seedinteger
Random seed for reproducibility. If None, a random seed is chosen.
vidu/q3/reference-to-video/mixVidu Q3 Mix by Shengshu - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.
Try the model
PNG, JPEG, WebP, or GIF · 20 MiB maximum each
Customize your input with more control.
What would you like to do next?
Select an example to load its inputs and result into the playground.
{
"prompt": "A character walking through a beach catching an apple.",
"reference_image_urls": [
"https://static.sandbase.ai/examples/6491437f-a95b-4ada-aea8-35a842416abf/input/aa16b50e-ec40-47df-bda1-3cf46278a584.png",
"https://static.sandbase.ai/examples/6491437f-a95b-4ada-aea8-35a842416abf/input/a35599ea-7845-46e2-b591-0a51da11c67c.png",
"https://static.sandbase.ai/examples/6491437f-a95b-4ada-aea8-35a842416abf/input/faffe658-17e3-41a9-ade8-f307be1c4ff7.png"
]
}Vidu Q3 Mix reference-to-video: reference images keep characters and objects consistent in a 1–16 second clip with native audio.
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 2,000 characters. |
aspect_ratio | 16:9 / 9:16 / 4:3 / 3:4 / 1:1 | 16:9 | Output frame shape. |
audio | boolean | true | Generate native audio. Same price on or off. |
resolution | 360p / 540p / 720p / 1080p | 720p | Sets the per-second rate. |
duration | integer 1–16 | 5 | Output length in seconds. |
seed | integer | random | Fix it to compare prompt changes. |
reference_image_urls | image URL[], required | — | Reference images, Image 1, Image 2, … |
You pay for output seconds: $0.07 at 360p or 540p and $0.154 at 720p or 1080p.
| Output | 540p | 720p | 1080p |
|---|---|---|---|
| 4s | $0.28 | $0.616 | $0.616 |
| 5s (default) | $0.35 | $0.77 | $0.77 |
| 8s | $0.56 | $1.232 | $1.232 |
| 16s | $1.12 | $2.464 | $2.464 |
Failed runs are not charged.
Other Vidu Q3 endpoints: vidu/q3/text-to-video, vidu/q3/image-to-video, vidu/q3/text-to-video/turbo, vidu/q3/image-to-video/turbo.
Start building
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "vidu/q3/reference-to-video/mix",
"audio": true,
"prompt": "A character walking through a beach catching an apple.",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"reference_image_urls": [
"https://static.sandbase.ai/examples/shengshu/vidu/q3/reference-to-video/mix/input_reference_image_urls_0.png",
"https://static.sandbase.ai/examples/shengshu/vidu/q3/reference-to-video/mix/input_reference_image_urls_1.png",
"https://static.sandbase.ai/examples/shengshu/vidu/q3/reference-to-video/mix/input_reference_image_urls_2.png"
]
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.
export SANDBASE_API_KEY="YOUR_API_KEY"Keep the key on your server. Do not expose it in browser code or commit it to a repository.
POST to /v1/run with this model ID and its inputs. The request example above includes submission and polling.
Use the returned run ID to poll until the status is completed, failed or timeout. Read output only after completed.
curl "https://api.sandbase.ai/v1/run/$RUN_ID" \
-H "Authorization: Bearer $SANDBASE_API_KEY"Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.
Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.
seedintegerRandom seed for reproducibility. If None, a random seed is chosen.
audiobooleanWhether to use direct audio-video generation. When true, outputs video with sound.
Default: true
promptstringrequiredText prompt for video generation, max 2000 characters
durationintegerDuration of the video in seconds (1-16 for Q3 models)
Default: 5
Minimum: 1
Maximum: 16
resolutionstringOutput video resolution
Default: "720p"
Possible values: "360p", "540p", "720p", "1080p"
aspect_ratiostringThe aspect ratio of the generated image.
Default: "16:9"
Possible values: "16:9", "9:16", "4:3", "3:4", "1:1"
reference_image_urlsarrayrequiredURLs of 1 to 4 reference images used to keep subjects or scenes consistent
{
"model": "vidu/q3/reference-to-video/mix",
"audio": true,
"prompt": "A character walking through a beach catching an apple.",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"reference_image_urls": [
"https://static.sandbase.ai/examples/shengshu/vidu/q3/reference-to-video/mix/input_reference_image_urls_0.png",
"https://static.sandbase.ai/examples/shengshu/vidu/q3/reference-to-video/mix/input_reference_image_urls_1.png",
"https://static.sandbase.ai/examples/shengshu/vidu/q3/reference-to-video/mix/input_reference_image_urls_2.png"
]
}A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
[
{
"poster": "https://static.sandbase.ai/examples/posters/207cfbc138fba616ee0b.jpg",
"source": "Vidu schema mirror",
"source_url": "https://www.vidu.com/",
"url": "https://static.sandbase.ai/examples/6491437f-a95b-4ada-aea8-35a842416abf/output/1baebebd-d9e3-4e36-bf6f-5d06bb0836be.mp4"
}
]