vidu/q3/reference-to-video/mix
Vidu 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.
PNG, JPEG, WebP, or GIF · 20 MiB maximum each
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runvidu/q3/reference-to-video/mixInput Schema
7 parameters · 1 required · 6 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Required | Text prompt for video generation, max 2000 characters · Max length: 2000 |
seed | integer | Optional | Random seed for reproducibility. If None, a random seed is chosen. |
audio | boolean | Optional | Whether to use direct audio-video generation. When true, outputs video with sound. · Default: true |
duration | integer | Optional | Duration of the video in seconds (1-16 for Q3 models) · Min: 1 · Max: 16 · Default: 5 |
resolution | string | Optional | Output video resolution · Options: 360p, 540p, 720p, 1080p · Default: "720p" 360p540p720p1080p |
aspect_ratio | string | Optional | The aspect ratio of the generated image. · Options: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16 21:916:93:24:35:41:14:53:42:39:16 |
reference_image_urls | string[] | Optional | URLs of 1 to 4 reference images used to keep subjects or scenes consistent |
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "vidu/q3/reference-to-video/mix",
"audio": true,
"prompt": "A character walking through a beach catching an apple.",
"duration": 5,
"resolution": "720p",
"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"
]
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
Vidu Q3 Reference to Video Mix
Vidu Q3 Reference to Video Mix is a specialized SandBase endpoint built to build a new video from written direction plus up to four visual references rather than a fixed first frame. It is most useful when teams need multi-reference subject guidance, scene mixing, native sound, and free composition across ten aspect ratios, with the route’s inputs defining a repeatable production contract instead of leaving critical delivery choices to an ad-hoc manual workflow.
Use this exact route when its input mode matches the creative asset already in hand: describe the visual or spoken result clearly, set only the controls that support the intended delivery, and keep the subject, action, environment, camera or performance direction internally consistent. The result is returned asynchronously as a downloadable media URL suitable for review, automation, or downstream finishing.
Highlights
- Reference-driven continuity. Up to four images can guide recurring people, objects, wardrobe, or environments across a newly composed shot.
- Mix rather than animate. References act as visual ingredients, leaving room for the prompt to establish a fresh scene and motion instead of copying one starting frame.
- Sound-aware generation. Native audiovisual output can pair the designed action with dialogue, ambience, and effects in one pass.
- Format-ready composition. Ten aspect ratios, four resolution tiers, and 1–16 second timing make the route adaptable to landscape, square, and vertical delivery.
Pricing
Billing follows the selected duration and resolution. The standard rate is $0.0700 per second at 360p/540p and $0.1540 per second at 720p/1080p.
| Duration | Resolution | Price |
|---|---|---|
| 1 sec | 360p | $0.0700 |
| 1 sec | 540p | $0.0700 |
| 1 sec | 720p | $0.1540 |
| 1 sec | 1080p | $0.1540 |
| 2 sec | 360p | $0.1400 |
| 2 sec | 540p | $0.1400 |
| 2 sec | 720p | $0.3080 |
| 2 sec | 1080p | $0.3080 |
| 3 sec | 360p | $0.2100 |
| 3 sec | 540p | $0.2100 |
| 3 sec | 720p | $0.4620 |
| 3 sec | 1080p | $0.4620 |
| 4 sec | 360p | $0.2800 |
| 4 sec | 540p | $0.2800 |
| 4 sec | 720p | $0.6160 |
| 4 sec | 1080p | $0.6160 |
| 5 sec | 360p | $0.3500 |
| 5 sec | 540p | $0.3500 |
| 5 sec | 720p | $0.7700 |
| 5 sec | 1080p | $0.7700 |
| 6 sec | 360p | $0.4200 |
| 6 sec | 540p | $0.4200 |
| 6 sec | 720p | $0.9240 |
| 6 sec | 1080p | $0.9240 |
| 7 sec | 360p | $0.4900 |
| 7 sec | 540p | $0.4900 |
| 7 sec | 720p | $1.0780 |
| 7 sec | 1080p | $1.0780 |
| 8 sec | 360p | $0.5600 |
| 8 sec | 540p | $0.5600 |
| 8 sec | 720p | $1.2320 |
| 8 sec | 1080p | $1.2320 |
| 9 sec | 360p | $0.6300 |
| 9 sec | 540p | $0.6300 |
| 9 sec | 720p | $1.3860 |
| 9 sec | 1080p | $1.3860 |
| 10 sec | 360p | $0.7000 |
| 10 sec | 540p | $0.7000 |
| 10 sec | 720p | $1.5400 |
| 10 sec | 1080p | $1.5400 |
| 11 sec | 360p | $0.7700 |
| 11 sec | 540p | $0.7700 |
| 11 sec | 720p | $1.6940 |
| 11 sec | 1080p | $1.6940 |
| 12 sec | 360p | $0.8400 |
| 12 sec | 540p | $0.8400 |
| 12 sec | 720p | $1.8480 |
| 12 sec | 1080p | $1.8480 |
| 13 sec | 360p | $0.9100 |
| 13 sec | 540p | $0.9100 |
| 13 sec | 720p | $2.0020 |
| 13 sec | 1080p | $2.0020 |
| 14 sec | 360p | $0.9800 |
| 14 sec | 540p | $0.9800 |
| 14 sec | 720p | $2.1560 |
| 14 sec | 1080p | $2.1560 |
| 15 sec | 360p | $1.0500 |
| 15 sec | 540p | $1.0500 |
| 15 sec | 720p | $2.3100 |
| 15 sec | 1080p | $2.3100 |
| 16 sec | 360p | $1.1200 |
| 16 sec | 540p | $1.1200 |
| 16 sec | 720p | $2.4640 |
| 16 sec | 1080p | $2.4640 |
When to Use
| Scenario | Why this route fits |
|---|---|
| Concept development | Choose Vidu Q3 Reference to Video Mix when its mix workflow matches the starting material and you need several clearly directed variations. |
| Production iteration | Use explicit duration, resolution, ratio, seed, or quality controls to compare versions without changing the core creative brief. |
| Channel adaptation | Generate directly in the landscape, square, portrait, or vertical format required by the destination whenever that control is available. |
| Automated pipelines | Integrate the asynchronous media URL into review queues, asset libraries, publishing tools, or a later finishing stage. |
| Alternative route | Pick a related text-, image-, reference-, edit-, or turbo route when the available source media or required degree of control is different. |
Prompt Guide
Lead with the main subject or source asset, then describe the intended action or transformation, environment, composition, camera or vocal delivery, lighting and mood. Keep instructions concrete and compatible; use the route’s explicit fields for duration, resolution, ratio, quality, voice, or reproducibility instead of burying those settings in prose.
{
"prompt": "A cinematic product reveal with deliberate subject motion, coherent lighting, and a slow camera push.",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "21:9",
"audio": true,
"reference_image_urls": [
"https://example.com/reference-1.jpg"
]
}
Technical Specs
| Property | Details |
|---|---|
| Model ID | vidu/q3/reference-to-video/mix |
| Required inputs | prompt |
| Execution | Asynchronous; poll the returned generation ID |
| Output | Downloadable media URL |
seed | integer; optional |
audio | boolean; optional; default: true |
prompt | string; required |
duration | integer; optional; range: 1–16; default: 5 |
resolution | string; optional; choices: 360p, 540p, 720p, 1080p; default: 720p |
aspect_ratio | string; optional; choices: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16 |
reference_image_urls | array; optional |
Related Models
| Model | Best for |
|---|---|
vidu/q3/text-to-video | Alternative text to video workflow |
vidu/q3/image-to-video | Alternative image to video workflow |
vidu/q3/image-to-video/turbo | Alternative turbo workflow |
vidu/q3/text-to-video/turbo | Alternative turbo workflow |

