Wan 2.2 t2v-480p generates unlimited AI videos from text prompts at 480p resolution, ideal for rapid prototyping and content creation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.15per run·~66 / $10
A young woman in a soft linen dress sits on a balcony in 19th-century Paris, painting the sunset with graceful strokes. Her hair is caught in a gentle breeze, and pastel clouds reflect on her canvas. Birds flutter overhead, and the Eiffel Tower stands distant in soft haze. The scene is delicate, dreamy, and infused with poetic nostalgia.
A woman photographer sets up her tripod in a wide open countryside at sunrise. The grass sways gently. She adjusts the focus ring on her camera and smiles in satisfaction. The camera follows her movements with a soft handheld feel.
A woman sits on a large driftwood log by a stormy beach, notebook in hand. Wind tousles her hair. Waves crash in the distance. She scribbles something, then stares out at the horizon. A slow dolly shot moves around her. Seagulls cry overhead.
Sidelight, soft light, high contrast, medium shot, center composition, clean single shot, warm tones. Young man standing in the woods, head slightly raised, eyes clear, sunlight filtering through the leaves creating a golden halo in his hair. He's wearing a light-colored shirt, and the breeze is blowing his hair and collar, the light flowing across his face as he moves. The background is bokeh, with dappled light and soft tree shadows in the distance.
A group of energetic hip-hop dancers in a variety of styles dance on an expansive stage illuminated by bright neon lights, their silhouettes surrounded by a halo of sidelights. The wide-format cinematography captures their neat steps, vibrant energy and youthful expressions. The fast-paced cinematography echoes the beat of the music, demonstrating the complexity of the footwork, the explosiveness, and the teamwork.
The visually stunning show creates a strong sense of atmosphere with the corn train as the central element. Dramatic warm spotlights illuminate the stage as a corn train moves forward across the stage. The video captures the shifting light and shadows cast by the train, creating abstract patterns, shapes and illusions that dance across the stage.
A fleeing male, in a neon, steamy back alley on a rainy night in the city, panics in his soaked trench coat as he runs down the alley, constantly looking back. Following the follow-up shot creates a strong sense of immersion for the viewer, as if the pursuer is right behind the camera.
An elderly man smiles warmly while handing a paper coffee cup to a child on a bustling street corner
In close-up, a bunny wearing pink skates glides on the ice. The panoramic lens captures every jump and spin of the bunny on the vast ice surface, while the trees and snowy landscape in the background add a bit of serenity and beauty to this joyful winter scene. The whole scene is smoothly displayed under a stabilized tracking lens.
Two sleek, futuristic fighter jets, with glowing blue thrusters, engage in a high-speed chase through a dense asteroid field. The camera follows closely behind the leading jet, capturing the pilot's fast, skillful maneuvers as they navigate between massive, tumbling rocks. Explosions from laser fire flash brightly against the deep, star-filled blackness of space. The motion is extremely fast and kinetic, with jarring camera movements to simulate the turbulence and adrenaline of the chase. The sound of whooshing air and sharp turns is implied. The video has an intense, action-packed sci-fi aesthetic.
A magnificent, brass-and-wood steampunk airship, with large, rotating propellers and intricate mechanical details, glides majestically through a cloudy, orange-hued sky at sunset. Below, a bustling, Victorian-era cityscape is visible, with smoke stacks billowing steam and clock towers rising towards the clouds. A lone figure in goggles and a leather jacket stands at the airship's helm, gazing out over the view. The camera tracks alongside the airship, capturing its slow, deliberate motion and the warm, ethereal light. The video has a nostalgic and adventurous feel, with a smooth,
A dynamic tracking shot following a passionate young chef in a modern, stainless-steel kitchen. He is meticulously garnishing a dish with fresh herbs, his movements precise and confident. Sweat glistens on his forehead, and his expression is a mix of intense focus and creative satisfaction. The kitchen is busy in the background, with other chefs working quickly. The lighting is bright and clean, with steam rising from a nearby pot. The atmosphere is energetic and professional. Shot in a fast-paced, documentary style with a sharp focus on the details of the food.
A close-up shot of a young woman with a thoughtful expression, her eyes scanning the pages of an old book. She is sitting in a quiet, sun-drenched library, wearing a simple, cozy sweater. A gentle breeze from an open window rustles the pages of her book and the light dust motes dancing in the air. The atmosphere is peaceful and scholarly, with the background of towering bookshelves blurred slightly. The camera slowly pans out to reveal her serene posture. Filmed with a soft focus and a warm, inviting color palette.
A medium-long shot of two young individuals, a man and a woman, standing on a train platform in the pouring rain. They are holding hands, their faces wet with rain and mixed emotions. Steam rises from the train engine behind them, and the platform lights create a hazy glow. The camera slowly zooms in on their clasped hands, conveying a sense of longing and a difficult goodbye. The atmosphere is somber and romantic. The lighting is soft and diffused by the rain, with a cool, melancholic color grade.
Create videos from pure imagination with Wan 2.2 Text-to-Video. Simply describe your scene in words and watch it come to life — no source images required. This accessible 480p model supports both landscape and portrait orientations, perfect for rapid prototyping and social media content.
Looking for higher resolution? Try Wan 2.2 T2V 720p for HD output.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the scene, action, and atmosphere you want. |
| negative_prompt | No | Elements to avoid in the generated video. |
| size | No | Output dimensions: 832×480 (landscape) or 480×832 (portrait). Default: 832×480. |
| duration | No | Video length: 5 or 8 seconds. Default: 5. |
| seed | No | Random seed for reproducibility. Use -1 for random. |
Per 5-second billing based on duration.
| Duration | Calculation | Cost |
|---|---|---|
| 5 seconds | 5 ÷ 5 × $0.15 | $0.15 |
| 8 seconds | 8 ÷ 5 × $0.15 | $0.24 |
| Size | Orientation | Best For |
|---|---|---|
| 832×480 | Landscape | YouTube, presentations, desktop viewing |
| 480×832 | Portrait | TikTok, Instagram Reels, Stories, mobile |
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/t2v-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 480p below.
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/t2v-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",
"negative_prompt": "blurry, low quality, distorted",
"size": "832*480",
"duration": 5,
"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].// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("wavespeed-ai/wan-2.2/t2v-480p", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"negative_prompt": "blurry, low quality, distorted",
"size": "832*480",
"duration": 5,
"seed": -1
});
console.log(result.outputs[0]); // → URL of the generated output# pip install wavespeed
import wavespeed
output = wavespeed.run(
"wavespeed-ai/wan-2.2/t2v-480p",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"negative_prompt": "blurry, low quality, distorted",
"size": "832*480",
"duration": 5,
"seed": -1
}
)
print(output["outputs"][0]) # → URL of the generated outputWan 2.2 T2v 480p is a WaveSpeedAI model for video generation, exposed as a REST API on WaveSpeedAI. Wan 2.2 t2v-480p generates unlimited AI videos from text prompts at 480p resolution, ideal for rapid prototyping and content creation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
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/wavespeed-ai/wan-2.2-t2v-480p.
Wan 2.2 T2v 480p starts at $0.15 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.
Key inputs: `prompt`, `duration`, `size`, `seed`, `negative_prompt`. 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/wavespeed-ai/wan-2.2-t2v-480p.
Average end-to-end generation time on WaveSpeedAI is around 73 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.