WAN 2.2 i2v-plus-1080p turns images into polished 1080p videos for content creation and prototyping. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.8per run·~12 / $10
ExamplesView all
A young woman sits by a sun-drenched window, the gentle breeze softly blowing her hair as she focuses on reading a book, a calm and content smile on her face. The lighting is soft, creating a warm, tranquil atmosphere. Cinematic close-up shot.
1
A person is deeply engrossed in a book in a cozy study. The wall behind them begins to ripple like water, slowly transforming into a swirling galaxy of stars and nebulae that reflects the fantasy world of the book. The light from the galaxy gently illuminates the side of their face. Magical, surreal, imaginative.
An architect stares intently at a blueprint on a table. As his eyes trace the lines, faint, glowing holographic lines rise from the paper, constructing a 3D model of the building in the air above the blueprint. The camera slowly pushes in, focusing on the intricate details of the glowing structure. Innovative, conceptual, magical realism.
A mountaineer reaches the summit of a snowy peak. They take a deep breath of the thin air, a look of awe and accomplishment washing over their face. Fierce winds whip at their jacket and nearby prayer flags, as clouds rush past below. Arc shot moving from behind to a close-up on their face. Epic, wide-angle, breathtaking.
A couple walks hand-in-hand on a beach during the golden hour. The low-angle setting sun casts long, soft shadows and bathes the entire scene in a warm, magical orange glow. Gentle waves lap at the shore. The camera tracks them slowly, with beautiful lens flares appearing as they move. Romantic, serene, dreamy.
A man stands in a bustling crowd, his face suddenly showing a look of shocking realization. The camera executes a dramatic dolly zoom: it moves physically closer to him while the lens zooms out, causing the background crowd to appear to stretch and rush away, visually amplifying his internal shock. Psychological, intense, disorienting.
A ballerina is frozen in a dramatic pose in the center of an empty, dark stage. A single spotlight illuminates her. The camera performs a slow, graceful 360-degree orbit shot around her, showcasing her form from all angles against the vast emptiness of the stage. Elegant, focused, cinematic.
Drone shot starting from a close-up of a person standing in the middle of a vast salt flat, looking up towards the sky. The drone then rapidly ascends straight up, pulling away to reveal the immense, geometric patterns of the sprawling landscape. The person becomes a tiny speck, emphasizing their solitude and the grand scale of nature. Awe-inspiring, high-angle, vast.
A female architect stands in a bright, sterile, minimalist office, filled with natural light. The scene is evenly lit with bright, shadowless high-key lighting, creating a sense of optimism and clarity. She smiles and makes a final, decisive stroke on a blueprint with a pen. The camera makes a clean, smooth slide to the side. Clean, futuristic, optimistic.
Related Models
README
WAN 2.2 Image-to-Video Model (1080p)
WAN 2.2 is an advanced image-to-video model provided by Cloud's DashScope platform. This model adopts an innovative MoE (Mixture of Experts) architecture for generating high-quality video content from images at full HD 1080p resolution.
Why it looks great
- Cinematic control: handles lighting, color, and composition with a film-style aesthetic.
- Stable, natural motion: restores nuanced subject movement and camera dynamics.
- Semantic fidelity: follows complex editing prompts while preserving scene coherence.
- Clean edits: supports negative prompts and prompt optimization to reduce artifacts.
Limits and Performance
- Input: one image + text prompt
- Output resolution: 1080p (Full HD)
- Clip length per job: 5 seconds
Pricing
Per-job billing with a 5-second clip length.
| Duration | Resolution | Cost per job |
|---|---|---|
| 5 s | 1080p | $0.80 |
How to Use
- Upload Image – drag & drop or paste a URL.
- Write Prompt – describe motion, mood, camera, lighting, etc.
- (Optional) Negative Prompt – exclude unwanted objects/styles.
- (Optional) Seed – fix for reproducibility (
-1= random). - Run – generate, preview, and download.
Notes
- Please check that your uploaded image URL is valid and accessible.
- If the URL is not working, consider uploading the image locally.
- Recommended image formats: JPG / PNG.
Wan 2.2 I2v Plus 1080p API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/alibaba/wan-2.2/i2v-plus-1080p 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 1080p below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/alibaba/wan-2.2/i2v-plus-1080p" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"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-1080p", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"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-1080p",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"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 1080p API — Frequently asked questions
What is the Wan 2.2 I2v Plus 1080p API?
Wan 2.2 I2v Plus 1080p is a Alibaba model for video generation from images, exposed as a REST API on WaveSpeedAI. WAN 2.2 i2v-plus-1080p turns images into polished 1080p videos for content creation and prototyping. 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 1080p 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-1080p.
How much does Wan 2.2 I2v Plus 1080p cost per run?
Wan 2.2 I2v Plus 1080p starts at $0.80 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 1080p 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-1080p.
How long does Wan 2.2 I2v Plus 1080p take to generate?
Average end-to-end generation time on WaveSpeedAI is around 66 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 1080p 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.