It is a composition decision, not a formatting one. The model composes for the frame it was given: ask for 9:16 and it frames a tall shot; ask for 16:9 and it frames a wide one. The same prompt at two ratios is not the same picture cropped — it is two different pictures.
That is why cropping after the fact is the expensive option. Cutting a 16:9 clip down to vertical throws away most of the frame and usually the composition with it, because the subject was placed for a wide frame. Generating at the ratio you will publish at costs the same and keeps the framing intact.
Support varies more than people expect. Some models accept a long list of ratios, others a handful, and a few take an explicit pixel size or an "adaptive" setting that follows the input image instead.
In practice
- 9:16 for full-screen mobile, 1:1 for feed squares, 16:9 for landscape players, 4:5 for tall feed posts.
- Reframing later is a separate job with its own tooling — plan the ratio before generating.
- A model that takes an explicit width and height still has a ratio; it is just implied by the numbers.
Frame shapes the catalog accepts
Every aspect ratio at least one live model will render, and how many models offer it. 196 of the 296 models in the Versely catalog qualify.
| Model | Provider | Type |
|---|---|---|
| GPT Image 2 Text to Image | OpenAI | Image |
| Mai Image 2.5 Edit | Microsoft | Image |
| Happy Horse 1.0 Text to Video | Alibaba | Video |
| Nano Banana 2 | Image | |
| Seedance 2.0 | ByteDance | Video |
| Seedream 5.0 Pro | ByteDance | Image |
| Wan 2.7 Text to Video | Wan | Video |
| Kling 2.5 Turbo | Kling | Video |
Browse all 90 spec pages for full settings, resolutions and credit costs.
The mistake to avoid
Generating everything wide and reformatting at the end. The subject sits in the middle third and the vertical crop leaves you with headroom and a chin.
Go deeper
Aspect Ratios: 9:16, 1:1, 16:9 and Where Each Wins
A working guide to video aspect ratios: where 9:16, 1:1, and 16:9 each win, per-platform rules, safe zones, and generating at the right ratio from the start.
Where you will run into it
- Change a Video's Aspect Ratio — One clip. Any frame.
- Make a Video Vertical — Landscape in. Full-screen mobile out.
- Convert a Vertical Video to Horizontal — Phone-shot footage, made presentation-ready.
Related terms
Resolution
Resolution is how many pixels an output contains, usually named by its height — 720p, 1080p, 4K — and set before generation rather than after.
Camera control
Camera control is the set of inputs that decide how the virtual camera behaves during a generated clip — whether it pushes in, orbits, pans, or stays locked off.
Style preset
A style preset is a named look — cinematic, anime, documentary — that a model applies without you having to describe it in the prompt.
Text-to-image
Text-to-image renders a still picture from a written description, with no picture going in.
Seed
A seed is the number that decides the random starting noise for a generation, so the same seed with the same settings reproduces the same output.
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.