WAN 2.2 t2v-plus-480p turns text prompts into 480p AI videos, enabling unlimited AI video generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.2per run·~50 / $10
ExamplesView all
An elderly craftsman with deep wrinkles and flour on his hands carefully shapes dough in a rustic, sunlit bakery. The focus is on his hands and the intense concentration on his face. --Close-up shot, shallow depth of field, soft natural window light, warm tones, 4K, photorealistic skin texture.
A woman in a flowing red dress walks alone on a cobblestone street in Paris at night. The city lights blur beautifully in the background as a gentle rain falls, reflecting the neon signs on the wet ground. --Medium shot, shallow depth of field, moody cinematic lighting, anamorphic lens flare, 35mm film grain.
A majestic bald eagle snatches a fish from a crystal-clear river in a single, fluid motion, water droplets flying in every direction and catching the morning sunlight. --Slow motion, close-up tracking shot, 8K, hyperrealistic, sharp focus.
A futuristic, sleek, self-driving car glides silently through a bustling Tokyo street filled with towering holographic advertisements. The car's polished surface reflects the vibrant city life. --Low-angle tracking shot from the front of the vehicle, photorealistic CGI, neon-drenched atmosphere, sharp reflections.
A spoonful of rich, molten chocolate is slowly poured over a scoop of vanilla bean ice cream. The camera captures every luscious drip and the texture of the dessert in extreme detail. --Extreme close-up, macro lens, high-speed camera for slow motion, warm studio lighting, 4K.
A time-lapse of a modern, minimalist house in the desert as clouds drift by. The shadows move across the clean lines of the building from sunrise to sunset, showing the changing colors of the sky. --Static wide shot, time-lapse, 8K, high detail, natural lighting, photorealistic rendering.
A young woman with long, flowing hair stands in the middle of a lavender field at sunset. She gently runs her fingers through the flowers as a warm, golden light illuminates her serene expression. --Medium close-up, slow motion, shallow depth of field with beautiful bokeh, 4K, dreamlike atmosphere.
A woman practices yoga on a wooden pier at dawn, facing a perfectly still and misty lake. Her movements are slow and deliberate, mirroring the tranquility of the surroundings. --Static wide shot, natural morning light, pastel color palette, 4K, serene and peaceful.
An elven princess with intricate braids in her hair reads an ancient book under a giant, glowing mushroom in an enchanted forest at night. Fireflies dance around her, lighting up the scene. --Medium shot, magical realism style, soft ambient lighting, ultra HD, detailed fantasy elements.
An extreme close-up of a woman's face as a single tear rolls down her cheek. Her eyes are filled with emotion, and the lighting is soft and dramatic, highlighting the details of her skin and eyes. --Extreme close-up, high detail, dramatic chiaroscuro lighting, slow motion, powerful emotional impact.
Related Models
README
WAN 2.2 Text-to-Video Model (480p)
WAN 2.2 is an advanced text-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 at 480p resolution.
Why it looks great
- Cinematic Aesthetics – professional-level control of lighting, color, and composition, delivering a true film-quality look.
- Natural Motion – restores complex movements with smooth transitions and precise controllability.
- Semantic Precision – understands complex scenes and multi-object interactions, keeping your creative intent intact.
- Multimodal Power – supports both text-to-video and image-to-video, flexible for storytelling, education, and creative content.
Pricing
| Video Length | Cost (USD) |
|---|---|
| 5 seconds | $0.05 |
How to Use
- Enter your prompt – describe the scene (e.g., camera angle, action, lighting).
- (Optional) Add a negative_prompt – specify what you don’t want in the video.
- Set size – choose output resolution (e.g., 832×480 or 480×832).
- Set seed – use -1 for random results, or fix a number for reproducibility.
- Click Run – preview and download your generated video.
Wan 2.2 T2v Plus 480p API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/alibaba/wan-2.2/t2v-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 T2v Plus 480p below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/alibaba/wan-2.2/t2v-plus-480p" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "832*480",
"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/t2v-plus-480p", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "832*480",
"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/t2v-plus-480p",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "832*480",
"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 T2v Plus 480p API — Frequently asked questions
What is the Wan 2.2 T2v Plus 480p API?
Wan 2.2 T2v Plus 480p is a Alibaba model for video generation, exposed as a REST API on WaveSpeedAI. WAN 2.2 t2v-plus-480p turns text prompts into 480p AI videos, enabling unlimited AI 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 T2v 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-t2v-plus-480p.
How much does Wan 2.2 T2v Plus 480p cost per run?
Wan 2.2 T2v 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 T2v Plus 480p accept?
Key inputs: `prompt`, `duration`, `size`, `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-t2v-plus-480p.
How long does Wan 2.2 T2v Plus 480p take to generate?
Average end-to-end generation time on WaveSpeedAI is around 30 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 T2v 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.