Hedra Character 3 aspect ratios vs Sume Avatar Video ratios
Hedra Character 3 lists seven aspect ratios including 9:21 and 21:9. Sume Avatar Video supports five: 1:1, 3:4, 9:16, 4:3 and 16:9, default 9:16.
Hedra Character 3 lists seven aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16, 9:21 and 21:9. Sume Avatar Video supports five of those: 1:1, 3:4, 9:16, 4:3 and 16:9, with 9:16 as the default. The two ultra-tall and ultra-wide ratios, 9:21 and 21:9, are not in Sume's list.
Hedra's list is from its model page and Sume's from the docs, both read 2026-10-01.
Which ratios does each side list?
| Ratio | Hedra Character 3 | Sume Avatar Video |
|---|---|---|
| 1:1 | Listed | Listed |
| 4:3 | Listed | Listed |
| 3:4 | Listed | Listed |
| 16:9 | Listed | Listed |
| 9:16 | Listed | Listed (default) |
| 9:21 | Listed | Not listed |
| 21:9 | Listed | Not listed |
How do I set the ratio on Sume?
Send aspect_ratio on POST /v1/avatar-1.0/talking-video. If you omit it, the docs give 9:16. The resolution is currently 720p. See Generate avatar video.
What if I need a wider frame than 16:9?
Sume Avatar Video will not produce 21:9. One documented building block is Timeline compose, which takes one still and one video and returns one MP4 with both on screen at once, using operation of stack or overlay. It requires image.url and video.url, both already on media.sume.com. Whether it gives the frame shape you want depends on your layout, so check the output. For other models' ratio ranges see MiniMax H3 aspect ratios.
Which ratio should I pick for social output?
For vertical feeds use 9:16, which is also Sume's default. For square posts use 1:1. The extra Hedra ratios matter only if your placement specifically needs 9:21 or 21:9.
Sources
Related posts
More in Models
- HeyGen cinematic avatar API: 3 looks per shot vs Sume's one
HeyGen cinematic_avatar takes a prompt and 1-3 avatar looks with no script. Sume Avatar Video resolves one avatar per final video from a script.
- Ideogram 4 custom_model_uri vs Sume catalog ids and sume/auto
Ideogram's custom-model endpoint picks a private model by custom_model_uri. Sume has no such field: you choose a catalog id or sume/auto. What to send instead.
- Ideogram 8K output resolution API vs Sume 512 to 4K tiers
Ideogram 4.0 takes output_resolution 1k, 2k, 4k or 8k as a pixel budget. Sume's image route takes a normalized 512, 1K, 2K or 4K tier.
- Ideogram Z-Image resolution rules vs Sume image_size
Ideogram Z-Image takes WIDTHxHEIGHT, sides in multiples of 16, area up to 1,048,576 px. Sume uses 512/1K/2K/4K tiers and GPT Image 2.5 custom pixels.
Written by Sume