vidu/q3-pro 🔢✓📝🖼️❓ → 🖼️

⭐ Official ▶️ 1.7K runs 📅 Mar 2026 ⚙️ Cog 0.16.9 ⚖️ License
image-to-video-with-audio start-end-to-video text-to-video-with-audio

About

High-fidelity video generation with text-to-video, image-to-video, and start-end-to-video modes. Up to 16 seconds at 1080p with synchronized audio.

Example Output

Prompt:

"A rabbit warrior slowly raises his sharp sword, winks at the camera, and is captured with a Hitchcock zoom effect."

Output

Performance Metrics

238.21s Prediction Time
238.24s Total Time
All Input Parameters
{
  "audio": true,
  "prompt": "A rabbit warrior slowly raises his sharp sword, winks at the camera, and is captured with a Hitchcock zoom effect.",
  "duration": 5,
  "resolution": "720p",
  "aspect_ratio": "16:9"
}
Input Parameters
seed Type: integer
Random seed. Set for reproducible generation.
audio Type: booleanDefault: true
Whether to generate audio synchronized with the video (dialogue and sound effects).
prompt (required) Type: string
Text prompt for video generation. Maximum 5000 characters.
duration Type: integerDefault: 5Range: 1 - 16
Duration of the video in seconds.
end_image Type: string
End frame image for the video. Must be used together with start_image for start-end-to-video mode. The aspect ratios of start and end images must be similar (ratio between 0.8 and 1.25). Supported formats: png, jpeg, jpg, webp.
resolution Default: 720p
Resolution of the output video.
start_image Type: string
Start frame image for the video. When provided without an end_image, the model runs in image-to-video mode. Supported formats: png, jpeg, jpg, webp.
aspect_ratio Default: 16:9
Aspect ratio of the output video. Only used in text-to-video mode (ignored when images are provided).
Output Schema

Output

Type: stringFormat: uri

Example Execution Logs
Task created: 927358055639699456
Video generated in 235.5sec
Downloading 4020469 bytes
Downloaded 3.83MB in 2.25sec
Output video duration: 5.042s
Version Details
Version ID
1a8e2767ffcf46d64a4d97727f187ccc2cadc59db844db7167327e01a2a79390
Version Created
April 12, 2026
Run on Replicate →