# Vidu Q4 > Create a 3–16 second Vidu Q4 video from one photo or up to 12 photo references. Choose 540p through 4K with native audio, and keep the result private on MixVio. - [Canonical Vidu Q4 page](https://mixvio.ai/models/vidu-q4) - [Official model source](https://www.vidu.com/vidu-q4) ## Route summary - **Provider:** Vidu - **Media:** video - **Inputs:** Start photo · Up to 12 photos · 3 audio - **Output:** 540p–4K video + audio - **Duration:** 3–16s - **Native audio:** Yes - **Credits:** 10–437 credits - **Availability:** Available ## Capabilities - **More references:** Reference to video keeps characters, objects, and style together from owned photos. This library video shows the orange cat and the cream robot at the chessboard. MixVio accepts 1–12 photos and up to 3 MP3 files. The official product page lists 15 photos; this route follows the 12-photo limit. The video does not display twelve photos. - **Authentic voice:** Reference to video can take up to 3 MP3 voice files, and native audio stays on unless you turn it off. This official video starts with her on the cliff, cuts to a close-up with her mouth open, then returns to the palace. Spoken audio is in the file. The MP3 files are not on screen. - **One take, full scene:** One generation can run up to 16 seconds and change shots inside the same scene. This ruined-street video is 15 seconds at 1080p. It cuts from a kneeling soldier to an armored vehicle in the smoke, then to her running through the rubble. 2K and 4K are available; this file is 1080p. - **Native aspect ratio:** Image to video follows the start photo’s ratio, so this route has no aspect-ratio control. This tennis video stays portrait. Durations are 3–16 seconds, from 540p through 4K. Audio stays on. ## How to use 1. **Start from one photo or a reference pack:** Use image to video for exactly one owned start photo, or reference to video for 1–12 photos and up to 3 MP3 files. Prefill from a Key Feature or Example if you want—nothing runs until you generate. 2. **Set length, resolution, and sound:** Choose 3–16 seconds and 540p, 720p, 1080p, 2K, or 4K. Image to video follows the photo ratio and always includes audio. Reference to video also sets 16:9, 9:16, 4:3, 3:4, or 1:1, and Audio stays on unless you turn it off. Tag photos with @Image1 and audio with @Audio1. 3. **Generate, review, then iterate:** Confirm the credit estimate, then generate. Review identity, motion, and sound before publishing or iterating. ## Pricing From 10 credits for 3 seconds at 540p, up to 437 credits for 16 seconds at 4K. The default 5-second 540p video is 16 credits. Duration and resolution change the quote. Audio does not. - [MixVio pricing](https://mixvio.ai/pricing) ## FAQ ### What is Vidu Q4? Vidu Q4 is Shengshu’s video model. On MixVio it creates 3–16 second videos from one start photo, or from 1–12 photo references with optional MP3 audio, at 540p, 720p, 1080p, 2K, or 4K. [Vidu Q4](https://www.vidu.com/vidu-q4) ### What inputs does MixVio support? Image to video uses exactly one owned start photo and follows that photo’s ratio. Reference to video uses 1–12 owned photos, an aspect ratio, and up to 3 MP3 files. Prompts can be up to 5,000 characters. There is no text-to-video route. ### How many photo references and audio files can I add? Reference to video accepts 1–12 photos, each up to 50 MB, in JPEG, PNG, or WebP. Add 0–3 MP3 files. Each MP3 must be 3–12 seconds, and the three files together can run up to 36 seconds. MixVio keeps each audio upload at 15 MB. Tag photos with @Image1 and audio with @Audio1. ### Which durations, resolutions, and ratios are supported? Both routes support 3–16 seconds and 540p, 720p, 1080p, 2K, or 4K. The default is 5 seconds at 540p. Reference to video ratios are 16:9, 9:16, 4:3, 3:4, and 1:1. Image to video follows the start photo and does not take an aspect ratio. ### Does Vidu Q4 include native audio? Yes. Image to video always includes native audio, with no off switch. Reference to video includes native audio unless you turn Audio off. A reference MP3 can guide voice or sound; it does not change the credit quote. ### How many credits does Vidu Q4 use? Vidu Q4 is available on the Free plan when your balance covers the quote. A 3-second 540p video is 10 credits. The default 5-second 540p video is 16 credits. A 16-second 4K video is 437 credits. Duration and resolution change the quote. Audio does not. Confirm the reservation before you generate. Failed runs cost no credits. ### Is text-to-video, a last frame, or a video reference available? No. MixVio does not offer Vidu Q4 text-to-video, a last-frame photo, video references, a subject library, or a movement-amplitude control. Empty reference packs are rejected so the route cannot silently become text-to-video. ### Can I use Vidu Q4 videos commercially? Paid-plan outputs may be used commercially, subject to the Terms of Service and current Provider terms. You must have rights to every prompt, photo, voice, face, and brand. Free-plan outputs include the MixVio watermark and are for evaluation. MixVio does not guarantee exclusivity or trademark clearance. ### Are my prompts and outputs private on MixVio? Yes. Prompts are routed server-side, and final media is archived privately to your workspace. Keep private prompts and asset IDs out of shared links.