Seedance Lite creates coherent multi-shot image-to-video clips in 1080p with smooth, stable motion and accurate prompt following. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.45per run·~22 / $10
An astronaut in a gleaming, futuristic suit floats gracefully through a swirling nebula, surrounded by bioluminescent space flora. The scene has a soft, dreamlike, pastel aesthetic.
Brushstrokes animate into live painting tidal wave under timelapse moon
Wolf dissolves into flying triangles reforming as a panther, drone rotation shot
Wings whirring levitate books into floating constellations, slow-motion
Rabbit's watering can sprouts glowing vines engulfing cottages in timelapse
360° grind on neon highway trailing particle fire, fisheye lens warp
The phoenix flew over the rolling hills and landed on a very tall geometric tree
Cat pounces causing data-wave ripple freezing raindrops mid-air
Helmet touch makes crystals bloom into alien flora with stop-motion pop
A couple walking hand-in-hand on a beach at sunset, with the sea breeze gently blowing through their hair. They look at each other and smile, eyes full of love. The camera slowly pushes in on them from the side.
A young woman, dressed in a flowing silk gown, gracefully dances alone on a dimly lit stage. Her movements are fluid and expressive, with spotlights highlighting her every turn. The camera slowly orbits her.
Seedance V1 Lite Image-to-Video 1080p is Full HD image-to-video generation model that transforms static images into stunning 1080p videos. With optional last-frame control, flexible durations up to 12 seconds, and multiple aspect ratios, create cinematic animations from any image.
| Parameter | Required | Description |
|---|---|---|
| prompt | No | Text description of desired motion and style. |
| image | Yes | Source image to animate (upload or public URL). |
| last_image | No | Optional ending frame image for controlled transitions. |
| duration | No | Video length: 2–12 seconds (default: 5). |
| aspect_ratio | No | Output aspect ratio (default: matches source). |
| camera_fixed | No | Fix camera position for stable shots. |
| seed | No | Set for reproducibility; -1 for random. |
| Aspect Ratio | Best For |
|---|---|
| 21:9 | Cinematic ultrawide content |
| 16:9 | YouTube, widescreen displays |
| 4:3 | Classic format, presentations |
| 1:1 | Instagram posts, social media squares |
| 3:4 | Portrait photos, Pinterest |
| 9:16 | TikTok, Instagram Stories, Reels |
| Duration | Price |
|---|---|
| 5 seconds | $0.45 |
| 10 seconds | $0.90 |
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/bytedance/seedance-v1-lite-i2v-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 Seedance v1 Lite I2v 1080p below.
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/bytedance/seedance-v1-lite-i2v-1080p" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"image": "https://example.com/your-input.jpg",
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 5,
"aspect_ratio": "21:9",
"camera_fixed": 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("bytedance/seedance-v1-lite-i2v-1080p", {
"image": "https://example.com/your-input.jpg",
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 5,
"aspect_ratio": "21:9",
"camera_fixed": false,
"seed": -1
});
console.log(result.outputs[0]); // → URL of the generated output# pip install wavespeed
import wavespeed
output = wavespeed.run(
"bytedance/seedance-v1-lite-i2v-1080p",
{
"image": "https://example.com/your-input.jpg",
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 5,
"aspect_ratio": "21:9",
"camera_fixed": false,
"seed": -1
}
)
print(output["outputs"][0]) # → URL of the generated outputSeedance v1 Lite I2v 1080p is a ByteDance model for video generation from images, exposed as a REST API on WaveSpeedAI. Seedance Lite creates coherent multi-shot image-to-video clips in 1080p with smooth, stable motion and accurate prompt following. 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/bytedance/bytedance-seedance-v1-lite-i2v-1080p.
Seedance v1 Lite I2v 1080p starts at $0.45 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`, `aspect_ratio`, `duration`, `seed`, `camera_fixed`. 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/bytedance/bytedance-seedance-v1-lite-i2v-1080p.
Average end-to-end generation time on WaveSpeedAI is around 161 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 (ByteDance). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.