Vidu Q4
vidu-q4Animate one starting image, or keep subjects and voices consistent using reference media. Image mode has native audio; reference mode has optional audio. Images and voice clips must be at most 50 MB combined.
Pricing
Includes our margin. Charged per request from your balance.
- Minimum charge
- $0.16
Per second by resolution
- 540p
- $0.054
- 720p
- $0.11
- 1080p
- $0.15
- 2K
- $0.23
- 4K
- $0.47
Both modes use the same duration and resolution pricing. Audio adds no surcharge.
Details
- Provider
- Vidu
- Added
- Oct 7, 2026
Options
Parameters this model accepts.
| Parameter | Values | Default |
|---|---|---|
mode | Image to video, Reference to video Default | image-to-video |
seedUse -1 for a random result. | -1 or more Default | -1 |
duration | 3–16 seconds Default | 5 |
imageUrlStarting PNG, JPEG or WebP image (up to 50 MB), required in image-to-video. An imageAttachmentId or imageDataUrl is also accepted. | Text | — |
resolution | 540p, 720p, 1080p, 2K, 4K Default | 720p |
aspect_ratio | 16:9, 9:16, 4:3, 3:4, 1:1 Default | 16:9 |
generate_audio | On or off Default | off |
reference_audiosReference mode only. Up to 3 MP3 voice clips, 3–12 seconds each, at most 50 MB. Enable generate_audio. Prompt tags: [reference_audio_1]. | Text | — |
reference_imagesReference mode only. Up to 12 image URLs or data URIs, including a starting image if supplied. Prompt tags: [@reference_image_1]. | Text | — |