Skip to main content

ByteDance's Seedance 2.0 Fast edits footage you already have from one written instruction: send a 2–15 second clip as @Video1, say what should change, and get a 480p or 720p re-render in which the cast, their timing and the camera move stay as shot.

From $0.045/s

Workbench

Input

Video editing
Lead with the change, then list what must not move: faces, hands, props, the timing of each gesture and the camera path. The source clip is @Video1; extra stills are @Image1, @Image2 and sound files @Audio1, in upload order. Phrase it as an edit of @Video1, because Fast has no edit switch and takes its cue from your wording. at least 1 characters
affects price1/1

Drop a video here, or browse · 1 file · Max 90 MB · MP4

  • 1
1 / 1 files
MP4, 2 to 15 seconds, 24 to 60 fps, 50 MB at most. Every frame must hold 409,600 to 2,086,876 pixels with an aspect ratio between 0.4 and 2.5, so 360p footage and anything sharper than 1080p is turned away. Clips outside the 2–15 second window are refused before any charge. at least 1 characters
0/9

Drop files or media links, paste, or browse · Up to 9 files · Max 10 MB · JPG · PNG · WEBP · GIF

0 / 9 files
Optional: up to 9 stills that pin down the target look, such as a jacket, a prop, a face or a colour board. Point to each one in the prompt ("the jacket from @Image1"); stills add nothing to the price. at least 1 items · at most 9 items
0/3

Drop an audio file here, or browse · Up to 3 files · Max 90 MB · MP3 · WAV

0 / 3 files
Optional: up to 3 files of 2–15 seconds, 15 seconds combined, that steer the new soundtrack toward a voice or a mood. They only count while generate_audio is on and do not change the price. at least 1 items · at most 3 items
affects price
480p or 720p (default). The frame shape follows the source: a widescreen clip came back 864×496 at 480p in our tests, a square one 640×640. Your choice sets the per-second rate.
Generate audio
On by default: Fast writes a new soundtrack for the edited picture. Off: the edit is delivered silent, because the source's own audio is not kept; lay it back in during post if you need it.
Safety checkerOff

SpicyAPI does not run a safety checker on this model. Your prompt and media go to the model as written, and the model itself decides what comes back.

Checking your account before enabling submission and pricing.

Output

Ready for a new run

Related models and next tasks

Missing the model you need?

FAST VIDEO ITERATIONS

Text, image, reference and extend: 4 to 15 seconds, audio in the same pass.

Key numbers

Endpoints
4
text-to-video · image-to-video · reference-to-video · video-extend
Clip length
4–15S
duration_seconds takes whole seconds from 4 to 15, default 5, or -1 to let the model choose.
Resolution
720P
resolution takes 480p or 720p, the default. Draft at 480p, keep takes at 720p.
Reference stills
9
Up to 9 reference images in a single reference-to-video request.
Aspect ratios
7
adaptive by default, or a fixed 21:9, 16:9, 4:3, 1:1, 3:4 or 9:16.
Sound included
AUDIO
Fast starts with generate_audio enabled to create sound alongside the image; disabling it is useful for footage you will score separately, without promising a lower rate.

Before you spend

All modes

For Fast, use authorised source images, clips and sound with adult participants and consent; check likeness, music and publication rights before sharing the generated sequence.

Text to video

SpicyAPI adds no review to Fast requests, but earlier SpicyAPI tests recorded model-side refusals of some text prompts; the unrestricted label is not a promise that every adult NSFW request succeeds.

Image to video

Seedance 2.0 Fast image-to-video animates your approved opening image; an optional closing image gives the short sequence a visual destination.

Reference to video

Seedance 2.0 Fast reference-to-video assigns different jobs to your images, clips and audio, so product appearance and movement can come from separate sources.

What it does

One endpoint per input

Choose the Fast mode for your source material

A sentence goes to text-to-video. An approved first frame goes to image-to-video, which follows that frame far more literally than the same words typed as a prompt. A face, a garment or a room you need held steady goes to reference-to-video. Choosing by what you already own is what keeps a request from silently ignoring half its fields.

Adaptive by default

Let the source set the shape

aspect_ratio defaults to adaptive: image-to-video keeps the proportions of the opening frame and reference-to-video follows the primary reference, so a portrait still is not cropped into a landscape box. The six fixed ratios — 16:9, 9:16, 4:3, 3:4, 1:1 and 21:9 — are still there when a placement dictates the shape.

Casting from your own stills

Nine references, three clips, three tracks

reference-to-video reconciles up to 9 images, 3 video clips and 3 audio tracks in a single request. Three angles of one face hold a character far better than nine unrelated stills, so give each asset one job instead of asking all of them to carry identity, style and motion at once.

Where it fits

  • Vertical cuts for a social feed

    Seedance 2.0 Fast text-to-video turns a written shot into 4–15 seconds of footage; specify the camera movement and sound before spending another render on a revised idea.

  • Uncensored shorts, couples included

    SpicyAPI adds no review to Fast requests, but earlier SpicyAPI tests recorded model-side refusals of some text prompts; the unrestricted label is not a promise that every adult NSFW request succeeds.

  • Extend a shot from its last frame

    SpicyAPI’s Seedance 2.0 Fast video-extend uses the source clip’s last frame to generate a continuation and joins the two segments for delivery.

  • Draft at 480p, deliver at 720p

    Fast exposes 480p and 720p, with 720p selected initially; use the smaller frame for motion drafts and check fine detail again at the delivery size. Fast exposes an optional integer seed from 0 to 2147483647; keeping it fixed helps compare one edit at a time but cannot guarantee identical frames.

Made with Seedance 2.0 Fast

  • 5s
  • 5s
  • Seedance 2.0 Fast text-to-video, 5 seconds at 720p, 9:16, audio generated with the picture.
    5s
  • Seedance 2.0 Fast text-to-video, 5 seconds at 720p, 16:9. Deliberately overexposed: blown highlights, heat shimmer and almost no shadow to fall back on.
    5s
  • 5s
  • 5s
  • 5s
  • 5s
  • 5s
  • 4s
  • 10s
  • 12s
  • 6s
  • 5s
  • 11s

Model reference

Seedance 2.0 Fast API reference

Seedance 2.0 Fast API specifications

Endpoints
text-to-video, image-to-video, reference-to-video, video-extend
Clip length
4–15 whole seconds, default 5; -1 lets the model choose
Resolution
480p, 720p (default)
Aspect ratio
Fast generation offers adaptive plus 16:9, 9:16, 4:3, 3:4, 1:1 and 21:9; choose the publication format before comparing camera takes.
Audio
Fast starts with generate_audio enabled to create sound alongside the image; disabling it is useful for footage you will score separately, without promising a lower rate.
References
9 images, 3 videos, 3 audio tracks on reference-to-video
Repeatability
Optional seed to make takes comparable

How to call the Seedance 2.0 Fast API

  1. Prepare a Fast shot

    Seedance 2.0 Fast text-to-video turns a written shot into 4–15 seconds of footage; specify the camera movement and sound before spending another render on a revised idea. Seedance 2.0 Fast image-to-video animates your approved opening image; an optional closing image gives the short sequence a visual destination. Seedance 2.0 Fast reference-to-video assigns different jobs to your images, clips and audio, so product appearance and movement can come from separate sources.

  2. Estimate your Fast take

    For a Fast shot, describe the subject’s action, the camera path, lighting and intended sound; on image-to-video the opening image is required while this text is optional.

  3. Approve the Fast result

    Fast pricing follows the selected duration, resolution and audio setting; text-to-video web search and reference-video duration also require a fresh estimate where used. Save the task ID returned for your Fast render and check its status after a connection loss; reuse the same Idempotency-Key for that request within 24 hours.

The short version

Seedance 2.0 Fast is ByteDance’s accelerated video model for short production iterations: test motion at 480p, then assess a 720p take with synchronised sound. For Fast, duration_seconds accepts 4–15 whole seconds, defaults to 5, and accepts -1 for automatic length; the automatic estimate reserves 15 seconds before settlement uses delivered duration. Fast pricing follows the selected duration, resolution and audio setting; text-to-video web search and reference-video duration also require a fresh estimate where used. SpicyAPI adds no review to Fast requests, but earlier SpicyAPI tests recorded model-side refusals of some text prompts; the unrestricted label is not a promise that every adult NSFW request succeeds.

Seedance 2.0 Fast API questions