps": {
"type": "integer",
"title": "Sample Steps",
"default": 30,
"maximum": 50,
"minimum": 1,
"x-order": 9,
"description": "Denoising steps for standard quality models only. Higher = better quality but slower. Ignored when using fast models."
},
"frames_per_second": {
"type": "integer",
"title": "Frames Per Second",
"default": 16,
"maximum": 24,
"minimum": 5,
"x-order": 5,
"description": "Video frame rate (16fps optimal for Wan 2.2 models)"
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
{
"type": "string",
"title": "Output",
"format": "uri"
}