WAN 2.2 i2v-plus-480p turns images into unlimited AI videos at 480p via image-to-video generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.2per run·~50 / $10
ExamplesView all
A bearded backpacker, around 30 years old, sits on a rock at a mountain summit, looking out over a sea of clouds and distant mountain ranges. The first light of sunrise is just breaking, painting the sky in shades of orange and pink. He is wearing a windproof jacket, with his trekking pole and backpack placed beside him. He takes a sip of hot tea from a thermos, a look of contentment and peace on his face. The camera slowly pushes in from behind him, moving over his shoulder to reveal the majestic view before him.
A young female potter, her hands covered in wet clay, is shaping a vase on a rapidly spinning potter's wheel. Her gaze is highly concentrated, and the muscles in her arms tense subtly as the vessel takes form. Her studio is filled with various unfinished pieces and jars of glaze. Sunlight streams through a dusty window, making the airborne dust particles visible. The entire scene is rich with the texture of craftsmanship and the quiet beauty of the creative process.
A female data analyst inside a control room filled with holographic screens and futuristic interfaces. She has sleek, silver short hair and a sharp, focused gaze. She wears a form-fitting, dark gray jumpsuit with clean, simple lines. Her fingers move swiftly through the air, interacting with a 3D data star map floating in front of her. The surrounding environment is dimly lit, with only the blue and white light from the data displays illuminating her face and hands, creating a high-tech and mysterious atmosphere.
An elderly librarian, wearing reading glasses, is carefully wiping the leather cover of an ancient book with a soft cloth. Afternoon sunlight streams through the tall library windows, creating distinct beams of light. The air is filled with the scent of old paper and wood. His movements are slow and full of reverence, his face showing a deep appreciation for knowledge. This is an extremely quiet close-up shot, focusing on the details of his hands and the interplay of light and shadow.
Related Models
README
WAN 2.2 Image-to-Video Plus (480p)
The WAN 2.2 I2V-Plus model is a state-of-the-art image-to-video generator available on Cloud's DashScope platform. It uses an innovative Mixture of Experts (MoE) architecture to create smooth and realistic videos from static images at a 480p resolution. This model is designed for short, high-quality clips.
Why it looks great
- MoE architecture: dynamically directs tasks to specialized experts for improved detail and motion accuracy.
- Natural motion synthesis: creates smooth and realistic transitions from a still image.
- Detail preservation: keeps sharp textures and clear faces in dynamic shots.
- Temporal stability: reduces flicker and frame inconsistencies.
- Optimized for portraits: excels at transforming human photos into realistic talking or moving videos.
Limits and Performance
- Output resolution: fixed at 480p
- Max clip length per job: 5 seconds
- Processing speed: ~5–10 seconds of wall time per second of video (varies by queue and complexity)
Pricing
| Output Resolution | Cost per 5 seconds | Max Length |
|---|---|---|
| 480p | $0.20 | 5 seconds |
Billing Rules
- Minimum charge = 5 seconds (one clip)
- No partial billing — all jobs are billed as a 5-second generation
- Total cost = number of clips × $0.20
How to Use
- Upload a source image (clear, high-quality recommended).
- (Optional) Add a prompt to guide motion or scene style.
- Select output length (5 seconds).
- Run the job and download the 480p video.
Notes
- This version only supports 480p and up to 5 seconds per clip.
- For longer or higher-resolution outputs, check newer WAN versions (WAN 2.5).
Wan 2.2 I2v Plus 480p API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/alibaba/wan-2.2/i2v-plus-480p with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Wan 2.2 I2v Plus 480p below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/alibaba/wan-2.2/i2v-plus-480p" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"image": "https://example.com/your-input.jpg",
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 5,
"enable_prompt_expansion": false,
"negative_prompt": "blurry, low quality, distorted",
"seed": -1
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("alibaba/wan-2.2/i2v-plus-480p", {
"image": "https://example.com/your-input.jpg",
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 5,
"enable_prompt_expansion": false,
"negative_prompt": "blurry, low quality, distorted",
"seed": -1
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"alibaba/wan-2.2/i2v-plus-480p",
{
"image": "https://example.com/your-input.jpg",
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 5,
"enable_prompt_expansion": false,
"negative_prompt": "blurry, low quality, distorted",
"seed": -1
}
)
print(output["outputs"][0]) # → URL of the generated outputWan 2.2 I2v Plus 480p API — Frequently asked questions
What is the Wan 2.2 I2v Plus 480p API?
Wan 2.2 I2v Plus 480p is a Alibaba model for video generation from images, exposed as a REST API on WaveSpeedAI. WAN 2.2 i2v-plus-480p turns images into unlimited AI videos at 480p via image-to-video generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Wan 2.2 I2v Plus 480p API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/alibaba/alibaba-wan-2.2-i2v-plus-480p.
How much does Wan 2.2 I2v Plus 480p cost per run?
Wan 2.2 I2v Plus 480p starts at $0.20 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Wan 2.2 I2v Plus 480p accept?
Key inputs: `prompt`, `image`, `duration`, `seed`, `negative_prompt`, `enable_prompt_expansion`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/alibaba/alibaba-wan-2.2-i2v-plus-480p.
How long does Wan 2.2 I2v Plus 480p take to generate?
Average end-to-end generation time on WaveSpeedAI is around 51 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Wan 2.2 I2v Plus 480p outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (Alibaba). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.