muapi Logomuapi Logo
muapi Logomuapi Logo

Vidu Q4 Reference to Video: Image-to-Video

Create videos from up to 15 reference images and 3 audio clips with Vidu Q4. Up to 4K with native audio. Pay per generation, no subscription. Vidu Q4 Reference-to-Video builds a 3-16 second clip at up to 4K from up to 15 reference images and 3 reference audio clips, keeping subjects consistent and adding synchronized dialogue and sound effects.

Interactive model controls

Vidu Q4 Reference-to-Video builds a 3-16 second clip at up to 4K from up to 15 reference images and 3 reference audio clips, keeping subjects consistent and adding synchronized dialogue and sound effects.

📝

Overview

About this model

Vidu Q4 Reference-to-Video generates a 3-16 second clip at up to 4K from a text prompt plus up to 15 reference images and up to 3 reference audio clips. Subjects and scenes from your references stay consistent, and the model adds synchronized dialogue and sound effects. Refer to inputs by order in the prompt, such as 'the person in reference image 2 says ... using reference audio 1'. For a single starting frame use Vidu Q4 Image to Video.

1Characters: Keep the same people consistent across scenes using reference images.
2Voice: Drive dialogue with reference audio clips for a matching voice.
3Ads: Combine product, model and background references into one shot.
4Storytelling: Compose multi-subject scenes from separate reference images.
💰

Pricing & Value

Cost analysis

muapiapp$0.095 per second at 720p ($0.475 per 5s clip)

Per-second pricing: 540p $0.045/s, 720p $0.095/s, 1080p $0.12/s, 2K $0.19/s, 4K $0.39/s. Audio included.

** Competitor pricing is estimated based on similar model architectures and usage tiers.

⚙️

Technical Details

Configuration schema

Promptstring

Text description of the video. Refer to inputs by order, e.g. "the man in reference image 2 says ... using reference audio 1".

Default ValueIn the scene of reference image 1, the person in reference image 2 turns to the person in reference image 3 and says: "What are you doing?"
Reference Image URLsarray

Reference image URLs (1 to 15). JPG, JPEG, PNG or WEBP.

Default Valueundefined
Reference Audio URLsarray

Optional reference audio URLs (up to 3). MP3 only, each 3-12 seconds and up to 50 MB.

Default Valueundefined
Aspect RatioEnum (5 options)

Output aspect ratio.

Default Value16:9
ResolutionEnum (5 options)

Output resolution.

Default Value720p
Durationint

Video length in seconds (3-16).

Default Value5
Audioboolean

Generate synchronized audio (dialogue and sound effects). Set false for a silent video.

Default Valuetrue
📖

Implementation Guide

Developer documentation

How to Use Vidu Q4 Reference to Video

  1. Collect references: Provide 1-15 image URLs in images_list, and optionally up to 3 MP3 clips (3-12 seconds each) in audios_list.

  2. Write the prompt: Refer to inputs by order, e.g. In the scene of reference image 1, the person in reference image 2 turns and says: "What are you doing?".

  3. Configure output: Set aspect_ratio (16:9, 9:16, 1:1, 4:3, 3:4), resolution (540p to 4k), duration (3-16s) and audio.

  4. Submit and collect the result: The endpoint is async — poll /api/v1/predictions/{request_id}/result or pass a webhook_url.

curl -X POST https://api.muapi.ai/api/v1/vidu-q4-reference-to-video \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{"prompt": "In the scene of reference image 1, the person in reference image 2 turns to the person in reference image 3 and says: What are you doing?", "images_list": ["https://example.com/scene.png", "https://example.com/person-a.png", "https://example.com/person-b.png"], "resolution": "1080p", "duration": 5, "aspect_ratio": "16:9", "audio": true}'
❓

Common Questions

Frequently asked

What resolutions and durations does Vidu Q4 support?

540p, 720p, 1080p, 2K and 4K output, with a duration of 3 to 16 seconds per clip.

Does Vidu Q4 generate audio?

Yes. Set audio to true (default) for synchronized dialogue and sound effects, or false for a silent video. Audio does not change the price.

How is pricing calculated?

Per second of output video, by resolution: $0.045/s at 540p, $0.095/s at 720p, $0.12/s at 1080p, $0.19/s at 2K and $0.39/s at 4K.

How do I get the result?

The endpoint is asynchronous. Poll /api/v1/predictions/{request_id}/result or pass a webhook_url to be notified when the video is ready.

How many references can I use?

Up to 15 reference images (images_list) and up to 3 reference audio clips (audios_list, MP3, 3-12 seconds each). Refer to them by order in the prompt, e.g. 'reference image 2' or 'reference audio 1'.

Which aspect ratios are supported?

16:9, 9:16, 1:1, 4:3 and 3:4, set with aspect_ratio.