Vidu Image-to-Video converts images into smooth-transition videos with high visual quality and diverse motion for cinematic results. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Inactivo
$0.2por ejecución·~50 / $10
A photorealistic video of a young woman with long, flowing red hair standing on a windy cliffside at sunset. The wind gently lifts strands of her hair, making them dance in the warm, golden light. She takes a slow, deep breath, her shoulders rising and falling subtly. The camera is handheld, with a very slight, natural sway. Lens flare from the setting sun. Hyper-detailed, 4K, atmospheric.
A male model with a sharp jawline and intense gaze, dressed in a sleek, black leather trench coat and tailored trousers. He is leaning against a rain-slicked brick wall in a narrow alleyway of a futuristic, neon-lit city like Tokyo. The vibrant pink and blue lights from the signs reflect in the puddles on the ground and create a moody, enigmatic atmosphere. Cinematic, Blade Runner aesthetic, anamorphic lens flare, mysterious and cool tone.
An extreme close-up, photorealistic video of a cat's face. The cat's eyes slowly blink, its pupils dilating slightly in response to a subtle change in light. Its whiskers twitch almost imperceptibly. A soft, gentle purr is implied by the subtle vibration of its throat. Shot with a macro lens, shallow depth of field, focusing razor-sharp on the eyes. The texture of its fur and the wetness of its nose are incredibly detailed.
An ultra-realistic, slow-motion video of a basketball player completing a dunk. The net ripples violently as the ball passes through. Muscles on his arm are tense and defined. Beads of sweat are visible on his forehead. The camera, positioned courtside, tracks the action with a slight, natural shake. Arena lights create a dramatic lens flare. 4K, 120fps, hyper-detailed, realistic physics.
A macro video of a thick-cut steak searing on a cast-iron pan. Sizzling oil bubbles around the edges. A wisp of aromatic smoke rises and curls slowly. The surface of the steak caramelizes, turning a deep, rich brown. Butter melts and glazes the top, glistening under warm kitchen lighting. Static, top-down camera angle. Incredibly realistic texture, appetizing, high-resolution.
An epic, hyper-realistic video of a massive ocean wave cresting and beginning to curl, shot from the water level with a waterproof camera. Sunlight shines through the translucent turquoise water of the wave's lip. Sea spray and foam are thrown into the air. The motion is powerful and majestic, captured in breathtaking slow-motion (240fps). Cinematic, raw power of nature, 8K resolution.
A young woman sitting by the window in a cozy café, warm golden sunlight streaming through the glass, steam rising slowly from her coffee cup, soft reflections on the window, pedestrians passing outside, cars moving in the distance, camera begins with a medium shot and slowly pushes in for a closer look, cinematic depth of field.
A candid, slow-motion video of a young child blowing bubbles in a sunlit backyard. A large, shimmering bubble detaches from the wand and wobbles through the air, reflecting the world around it in its iridescent surface. The child's face is filled with pure, unadulterated joy and wonder. Shot from a low angle, capturing the child's perspective. Photorealistic, heartwarming, 120fps.
A black and white, 1940s film noir style video of a woman sitting in a dimly lit bar. Smoke from her cigarette curls upwards, catching the sliver of light from a half-closed window blind. She slowly raises her eyes to look at the camera with a mysterious expression. Subtle film grain, high contrast lighting (chiaroscuro), and a slow, almost imperceptible camera zoom-in. Realistic period detail, 35mm film look.
An epic, cinematic shot of ancient Roman legionaries marching in perfect formation along a dusty road. Their armor and shields glint in the Mediterranean sun. Dust is kicked up by their sandals. The camera pans with them, capturing the scale and discipline of the army. Shot to look like a scene from a high-budget historical film, hyper-realistic, 4K.
Vidu Image-to-Video is a fast and affordable image-to-video generation model that transforms static images into dynamic, animated videos. Simply provide an image and describe the motion you want — the model brings your photo to life with smooth, natural animation.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of desired motion and style. |
| image | Yes | Source image (upload or public URL). |
| movement_amplitude | No | Motion intensity: auto, small, medium, or large (default: auto). |
| seed | No | Set for reproducibility; -1 for random. |
| Output | Price |
|---|---|
| Per video | $0.20 |
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/vidu/image-to-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Image To Video below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"movement_amplitude": "auto",
"seed": -1
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/vidu/image-to-video" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/vidu/image-to-video";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"movement_amplitude": "auto",
"seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"movement_amplitude": "auto",
"seed": -1
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/vidu/image-to-video", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout"}:
raise RuntimeError(result)
if status not in {"created", "processing"}:
raise RuntimeError(f"Unexpected status: {status}")
time.sleep(2)Image To Video is a Vidu model for video generation from images, exposed as a REST API on WaveSpeedAI. Vidu Image-to-Video converts images into smooth-transition videos with high visual quality and diverse motion for cinematic results. 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 result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/vidu/vidu-image-to-video.
Image To Video 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.
Key inputs: `prompt`, `image`, `seed`, `movement_amplitude`. 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/vidu/vidu-image-to-video.
Median end-to-end generation time on WaveSpeedAI is around 93 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (Vidu). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.