Vidu Start End To Video Q2 Turbo
Playground
Try it on WavespeedAI!Vidu Q2 Turbo Start-End to Video creates smooth Image-to-Video transitions between start and end images with fast high-quality results. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
Vidu Q2 Start-End to Video Turbo
Vidu Q2 Start-End to Video Turbo creates a coherent video from just two images: a start frame and an end frame. Turbo accelerates bi-frame interpolation with optimized inference for faster turnaround and smoother motion — ideal for scene transitions, bridging shots, and rapid storytelling.
Why Choose This?
-
Bi-frame guidance Anchors identity, layout, and lighting from both start and end frames.
-
Turbo temporal smoothing Reduces flicker and popping while preserving subject integrity at higher throughput.
-
Object and human-aware motion Protects faces, hands, hair, and thin structures while animating garments and props.
-
Layout-smart interpolation Respects depth, occlusion, and parallax for clean foreground/background motion.
-
Adaptive camera pathing Natural pans, push-ins, and dolly moves without warping.
-
Speed-optimized pipeline Faster than Pro at the same settings, perfect for rapid iteration.
Parameters
| Parameter | Required | Description |
|---|---|---|
| start_frame | Yes | Starting image for the video |
| end_frame | Yes | Ending image for the video |
| prompt | No | Describe motion style, mood, or camera movement |
| duration | No | Video length in seconds (1–10) |
| resolution | No | Output resolution: 540p, 720p, or 1080p |
| movement_amplitude | No | Motion intensity: auto, small, medium, or large |
| bgm | No | Enable background music generation |
| seed | No | Random seed for reproducibility (-1 for random) |
How to Use
- Upload start frame — the beginning image of your video.
- Upload end frame — the ending image of your video.
- Write a prompt (optional) — describe motion style, mood, or camera movement.
- Set duration — choose video length from 1 to 10 seconds.
- Select resolution — 540p, 720p, or 1080p based on quality needs.
- Enable BGM (optional) — add background music automatically.
- Set seed (optional) — use for reproducible results.
- Run — submit and download your video.
Pricing
| Resolution | Duration | Price |
|---|---|---|
| 540p | 1s | $0.03 |
| 540p | 2s | $0.04 |
| 540p | 3s | $0.05 |
| 540p | 4s | $0.06 |
| 540p | 5s | $0.07 |
| 540p | 6s | $0.08 |
| 540p | 7s | $0.09 |
| 540p | 8s | $0.10 |
| 540p | 9s | $0.20 |
| 540p | 10s | $0.30 |
| 720p | 1s | $0.04 |
| 720p | 2s | $0.05 |
| 720p | 3s | $0.10 |
| 720p | 4s | $0.15 |
| 720p | 5s | $0.20 |
| 720p | 6s | $0.25 |
| 720p | 7s | $0.30 |
| 720p | 8s | $0.35 |
| 720p | 9s | $0.45 |
| 720p | 10s | $0.50 |
| 1080p | 1s | $0.175 |
| 1080p | 2s | $0.225 |
| 1080p | 3s | $0.275 |
| 1080p | 4s | $0.325 |
| 1080p | 5s | $0.375 |
| 1080p | 6s | $0.425 |
| 1080p | 7s | $0.475 |
| 1080p | 8s | $0.525 |
| 1080p | 9s | $0.625 |
| 1080p | 10s | $0.725 |
Billing Rules
540p: $0.03 for 1s, +$0.01/s up to 8s, then $0.20 for 9s, $0.30 for 10s
720p: $0.04 for 1s, $0.05 for 2s, then +$0.05/s from 3s
1080p: $0.175 for 1s, then +$0.05/s up to 8s, then +$0.10/s for 9s-10s
Best Use Cases
- Storyboarding and Concept Animation — Animate between keyframes to preview beats in seconds.
- Scene Interpolation — Seamless bridges between shots with consistent style.
- Before/After Visualization — Visualize transformations with smooth, controlled motion.
- Film Pre-visualization — Explore blocking and camera moves early and often.
- Transitions — Create smooth video transitions between key moments.
Pro Tips
- For large pose or layout jumps, try shorter durations or insert intermediate keyframes.
- Use consistent lighting and style between start and end frames for smoother interpolation.
- Turbo generally returns faster than Pro at the same settings.
- Add a prompt to guide the motion style and camera movement between frames.
Notes
- Maximum duration is 10 seconds per generation.
- Actual processing time depends on resolution, duration, and current queue load.
- Ensure you have rights to all uploaded images.
- For complex transformations, consider using intermediate keyframes.
Related Models
- Vidu Q2 Pro Start-End to Video — Higher quality at slightly higher cost.
- Vidu Q2 Turbo Image-to-Video — Single image to video generation.
- Vidu Q2 Turbo Text-to-Video — Generate videos from text prompts only.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/vidu/start-end-to-video-q2-turbo" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"duration": 5,
"resolution": "720p",
"bgm": true,
"movement_amplitude": "auto",
"seed": -1
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | The positive prompt for the generation. | |
| image | string | Yes | - | The start image for generating the output. | |
| last_image | string | Yes | - | - | The end image for generating the output. |
| duration | number | No | 5 | 1 ~ 10 | The duration of the generated media in seconds. |
| resolution | string | No | 720p | 720p, 1080p | Video resolution. |
| bgm | boolean | No | true | - | The background music for generating the output. |
| movement_amplitude | string | No | auto | auto, small, medium, large | The movement amplitude of objects in the frame. Defaults to auto, accepted value: auto small medium large. |
| seed | integer | No | -1 | -1 ~ 2147483647 | The random seed to use for the generation. -1 means a random seed will be used. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Array of URLs to the generated content (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction, the ID of the prediction to get |
| data.model | string | Model ID used for the prediction |
| data.outputs | string | Array of URLs to the generated content (empty when status is not completed). |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |