Wan 2.1 I2V 480P | Fast Image-to-Video API

WAN 2.1 Image-to-Video 480p — wavespeed-ai/wan-2.1/i2v-480p

wavespeed-ai/wan-2.1/i2v-480p animates a single image into a short, smooth 480p video clip with natural motion, stable framing, and strong prompt control—ideal for fast I2V iteration and lightweight production previews.

What it’s good at

Turning a still image into a 5–10s video with coherent motion
Subtle, natural gestures (talking-to-camera, nods, hand movement)
Smooth camera feel (gentle push-in, slight handheld, slow pan) without over-shaking
Quick story beats for ads, explainers, and social clips at 480p

Playground inputs

Image (required): the source frame to animate
Prompt (required): describe subject, action, environment, and camera
Negative prompt (optional): reduce blur, jitter, artifacts, unwanted styles
Size: 480p
Duration: 5s or 10s

Prompting guide for natural I2V

Write like a director’s brief:

Subject: who is in frame
Action: what they do (small, realistic verbs work best)
Environment: lighting + background
Camera: framing + motion style
Motion quality: smooth, natural, stable

Example prompt (talking head / business): A confident young tech professional standing in a modern office, talking to the camera with calm hand gestures. Soft daylight, clean environment, business casual outfit, focused expression. Center frame, smooth motion, natural micro-expressions.

Negative prompt suggestions: blurry, jittery, shaky camera, low quality, distorted face, warped hands, inconsistent motion

Use cases

Product demos: bring a hero image to life with subtle motion and camera polish
Corporate explainers: talking-to-camera clips from a portrait-style photo
Social ads: quick 5-second motion posts for faster iteration
Concept validation: test prompts and motion direction cheaply before higher resolutions

Pricing

Model	Resolution	Duration	Price per run
wavespeed-ai/wan-2.1/i2v-480p	832×480	5s	$0.20
wavespeed-ai/wan-2.1/i2v-480p	832×480	10s	$0.30

Notes

For the most stable faces, keep actions subtle (talk, nod, small gestures) and avoid extreme head turns.
If motion looks too “busy,” describe a calmer camera style (locked-off, slow push-in, gentle handheld).
If details smear, add stronger constraints in the prompt (center frame, steady, smooth motion) and use a negative prompt that targets blur/jitter.

Wan 2.1 I2v 480p API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.1/i2v-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 2.1 I2v 480p below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.1/i2v-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",
    "image": "https://example.com/your-input.jpg",
    "negative_prompt": "blurry, low quality, distorted",
    "size": "832*480",
    "num_inference_steps": 30,
    "duration": 5,
    "guidance_scale": 5,
    "flow_shift": 3,
    "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("wavespeed-ai/wan-2.1/i2v-480p", {
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "image": "https://example.com/your-input.jpg",
        "negative_prompt": "blurry, low quality, distorted",
        "size": "832*480",
        "num_inference_steps": 30,
        "duration": 5,
        "guidance_scale": 5,
        "flow_shift": 3,
        "seed": -1
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "wavespeed-ai/wan-2.1/i2v-480p",
    {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "image": "https://example.com/your-input.jpg",
    "negative_prompt": "blurry, low quality, distorted",
    "size": "832*480",
    "num_inference_steps": 30,
    "duration": 5,
    "guidance_scale": 5,
    "flow_shift": 3,
    "seed": -1
}
)

print(output["outputs"][0])  # → URL of the generated output

Wan 2.1 I2v 480p API — Frequently asked questions

What is the Wan 2.1 I2v 480p API?

Wan 2.1 I2v 480p is a WaveSpeedAI model for video generation from images, exposed as a REST API on WaveSpeedAI. Wan 2.1 i2v-480p turns images into unlimited 480p AI videos with the Wan 2.1 image-to-video model, perfect for fast 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.

How do I call the Wan 2.1 I2v 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/wavespeed-ai/wan-2.1-i2v-480p.

How much does Wan 2.1 I2v 480p cost per run?

Wan 2.1 I2v 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 2.1 I2v 480p accept?

Key inputs: `prompt`, `image`, `duration`, `size`, `seed`, `guidance_scale`. 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-2.1-i2v-480p.

How long does Wan 2.1 I2v 480p take to generate?

Average end-to-end generation time on WaveSpeedAI is around 45 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 2.1 I2v 480p outputs commercially?

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.

示例查看全部

相关模型

README