WAN 2.5 Fast converts text or images into synchronized-audio videos in 480p, 720p, or 1080p, offering faster, more affordable generation compared to Google Veo3. REST API, no coldstarts, affordable pricing.
Inactivo
$0.34por ejecución·~29 / $10
Drone aerial shot of a red Ferrari supercar speeding along a winding coastal highway during the golden hour at sunset. The camera tracks the car as it masterfully navigates the curves. Sunlight glints off the car's polished surface, with the dramatic ocean and cliffs in the background. The mood is warm, passionate, and liberating, cinematic, 4K.
Extreme macro shot, a ripe, juicy orange is slowly sliced in half by a sharp chef's knife. The texture of the orange peel and its oil cells are clearly visible. As the blade presses down, juice bursts out and the pulp's fibers separate. Filmed in 120fps slow motion, with bright, clean lighting against a minimalist white marble countertop, hyperrealistic, satisfying.
Cinematic video of a young woman standing gracefully on outdoor stairs under a clear blue summer sky. She wears a loose white sleeveless dress flowing naturally in the wind, short black bob haircut, with white socks and beige shoes. Camera starts with a wide low-angle shot, then performs a slow pan from left to right, gradually pushing in closer with a subtle dolly movement. Soft lens flare from the sun peeks through power lines above, adding dreamy atmosphere. The wind gently moves her dress and hair. Background power poles and wires shimmer slightly from heat haze, enhancing realism. The mood is poetic, festival-like, evoking the aesthetic of an indie Japanese film with natural soundscape of distant cicadas and summer ambience.
A short 3D animated scene in a soft, pastel cartoon style. A tiny, fluffy creature resembling a bee with stubby wings and a glowing abdomen, clumsily navigates a garden of giant, glowing flowers. The scene should feature oversized, dewy leaves, shimmering pollen particles floating in the air, and a warm, honey-colored light. The creature's buzzing hums and wide-eyed wonder should convey a sense of delightful exploration. Adopt a gentle and enchanting tone, with soft, luminous colors and smooth animation.
On a silent, snowy night with moonlight casting long shadows across a pine forest, a lone wolf stands on a rocky outcrop. It tilts its head back and lets out a powerful howl, its breath visible in the frigid air. The camera slowly cranes up from behind the wolf, settling on a shot of its silhouette against a huge, full moon. The mood is mysterious, wild, and melancholic, with a cool color palette.
In a starkly lit interrogation room, a calm female detective leans forward, hands clasped, eyes locked on the suspect. She asks slowly and deliberately, **"Tell me, why was your car at the docks at 10 PM?"** A tight close-up shot captures the subtle movement of her lips and the undeniable pressure in her eyes as she says the word "docks".
Medium close-up shot of an elderly male historian with a thoughtful expression, sitting in a library filled with old books. The lighting is warm and soft. He adjusts his glasses, looks slightly off-camera as if recalling a memory, and says in a calm, measured voice: 'To truly understand the present, we must have the courage to face the ghosts of the past. History doesn't just tell us stories; it asks us questions.
Shot from a car's passenger seat, a person turns to the driver (camera) with a bright smile, the afternoon sun lighting their face. They say cheerfully: 'Okay, I'm ready! Let's go!'
A young journalist standing in front of a modern glass building, holding a microphone. Cars pass by in the background with the sound of engines and occasional honking. She speaks confidently: 'Today we are reporting live from the city center, where a new art exhibition has just opened to the public.' Her clear voice is mixed with the natural street sounds and the faint chatter of pedestrians.
A young woman with long dark wavy hair stands by a large window, gently parting sheer white curtains with one hand. She gazes softly outside at the blurred cityscape, her expression calm and contemplative. Warm morning backlight filters through the translucent fabric, casting a golden rim light along her shoulder and hair. She wears a simple white tank top. The camera holds steady with a subtle slow push-in toward her profile, as the curtains sway faintly in a gentle breeze. Soft ambient city sounds drift in — distant traffic, birds, the quiet hum of morning. The mood is intimate, serene, and cinematic. Shallow depth of field, natural diffused light, 16:9 aspect ratio.
WAN 2.5 is an advanced image-to-video model on Cloud’s DashScope. It generates high-quality videos from images and supports output resolutions of 480p, 720p, and 1080p.
| Resolution | Price per second |
|---|---|
| 720p | $0.068 |
| 1080p | $0.102 |
Audio limits
Over-limit handling
Image Upload
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/alibaba/wan-2.5/image-to-video-fast 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 2.5 Image To Video Fast below.
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/alibaba/wan-2.5/image-to-video-fast" \
-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",
"audio": "https://example.com/your-audio.mp3",
"negative_prompt": "blurry, low quality, distorted",
"resolution": "720p",
"duration": 5,
"enable_prompt_expansion": false,
"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("alibaba/wan-2.5/image-to-video-fast", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"audio": "https://example.com/your-audio.mp3",
"negative_prompt": "blurry, low quality, distorted",
"resolution": "720p",
"duration": 5,
"enable_prompt_expansion": false,
"seed": -1
});
console.log(result.outputs[0]); // → URL of the generated output# pip install wavespeed
import wavespeed
output = wavespeed.run(
"alibaba/wan-2.5/image-to-video-fast",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"audio": "https://example.com/your-audio.mp3",
"negative_prompt": "blurry, low quality, distorted",
"resolution": "720p",
"duration": 5,
"enable_prompt_expansion": false,
"seed": -1
}
)
print(output["outputs"][0]) # → URL of the generated outputWan 2.5 Image To Video Fast is a Alibaba model for video generation from images, exposed as a REST API on WaveSpeedAI. WAN 2.5 Fast converts text or images into synchronized-audio videos in 480p, 720p, or 1080p, offering faster, more affordable generation compared to Google Veo3. REST API, 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/alibaba/alibaba-wan-2.5-image-to-video-fast.
Wan 2.5 Image To Video Fast starts at $0.34 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`, `image`, `audio`, `resolution`, `duration`, `seed`. 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-2.5-image-to-video-fast.
Average end-to-end generation time on WaveSpeedAI is around 333 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 (Alibaba). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.