Vidu
Overview
Vidu is Shengshu Technology's (Tsinghua-affiliated) video model, first released in April 2024 and known for its reference-to-video feature keeping characters and objects consistent across clips; the Q series added native audio-video output.
Field checks and source notes
When sources disagree on a field, every reading is listed here with its own citation. We do not take a midpoint, invent a missing figure, or decide which side is right — follow the citation and judge for your case.
These field-level notes are recorded verbatim in Chinese in the source data. Open the Chinese version
Plain-language benchmarks
Practical facts
| Context length | Not disclosed |
|---|---|
| Max output | Not disclosed |
| Parameters | Not disclosed |
| Input | Not disclosed |
| Output price | Not disclosed |
| CNY | Official open-platform pricing (platform.vidu.cn): Q1 text-to-video and image-to-video at 5 seconds and 1080p cost CNY 2.50 per run; Q2 bills credits per second, so Q2-turbo image-to-video at 540P costs 6 credits for the first second and 2 credits for each further second (CNY list prices, per the vendor's official pricing page). |
| Free tier | Not disclosed |
| Output speed | Not disclosed |
| Release date | |
| License | Not disclosed |
Show technical data
Technical benchmark table
| Version | Release date | Status | Openness | Parameters | What changed | Detail | |
|---|---|---|---|---|---|---|---|
| Vidu Q3Showing version | Active | Closed source | Not disclosed | TBD | Detail | ||
| Vidu Q2 | Superseded | Closed source | Not disclosed | TBD | Detail | ||
| Vidu Q1 | Superseded | Closed source | Not disclosed | TBD | Detail | ||
| Vidu 1.0 | Superseded | Closed source | Not disclosed | TBD | Detail |
Last updated: · Sources on detail page