What resolution do AI video tools default to?
Where a page names a default, it is often below the maximum. Alibaba Cloud's Wan defaults to 1080P; Vidu's viduq3 and viduq2 default to 720p with 1080p available; Grok Imagine defaults to 480p, with 720p and 1080p on request. From 3 source pages, read 2026-09-25; no maker pays to be listed.
| Source | Figure | Where it applies |
|---|---|---|
| Alibaba Cloud Wan | 1080P, 720P or 480P, with 1080P the default | Wan3.0 video generation, resolution parameter |
| Grok Imagine | 1080p, 720p or 480p (the default); 1080p on grok-imagine-video-1.5 for text and image to video | Resolution table |
| Vidu | 540p, 720p or 1080p on viduq3 and viduq2 (720p default); viduq1 is 1080p only | Text to video, resolution parameter |
Inclusion rule. Vendor pages and references whose printed figures bear on this delivery target. Order. Alphabetical by source name.
1As printed
Default value: 1080P. Valid values: 1080P 720P 480P
Alibaba Cloud Model Studio, Wan3.0 video generation API reference
viduq3-pro , viduq3-turbo (1-16s): default 720p, available: 540p, 720p, 1080p
Vidu API docs, text to video
1080p Full HD quality 720p HD quality 480p Standard definition, faster processing (default)
xAI docs, video generation
2What it means for delivery
A default is the resolution a job comes out at when nobody changes it, which is how most drafts get made. Reading the default as the maximum under-rates a tool; reading the maximum as the default over-budgets a draft. The two figures answer different questions and both are worth checking.
- Wan3.0 video generation1080P, 720P or 480P, with 1080P the defaultresolution parameter
- Text to video540p, 720p or 1080p on viduq3 and viduq2 (720p default); viduq1 is 1080p onlyresolution parameter
- Resolution table1080p, 720p or 480p (the default); 1080p on grok-imagine-video-1.5 for text and image to video
3The production side of the spec
For a delivery question like “What resolution do AI video tools default to”, SceneMixer states the following about what it produces:
Video is 16:9 landscape by default, with 9:16 vertical available; you set it once per project. Segments are typically 4 to 15 seconds, and some model tiers go to 30.
SceneMixer, AI Short Drama Generator — “What length and aspect ratio does it output?” (read 2026-10-13)
SceneMixer turns a novel into a watchable short-drama series in one pipeline: upload the novel (Chinese or English) → AI extracts characters, scenes, and an episode-by-episode structure → generates consistent character and scene art → writes storyboard scripts → renders video segment by segment (16:9 by default, 9:16 in one setting) → composites full episodes.
SceneMixer, Turn a Novel into a Video Series with AI (read 2026-10-13)