Vidu Q3 Pro
Text & image to video
The quality tier of Vidu Q3: up to 16 seconds at up to 1080p, with native dialogue, effects and music.
AI video model · By ShengShu Technology
Vidu Q3 Pro and Q3 Turbo in your Qten account: story-driven clips with sound, up to 16 seconds.
Free plan · No credit card · Updated 2026-11-18
Vidu
By ShengShu Technology
2 versions of Vidu in one Qten account, from fast drafts to the newest release.
Vidu is the AI video model family from ShengShu Technology. Vidu Q3, released in January 2026, produces up to 16 seconds of 1080p video with native audio (dialogue, effects and music) in one pass, from text, images, start and end frames or up to four reference images. Qten offers Vidu Q3 Pro and Vidu Q3 Turbo.
Vidu comes from ShengShu Technology, a Chinese AI company working with Tsinghua University researchers. Vidu Q3, released on January 30, 2026, is built for story-driven work such as short dramas, ads and character scenes: it generates picture and sound together, supports text-to-video, image-to-video, start and end frames, and reference-to-video with up to four images. Q3 Pro favors quality; Q3 Turbo favors speed.
| Made by | ShengShu Technology |
|---|---|
| Newest on Qten | Vidu Q3 Pro |
| Versions on Qten | 2 |
| Max resolution | Up to 1080p |
| Max length | Up to 16 s |
| Native audio | Yes |
| Reference images | Up to 4 |
| Inputs | Text prompt · Start image · First & last frame · Reference images |
Limits are the maker's published figures, checked 2026-11-18. What you can use may depend on your plan.
2 versions of Vidu in one Qten account, from fast drafts to the newest release.
Text & image to video
The quality tier of Vidu Q3: up to 16 seconds at up to 1080p, with native dialogue, effects and music.
Text & image to video
The fast tier of Vidu Q3, for quick drafts and high volume, with the same input modes.
| Version | What it makes | Tier | Released |
|---|---|---|---|
| Vidu Q3 Turbo | Text & image to video | Fast / lower cost | — |
| Vidu Q3 Pro | Text & image to video | Pro tier | — |
Longer story beats in one generation.
Dialogue, effects and music generated with the picture.
Text, image, start and end frames, or reference images.
Up to four reference images keep people and props the same.
A young detective in a trench coat enters a rainy alley, stops, and whispers: "He was here." Thunder rumbles, neon reflections, 16:9.Use the three reference images (the girl, the red bicycle, the bakery) to show her riding past the bakery and waving at the baker, morning light, 9:16.Start frame: a closed flower bud. End frame: the flower fully open in sunlight. Smooth time-lapse, birdsong, 1:1.Character scenes with dialogue and sound.
Product stories with consistent props from references.
Start and end frames for controlled change.
16-second clips for Reels, Shorts and TikTok.
The other video models in the same Qten account. Pick per scene, or let Qten choose.
| Vidu | Kling | Seedance | MiniMax Hailuo | PixVerse | |
|---|---|---|---|---|---|
| Made by | ShengShu Technology | Kuaishou | ByteDance | MiniMax | PixVerse |
| Newest on Qten | Vidu Q3 Pro | Kling 4 | Seedance 2.5 | MiniMax H3 | PixVerse V6 Max |
| Versions on Qten | 2 | 6 | 7 | 7 | 3 |
| Max resolution | Up to 1080p | Up to 1080p | Up to 1080p | Up to 1080p | Up to 1080p |
| Max length | Up to 16 s | Up to 30 s (Kling 4) | Up to 30 s (Seedance 2.5) | Up to 15 s (MiniMax H3) | Up to 15 s (V6) |
| Native audio | Yes | Yes | Yes (Seedance 2.0 / 2.5) | Yes (MiniMax H3) | Yes (PixVerse V6 / V6 Max) |
| Inputs | Text prompt · Start image · First & last frame · Reference images | Text prompt · Start image · First & last frame · Reference images | Text prompt · Start image · Reference images · Audio | Text prompt · Start image · First & last frame · Reference images | Text prompt · Start image |
Limits are the maker's published figures, checked 2026-11-18. What you can use may depend on your plan.
Sign up on the Free plan. No credit card, and you get credits to start.
Write your prompt or script, then choose Vidu as the model, or let Qten pick the best model for each step.
Review the result, edit it in Qten, and post or schedule it to YouTube, TikTok, Instagram and more.
FAQ
Vidu Q3 is ShengShu Technology's AI video model, released in January 2026. It makes up to 16 seconds of 1080p video with native audio from text, images, frames or references.
Qten offers Vidu Q3 Pro and Vidu Q3 Turbo.
Qten has a Free plan with 100 free credits and no credit card. Generating with Vidu uses credits, depending on the tier and clip length. See the Pricing page for details.
Vidu Q3 makes clips of up to 16 seconds, at up to 1080p.
Vidu Q3 is a strong pick for story scenes with dialogue and reference images. Kling makes longer, multi-shot clips, up to 30 seconds with Kling 4. Both are in Qten.
No. You use Vidu from your Qten account with Qten credits, without a separate Vidu plan.
Model names and logos are trademarks of their owners. Qten is not affiliated with or endorsed by them.
Vidu and 130+ other AI models in one account. Start free.
Start creating free