Resolution claims need their conditions
Resolution is named by 20 tools, and almost every figure comes with a condition. MiniMax lists 1080p at 6 seconds; Kling AI and Vidu name 4K for images, not video; OpenAI names 1080p for sora-2-pro only. From 4 source pages, read 2026-09-25; no maker pays to be listed.
A 4K claim for one model says nothing about the others on the same platform.
For finishing, bit depth and format matter as much as pixel count.
Read the model and length a resolution applies to before planning a delivery around it.
| Tool | Hook | What the documentation says |
|---|---|---|
| MiniMax | Resolution | 1080p at 6 seconds for Hailuo 2.3 |
| Kling AI | Resolution | Direct 2K and 4K output named for its image models |
| Vidu | Resolution | Up to 4K output named for image generation |
| OpenAI Sora | Resolution | 1080p exports in landscape or portrait with sora-2-pro |
Inclusion rule. Readings from the register used on this page. Order. The order the text takes them in.
1As the documentation puts it
1080p 6s • 768p 6s, 10s 24 fps
MiniMax, API documentation
series generation & batch optimization and direct 2K/4K output
Kling AI, API documentation
Text and reference to image with up to 4K output and strong subject consistency.
Vidu, API platform
Use sora-2-pro when you need 1080p exports in 1920x1080 or 1080x1920 .
OpenAI, video generation guide
- Models1080p at 6 seconds for Hailuo 2.3
- Choose by modelDirect 2K and 4K output named for its image models
- Image generationUp to 4K output named for image generation
- Models1080p exports in landscape or portrait with sora-2-pro
2Where a drama generator fits
Read against “Resolution claims need their conditions”, this is how SceneMixer describes the matching stage of its own pipeline:
The same way as a photographic one: the character is generated once as a reference sheet and that image is sent with every shot they are in, along with a couple of face-distinguishing notes. Shots refer to the character rather than re-describing their look.
SceneMixer, AI Animated Series Generator — “How do I keep a stylised character on model across episodes?” (read 2026-10-13)
SceneMixer writes dialogue into the script analysis, assigns each line to a shot with a speaker and a short delivery note, and the video model performs it — picture and audio generated together, so the mouth forms that sentence in the language you chose.
SceneMixer, AI Dialogue Generator (read 2026-10-13)