Seedance 2.0 resolution in pixels: 480p, 720p and 1080p by ratio
Seedance 2.0 720p at 16:9 is 1280×720 and 1080p is 1920×1080. The full pixel table for six aspect ratios, as fal lists it and Sume prices it, with no 4K.
At 16:9, Seedance 2.0 at 720p is 1280×720 pixels and at 1080p is 1920×1080; at 9:16 they are 720×1280 and 1080×1920. fal's Seedance 2.0 page lists the 480p and 720p sizes for six aspect ratios, and Sume's price estimate uses the same 480p and 720p sizes plus a 1080p column. Neither lists 4K.
The Sume sizes below come from the pricing code and are the frame sizes it uses to count tokens; the Video generation docs list seedance-2 at 480p, 720p and 1080p.
What are the pixel sizes at each resolution and ratio?
Each cell is width × height. Send resolution and aspect_ratio and Sume prices the clip at the size in the table.
| Aspect ratio | 480p | 720p | 1080p |
|---|---|---|---|
21:9 | 992×432 | 1470×630 | 2205×945 |
16:9 | 864×496 | 1280×720 | 1920×1080 |
4:3 | 752×560 | 1112×834 | 1668×1251 |
1:1 | 640×640 | 960×960 | 1440×1440 |
3:4 | 560×752 | 834×1112 | 1251×1668 |
9:16 | 496×864 | 720×1280 | 1080×1920 |
Does Seedance 2.0 make 4K video?
Not on Sume. The seedance-2 descriptor advertises 480p, 720p and 1080p, and a request for 4K is refused with 400 unsupported_capability. On fal's reference-to-video page the standard endpoint's maximum resolution is 1080p. fal's price line also names a 4k token rate, but its resolution options stop at 1080p, so treat 1080p as the top size.
How do these sizes turn into tokens?
Sume counts (width * height * duration_seconds * 24_fps) / 1024 video tokens and multiplies by the model's rate per 1,000 tokens. One second of 720p at 16:9 is 21,600 tokens. A 1080p 16:9 second has 2.25 times as many pixels as a 720p one, so it counts 2.25 times the tokens. fal states the same formula on its Seedance 2.0 pages.
Which resolution should I request?
Pick the smallest size that fits the placement, because the frame size sets the token count and so the reserve. Draft at 480p or 720p while you settle the prompt, and move to 1080p on seedance-2 for the final render. The docs name 1080p for seedance-2 and do not name it for the Fast or Mini ids, so read supported_resolutions for the id you call. fal's page says its Fast tier tops out at 720p.
curl -X POST https://api.sume.com/v1/videos \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2",
"prompt": "A red kayak on a still alpine lake at sunrise",
"duration": 5,
"resolution": "1080p",
"aspect_ratio": "9:16"
}'Are these the exact dimensions of the file I get back?
The docs do not publish output file dimensions for Sume. Treat the table as the size Sume prices and fal lists, and read the width and height from your finished file before you build a layout around it. If your player or editor needs an exact frame size, add a resize step after download rather than assuming the table.
Sources
Related posts
More in Models
- Seedance 2.5 aspect ratios: 9:16 vertical, 21:9 and the rest
Seedance 2.5 on Sume accepts 21:9, 16:9, 4:3, 1:1, 3:4 and 9:16. Set aspect_ratio explicitly; 3:2 is rejected. Ratios, errors and the price effect.
- Seedance 2.5 audio reference: how to send an audio clip
Seedance 2.5 accepts an audio clip as a reference, even without an image or video. The audio_url request on Sume, the vendor's file limits and what to expect.
- Seedance 2.5 image to video: first frame and last frame
Send a first_frame, or a first_frame and last_frame, with seedance-2.5 on Sume. Rules for frame_images, how it differs from input_references and what to set.
- Seedance 2.5 omni reference: how @image, @video and @audio tags work
Seedance 2.5 prompts point at references with tags such as @Image 1. Sume rewrites lowercase tags like @image1 to the casing the model expects. Examples.
Written by Sume