Which Seedance 2.0 Fast scenes are available on Kyeo AI?

Seedance 2.0 Fast / Generation scene — Text accepts only a prompt; frames requires a first frame and can add a last frame; reference requires a prompt plus at least one image, video, or audio reference. The three scenes are mutually exclusive.

How much media can multimodal reference mode accept?

Seedance 2.0 Fast / Upload limit / Runtime — Up to nine images, three video clips, and three audio files. Each video or audio file must be 2–15 seconds; all reference video may total at most 15 seconds, and all reference audio has its own 15-second aggregate limit. Images must be 300–6000 pixels on each side with a 0.4–2.5 aspect ratio; reference videos must also be 300–6000 pixels on each side, have 409600–927408 pixels total, and run at 24–60 fps.

AI video model

ByteDance

Seedance

Seedance 2.0 Fast

Q: Is Fast guaranteed to be faster than standard Seedance 2.0?

Seedance 2.0 Fast / Runtime / Prompt length — Compare matched requests and record queueing, runtime, failures, and retries instead of treating the name as a guarantee.

Q: Can I publish or commercialize the generated video automatically?

Seedance 2.0 Fast / NSFW check / Runtime — No. Review people, voices, text, products, trademarks, copyright, likeness rights, and advertising claims. Uploading image, video, or audio references—or enabling web search—does not grant rights or publication clearance.

Seedance 2.0 Fast / Capabilities — Text accepts no media; frames requires a first frame and allows a last frame; reference requires a prompt and at least one image, video, or audio reference. Reference media cannot be sent with endpoint-frame fields. 480p/720p · 4–15 · 47–450 credits per request.

Capabilities

Text, endpoint frames, multimodal reference

Credit cost

47–450 credits per request

Prompt length

3–20,000 characters

Upload limit

9 reference images / 3 videos / 3 audio files

Seedance 2.0 Fast / Three mutually exclusive input scenes — Text accepts no media; frames requires a first frame and allows a last frame; reference requires a prompt and at least one image, video, or audio reference. Reference media cannot be sent with endpoint-frame fields.

Seedance 2.0 Fast / Upload limit — Kyeo AI allows JPG/JPEG/PNG/WebP/GIF/BMP/TIFF images up to 30 MB, videos up to 50 MB, and audio up to 15 MB. Reference mode accepts 9 images, 3 videos, and 3 audio files, with separate 15-second aggregate limits for video and audio. Images must be 300–6000 pixels on each side with a 0.4–2.5 ratio; reference videos must be 300–6000 pixels on each side, have 409600–927408 pixels total, and run at 24–60 fps. Upload metadata is verified again before generation.

Seedance 2.0 Fast / Resolution — 480p/720p · 4–15 seconds · 47–450 credits per request

Use this model View credit pricing Back to Model Hub

30-second overview

Seedance

47–450 credits per request

What it does best

Seedance 2.0 Fast / Runtime — Text accepts no media; frames requires a first frame and allows a last frame; reference requires a prompt and at least one image, video, or audio reference. Reference media cannot be sent with endpoint-frame fields.

Best for

Seedance 2.0 Fast — Use it for controlled tests of a written shot, an endpoint transition, or a multimodal-reference brief. People, products, advertising, and social content still need matched samples and manual review.

At a glance

What is this model like?

Runtime — Text accepts no media; frames requires a first frame and allows a last frame; reference requires a prompt and at least one image, video, or audio reference. Reference media cannot be sent with endpoint-frame fields.

What it does best

Best for

Why use it on Kyeo AI

Seedance 2.0 Fast / Credit cost — 480p: 11.7 credits × output seconds, or 6.8 credits × (output + reference-video seconds). 720p: 24.8 credits × output seconds, or 15 credits × (output + reference-video seconds). Totals round up; the current request range is 47–450 credits.

Key facts

Quickly assess whether this model fits your use case.

Also known as

The same model may appear under different names across documentation and community discussions; this list keeps them easy to search and compare.

Seedance 2.0 Fast

Seedance 2 Fast

ByteDance Seedance 2.0 Fast

Common questions

These practical questions focus on the task, input conditions, and result requirements you should confirm before choosing.

Seedance 2.0 Fast reference media limits

Seedance text frames reference scenes

how to use Seedance endpoint frames

Seedance 2.0 Fast reference-video billing

Seedance 2.0 Fast supported duration

Seedance 2.0 Fast generated audio

Selection guide

Use these decision points when choosing a model.

Choose the scene from the available input / Seedance 2.0 Fast

Choose the scene from the available input / Seedance 2.0 Fast — Use text when there is no media, frames for a required first frame and optional last frame, or reference for image, video, or audio guidance. The paths are mutually exclusive, so confirm the available media before creating the task.

Start with the smallest valid request / Seedance 2.0 Fast

Start with the smallest valid request / Seedance 2.0 Fast — Begin at 480p and 4 seconds in one scene. In reference mode, start with one media type and confirm the input, audio, returned last frame, and result. Then add media or duration one item at a time and recalculate the credits.

Count, format, size, and duration rules for media / Seedance 2.0 Fast

Count, format, size, and duration rules for media / Seedance 2.0 Fast — Kyeo AI allows JPG/JPEG/PNG/WebP/GIF/BMP/TIFF images up to 30 MB, videos up to 50 MB, and audio up to 15 MB. Reference mode accepts 9 images, 3 videos, and 3 audio files, with separate 15-second aggregate limits for video and audio. Images must be 300–6000 pixels on each side with a 0.4–2.5 ratio; reference videos must be 300–6000 pixels on each side, have 409600–927408 pixels total, and run at 24–60 fps. Upload metadata is verified again before generation.

Popular comparisons

Compare common alternatives on the same task to clarify differences in inputs, controls, and cost.

Model comparison

Compare the current model with alternatives at a glance.

Kyeo AI input scene

Seedance 2.0 Fast

Kyeo AI input scene — Text / first or first-and-last frames / multimodal reference

Seedance 2.0

Seedance 2.0 — Text / first or first-and-last frames / multimodal reference

Seedance 1.5 Pro

Text and image input with up to two images

Current billing formula

Seedance 2.0 Fast

Current billing formula — 480p: 11.7 credits × output seconds, or 6.8 credits × (output + reference-video seconds). 720p: 24.8 credits × output seconds, or 15 credits × (output + reference-video seconds). Totals round up; the current request range is 47–450 credits.

Seedance 2.0

No video: 19/41/102/208 per second; video: 11.5/25/62/128 × total seconds

Seedance 1.5 Pro

Current billing formula — Seedance 1.5 Pro: A currently available alternative in the same category; open its detail page to compare capabilities and pricing.

Reference-media limits

Seedance 2.0 Fast

Reference-media limits — 9 images, 3 videos, 3 audio files; 15-second video/audio totals

Seedance 2.0

Seedance 2.0 — 9 images, 3 videos, 3 audio files; 15-second video/audio totals

Seedance 1.5 Pro

Up to two images

Duration and resolution

Seedance 2.0 Fast

Duration and resolution — 480p / 720p, 4–15 seconds

Seedance 2.0

480p/720p/1080p/4K, 4–15 seconds

Seedance 1.5 Pro

480p/720p/1080p, 4/8/12 seconds

Practical usage insights

Practical guidance based on public sources, current on-site limits, and representative tasks.

Eight controls and dynamic credit calculation / Seedance 2.0 Fast

Eight controls and dynamic credit calculation / Seedance 2.0 Fast — 480p: 11.7 credits × output seconds, or 6.8 credits × (output + reference-video seconds). 720p: 24.8 credits × output seconds, or 15 credits × (output + reference-video seconds). Totals round up; the current request range is 47–450 credits.

A higher rate is not a quality guarantee / Seedance 2.0 Fast

A higher rate is not a quality guarantee / Seedance 2.0 Fast — Every standard rate is above the corresponding Fast rate, but a higher price does not guarantee better image quality, instruction following, stability, or success rate.

Capabilities

Three mutually exclusive input scenes

Three mutually exclusive input scenes — Text accepts no media; frames requires a first frame and allows a last frame; reference requires a prompt and at least one image, video, or audio reference. Reference media cannot be sent with endpoint-frame fields.

Eight controls and dynamic credit calculation

Eight controls and dynamic credit calculation — Kyeo AI sends resolution, seven ratios including `adaptive`, 4–15-second duration, generated audio, returned last frame, web search, and an NSFW check, then selects one of two rate formulas. Kyeo currently exposes 480p and 720p.

Count, format, size, and duration rules for media

Count, format, size, and duration rules for media — Kyeo AI allows JPG/JPEG/PNG/WebP/GIF/BMP/TIFF images up to 30 MB, videos up to 50 MB, and audio up to 15 MB. Reference mode accepts 9 images, 3 videos, and 3 audio files, with separate 15-second aggregate limits for video and audio. Images must be 300–6000 pixels on each side with a 0.4–2.5 ratio; reference videos must be 300–6000 pixels on each side, have 409600–927408 pixels total, and run at 24–60 fps. Upload metadata is verified again before generation.

Use cases

A text-only shot sample

Submit only a prompt in the text scene, keep ratio, resolution, and duration fixed, and review the shot, movement, audio, and any rendered text against the brief.

A first-frame or endpoint-frame transition

The frames scene requires a first frame and can add a last frame. It anchors endpoints, but intermediate people, objects, text, and motion still require frame-by-frame review.

A matched multimodal comparison

Assign a role to each image, video, or audio file in reference mode, then run the same input through Fast. Reference media does not guarantee consistent results.

Prompt tips

Write observable camera and action requirements

Describe framing, camera movement, subject action, environmental change, dialogue, and sound in sequence. Replace labels such as 'cinematic' or 'perfectly stable' with reviewable conditions.

Assign a specific role to every reference

State which image supplies subject or composition, which clip supplies motion or camera behavior, and which audio file supplies timing.

Change one variable at a time

Complete a 480p, 4-second request first, then change resolution, duration, media, or model version separately. Recalculate credits on every request so the source of a difference remains visible.

Why choose it

Capabilities — Three explicit scene modes cover text, first or first-and-last frames, and multimodal references.

Resolution — Kyeo AI offers 480p/720p and every integer duration from 4 through 15 seconds.

Upload limit — The page checks reference counts and the total duration of video and audio inputs.

Credit cost — The current media combination can be priced before task creation.

What to know first

Seedance 2.0 Fast / NSFW check — The NSFW check defaults off; whether enabled or not, it does not replace manual content, rights, and publication review.

Seedance 2.0 Fast / Runtime — Compare matched requests and record queueing, runtime, failures, and retries instead of treating the name as a guarantee.

Seedance 2.0 Fast / Category — No. Review people, voices, text, products, trademarks, copyright, likeness rights, and advertising claims. Uploading image, video, or audio references—or enabling web search—does not grant rights or publication clearance.

Adjustable parameters

Quickly assess whether this model fits your use case.

Generation scene

seedance_scene

Optional

Parameter type: select

Default: text

Text-to-video

First frame / first and last frame

Multimodal reference

Resolution

resolution

Optional

Parameter type: select

Default: 720p

480p

720p

Aspect ratio

aspect_ratio

Optional

Parameter type: select

Default: 1:1

1:1

4:3

3:4

16:9

9:16

21:9

Adaptive

7 options

Duration

duration

Optional

Parameter type: number

Default: 5

4–15 seconds

Generate audio

generate_audio

Optional

Parameter type: select

Default: true

Off

Return last frame

return_last_frame

Optional

Parameter type: select

Default: false

Off

Web search

web_search

Optional

Parameter type: select

Default: false

Off

NSFW check

nsfw_checker

Optional

Parameter type: select

Default: false

Off

Credit usage

47–450 credits per request

480p: 11.7 credits × output seconds, or 6.8 credits × (output + reference-video seconds). 720p: 24.8 credits × output seconds, or 15 credits × (output + reference-video seconds). Totals round up; the current request range is 47–450 credits.

Budget tip

Before batch generation, run an A/B test with the same assets across the current model and alternatives to validate quality and avoid wasting credits.

FAQ

Related models

Compare these similar candidates before deciding.

Seedance 1.5 Pro

Seedance 1.5 Pro / Capabilities — Seedance 1.5 Pro on Kyeo AI accepts text alone or up to two images and exposes 480p/720p/1080p, 4–12 seconds, generated audio, six ratios, and a fixed-lens switch. The 7–180-credit cost follows the selected combination; the Pro name and higher credit cost do not prove image quality, stability, or publication readiness.

AI video model

7–180 credits per request

View details Use now

Seedance 2.0

Seedance 2.0 / Capabilities — Text accepts no media; frames requires a first frame and allows a last frame; reference requires a prompt and at least one image, video, or audio reference. Reference media cannot be sent with endpoint-frame fields. Seedance 2.0 supports three mutually exclusive text, frame, and multimodal-reference scenes. The current callable output set is 720p, 1080p, and 4K for 4–15 seconds; video-reference requests are available only at 1080p or 4K because those are the current priced combinations. 164–3,840 credits per request

AI video model

164–3,840 credits per request

View details Use now

Kling 2.6

Kling 2.6 is a two-workflow video service on Kyeo: text requests use text-to-video, while requests with an image use single-image animation. Both routes offer 5/10 seconds and a `sound` toggle; text generation also provides three aspect ratios. The four Kyeo credit tiers are 55, 110, 110, and 220.

AI video model

55-220 credits / request

View details Use now

Sources

Content is based on model documentation, feature references, and the settings available on Kyeo AI.

Source note

Seedance 2.0 Fast — ByteDance documents text, image, video, and audio inputs, up to 9 images, 3 videos, 3 audio files, and 15-second output for Seedance 2.0.

Last updated: 2026-08-26

ByteDance Seed: Seedance 2.0 Official Launch

Official

ByteDance documents text, image, video, and audio inputs, up to 9 images, 3 videos, 3 audio files, and 15-second output for Seedance 2.0.

View source