Seedance 2 Fast sits between Seedance 2 Mini and Seedance 2.0. It takes text, a still image or an existing clip, bills per second, and charges noticeably less when you give it video to work from.
A written description, a still image, or a clip you already have.
Transforming existing motion costs about 40% less per second than inventing it.
Generated with Seedance 2 Fast on this site on 2026-08-04, five seconds at 480p, unretouched. One clip rather than three: video bills per second, and a single honest example beats three described ones.
Seedance 2 Fast is the middle tier of ByteDance's Seedance 2 family, above Seedance 2 Mini and below Seedance 2.0. Like the rest of the family it accepts three kinds of input — text, a still image, or an existing video clip to work from — and it caps at 720p where the top tier reaches 1080p and beyond.
The pricing detail that shapes how people actually use it is the video-input discount: supplying a source clip costs materially less per second than asking the model to invent motion from nothing, because transforming motion that already exists is less work than creating it. That makes Fast the natural tier for restyling and extending footage you already have, as opposed to conjuring a scene.
When you are generating from scratch, it is the tier to reach for once Mini has told you the prompt works and before Seedance 2.0's 1080p is worth paying for.
Creative engine
Per second, by resolution, and by whether you supplied a source video.
Above Mini, below Seedance 2.0, and capped at 720p.
About 40% cheaper per second than generating motion from a still or from text.
Length is the main lever on cost, so a short test is a cheap test.
Two situations, and they are different from each other. The first is working from footage: if you have a clip and want it restyled, extended or given a different look, this is the cheapest sensible place to do it, because the video-input rate is the lowest in the family that still reaches 720p. The second is the middle of a from-scratch workflow — you have found the prompt on Mini, the motion works, and you want a better version without paying Seedance 2.0's 1080p rate for a frame nobody will view at 1080p. Skip it entirely in two cases: when you are still guessing, where Mini is cheaper for the same information, and when the clip is the final deliverable and the resolution shows, where 2.0 is the answer.
The video-input rate makes this the cheapest 720p-capable tier for transforming clips.
Once Mini has proven the prompt, Fast is the version worth keeping.
Enough for social video, where 720p is the delivery resolution anyway.
What this tier covers, and where the tier above it picks up.
Generate a clip from a written description with no source material.
Start from a still and describe the motion you want added to it.
Work from a clip you supply, at a materially lower per-second rate.
Two resolutions, with 1080p and above on Seedance 2.0.
Taken from the KIE (kie.ai) spec for this model, which is the API it runs on here.
Four steps, and the first one is where the cost is decided.
It is the cheapest input mode on this tier and it removes most of the guesswork about motion.
Stated actions and camera moves survive a render; adjectives largely do not.
Resolution has no bearing on whether the motion works, and it roughly halves the rate.
Video output varies run to run, so budget for two attempts rather than one perfect prompt.
Jobs where 720p is enough and the input is often footage rather than an idea.
Change the look of a clip you already have, at the lower video-input rate.
Short vertical clips delivered at 720p, where the extra tier buys nothing visible.
The keeper after Mini has confirmed the prompt does what you meant.
A photo given a camera move and a little life, without paying the top rate.
One credit pool covers Nano Banana images and Seedance and Veo video. The cost shows before every run, and failed jobs are not charged. Use a subscription for ongoing work, or a one-time pack when you just need to top up.
What's included
Secure checkout by Stripe. Card details never touch our servers.
What's included
Secure checkout by Stripe. Card details never touch our servers.
What's included
Secure checkout by Stripe. Card details never touch our servers.
What's included
Secure checkout by Stripe. Card details never touch our servers.
One-time top-ups — buy extra credits any time you run low.
What's included
Secure checkout by Stripe. Card details never touch our servers.
What's included
Secure checkout by Stripe. Card details never touch our servers.
What's included
Secure checkout by Stripe. Card details never touch our servers.
Charges appear as “KAVEL AI” on your card statement. You can cancel any time from Settings → Billing; cancellation takes effect at the end of the period you already paid for.
Powered by
Use one balance across every supported image and video model — ten of them today, listed below — and check the credit cost before each request.
Video models
Image models
Model credit guide
You're only charged for successful generations. The exact estimate in the generator varies by model, length, resolution, audio, and number of images.
| Type | Model | Credit cost |
|---|---|---|
| Video | Seedance 2.0 | 5s 720p image-to-video ≈ 188 credits; text-to-video ≈ 308 credits. Scales with resolution and length. |
| Video | Seedance 2 Fast | Faster and lower cost. 5s 720p text-to-video ≈ 248 credits. |
| Video | Seedance 2 Mini | The cheapest Seedance tier. 5s 720p ≈ 154 credits, 5s 480p ≈ 72 credits. |
| Video | Seedance 1.5 Pro | Audio doubles the rate. 5s 720p ≈ 27 credits silent, ≈ 53 with audio; 1080p ≈ 57 and ≈ 113. |
| Video | Veo 3.1 | Billed per video, not per second (Lite tier). About 45 credits at 720p and 53 at 1080p. |
| Video | Kling 3.0 | Audio raises the rate. 5s 720p ≈ 105 credits silent, ≈ 150 with audio; 1080p ≈ 135 and ≈ 203. |
| Video | MiniMax H3 | Fixed 2K, no resolution ladder. Priced per second — a 5s clip ≈ 158 credits. |
| Image | Nano Banana 2 | Generate or edit from text and images. About 8 credits per 1K image, 12 at 2K, 18 at 4K. |
| Image | Nano Banana Pro | Consistent run times across generations. About 12 credits per 1K or 2K image, 21 at 4K. |
| Image | Nano Banana 2 Lite | Faster, simpler variant. A flat 8 credits per image at every resolution. Start here to test. |
| Image | GPT Image 2 | The lowest-cost image model here. About 3 credits per 1K image, 6 at 2K, 12 at 4K. |
| Image | Seedream 5.0 Lite | Flat pricing — about 8 credits per image whether you generate or edit. |
Common questions about the middle tier of the Seedance 2 family.
Fast caps at 720p where Seedance 2.0 reaches 1080p and above, and costs substantially less per second. Both take text, image or video input.
Mini is the cheaper tier below it, also capped at 720p. Fast is the version to run once Mini has told you the prompt and the motion work.
Transforming motion that already exists is less work than generating it from nothing, and the per-second rate reflects that — about 40% less on this tier.
About 117 credits for 5 seconds at 480p generated without a source clip, about 68 with one. At 720p it is roughly 248 and 150.
No — 480p and 720p only. Seedance 2.0 is the tier that reaches 1080p.
Credits are returned automatically, unless the request broke the content policy.
Supply a clip if you have one, describe the action, and start at 480p.
Two resolutions, with 1080p available a tier up on Seedance 2.0.
