Seedance 2.0 Fast

Video

Faster & cheaper · 480p/720p native

What Is Seedance 2.0 Fast API?

Overview

Seedance 2.0 Fast (sd2-fast) is ByteDance Seed's faster and more cost-efficient version of Seedance 2.0. It retains the core multimodal video generation capabilities of Seedance 2.0 while prioritizing generation speed and lower cost.

Available workflows:

Text to Video
Image to Video
First-Last Frame to Video
Multi-Reference to Video

Key Capabilities

Faster, lower-cost generation: Optimized for faster generation and lower credit usage than Seedance 2.0 Pro.
15-second video generation: Generate synchronized audio-video content up to 15 seconds.
Multimodal references: Support up to 9 images, 3 videos, and 3 audio files.
Native 480p / 720p output: Higher resolutions are automatically upscaled on SeeGen AI.
Video editing and extension: Edit or continue existing videos using reference-based workflows.
Synchronized audio: Generate speech, sound effects, and background music alongside the video.

Inputs

Seedance 2.0 Fast supports image, video, and audio references for multimodal video generation.

Modality	Limit	Formats	Constraints
Images	Up to 9	JPEG, PNG, WebP, GIF, BMP, TIFF, HEIC	Max 30 MB each; shortest side ≥ 400 px
Videos	Up to 3	MP4, MOV	Max 50 MB each; each video 2–15s; total duration ≤ 15s
Audio	Up to 3	MP3, WAV	Max 15 MB each; each file 2–15s; total duration ≤ 15s

Note: Total reference assets across all modalities must not exceed 12. Audio cannot be used as the only reference; at least one image or video is required.

Parameters

Parameter	Type	Default	Options / Description
prompt	string	—	Text description of the video. Max 20,000 characters.
urls	string[]	—	Reference images. Supports HTTP URLs and asset:// references. Up to 9 images in reference mode.
videoUrls	string[]	—	Reference video asset:// URIs. Up to 3 videos; external video URLs are not supported.
audioUrls	string[]	—	Reference audio inputs. Up to 3 audio files; audio cannot be used alone and requires at least one image or video.
videoInputMode	string	"keyframe"	"keyframe" for image / first-last frame generation; "reference" for multimodal reference generation.
mode	string	—	Omit for standard reference generation; use "edit" for video editing or "extend" for video continuation.
duration	string	"5s"	Output duration from "4s" to "15s".
resolution	string	"auto"	Aspect ratio: auto, 720x720, 720x960, 960x720, 1280x720, 720x1280, 1280x540.
outputResolution	string	"720p"	480p, 720p, 1080p, 2k, 4k. Fast is native at 480p/720p; higher tiers are automatically upscaled.
generateAudio	boolean	true	Generate synchronized speech, sound effects, and background music. Set false for silent video.
bitrateMode	string	"standard"	"standard" or "high". High bitrate preserves more detail at a larger file size; pricing is unchanged.
seed	integer	-1	-1 or omit for a random seed; 0–2147483647 for a fixed seed.

Seedance 2.0 Fast API Pricing

Seedance 2.0 Fast uses pay-as-you-go credit pricing. The rates below are calculated based on the $500 API Pack (125,000 credits, $0.004/credit).

Condition	Rate	10-sec clip
SD2-Fast 480p, no video input	16 credits/sec (~$0.064/sec)	~160 credits (~$0.64)
SD2-Fast 480p, with video input	12 credits/sec (~$0.048/sec)	Based on output + reference video duration
SD2-Fast 720p, no video input	32 credits/sec (~$0.128/sec)	~320 credits (~$1.28)
SD2-Fast 720p, with video input	24 credits/sec (~$0.096/sec)	Based on output + reference video duration
SD2-Fast 1080p (upscaled), no video input	52 credits/sec (~$0.208/sec)	~520 credits (~$2.08)
SD2-Fast 2K (upscaled), no video input	62 credits/sec (~$0.248/sec)	~620 credits (~$2.48)
SD2-Fast 4K (upscaled), no video input	72 credits/sec (~$0.288/sec)	~720 credits (~$2.88)

For 1080p, 2K, and 4K output, SeeGen AI automatically upscales the generated video. Upscaling adds 20 / 30 / 40 credits per output second, respectively.

Credit Calculation

1. No video input

credits = out × rate

2. With video input

credits = (out + in) × rate

out = output_seconds. in = the sum of ⌈duration⌉ for each input video. Each duration is rounded up, with a minimum input duration of ceil(out × 2 / 3). For upscaled output, add the upscale cost based on output duration.

3. Upscaled output (added on output duration)

1080p: + out × 20
2K:    + out × 30
4K:    + out × 40

Run Seedance 2.0 Fast API

Generate a video in two steps: create a generation task, then query the result using the returned taskId.

Asset Requirements

If your generation uses reference images, videos, or audio files, upload them as assets first and wait until their status becomes ACTIVE. Then use the returned asset:// URIs in your request.

Images → urls
Videos → videoUrls
Audio → audioUrls

All reference assets must be reviewed and ACTIVE before use.

View Asset Upload Guide →

Create a Task

curl -X POST https://seegen.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $SEEGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sd2-fast",
    "inputs": {
      "prompt": "An anime warrior monk with glowing golden tattoos and a giant staff fights colossal stone guardians inside a collapsing mountain temple. With fluid martial arts, explosive shockwaves, and cinematic action shots, he battles through falling debris and shattered pillars before ending the fight with a godlike final strike.",
      "duration": "5s",
      "resolution": "auto",
      "outputResolution": "720p",
      "bitrateMode": "standard",
      "generateAudio": true,
      "seed": -1
    }
  }'

Query the Result

Use the returned taskId to check the task status. When the status becomes COMPLETED, the generated video is available in output[0].url.

curl \
  -H "Authorization: Bearer $SEEGEN_API_KEY" \
  "https://seegen.ai/api/v1/jobs/queryTask?taskId=YOUR_TASK_ID"

A completed task returns status: "COMPLETED" and the generated video URL in output[0].url.

Seedance 2.0 Fast API Use Cases

Seedance 2.0 Fast is optimized for faster, lower-cost video generation, making it suitable for high-volume content creation and rapid iteration.

Use Case	Fast Generation	Multimodal References	Video Editing	Native Audio
Social Media Content	Quickly generate short-form videos for TikTok, Reels, Shorts, and X	Keep characters, products, and styles consistent across posts	Modify scenes, products, or visual details	Generate dialogue, music, and sound effects
Advertising & E-commerce	Produce multiple ad variations and product videos faster	Maintain brand identity, products, models, and visual style	Replace SKUs, labels, backgrounds, or product details	Add voiceovers, music, and product sounds
Creative Prototyping	Test prompts, camera ideas, and concepts before higher-cost production	Compare different characters, scenes, and reference combinations	Quickly refine or extend generated concepts	Test audio-visual ideas in early production stages
Content Automation	Generate video content at scale for automated workflows	Reuse consistent assets across multiple generations	Update recurring content without rebuilding from scratch	Generate synchronized audio automatically
Games & Virtual Content	Rapidly create character clips, environments, and promotional content	Combine virtual characters, environments, and motion references	Modify character appearance, style, and scene details	Generate dialogue, music, and game-style SFX

Seedance 2.0 Fast is especially useful for workflows where generation speed and lower credit usage are more important than native high-resolution output.

Seedance 2.0 Fast vs Seedance 2.0 Mini

Seedance 2.0 Fast is designed for faster, cost-efficient generation, while Seedance 2.0 Mini is the lowest-cost Seedance 2.0 option.

Feature	Seedance 2.0 Fast	Seedance 2.0 Mini
Model ID	sd2-fast	sd2-mini
Maximum duration	Up to 15 seconds	Up to 15 seconds
Reference inputs	Up to 9 images + 3 videos + 3 audio	Up to 9 images + 3 videos + 3 audio
Native resolution	480p, 720p	480p, 720p
Higher resolutions	1080p, 2K, 4K upscaled	1080p, 2K, 4K upscaled
480p, no video input	16 credits/sec	10 credits/sec
720p, no video input	32 credits/sec	20 credits/sec
480p, with video input	12 × (out + in)	7.5 × (out + in)
720p, with video input	24 × (out + in)	15 × (out + in)
Best for	Faster generation and frequent iteration	Lowest-cost, high-volume generation

Choose Seedance 2.0 Fast when generation speed and lower cost than Pro are both important. Choose Seedance 2.0 Mini when minimizing credit usage is the priority.

FAQs about Seedance 2.0 Fast API

How long can Seedance 2.0 Fast videos be?

Seedance 2.0 Fast supports video generation from 4 to 15 seconds.

What reference inputs does Seedance 2.0 Fast support?

It supports up to 9 images, 3 videos, and 3 audio files, with a maximum of 12 reference assets per generation.

Why is the total reference limit 12 instead of 15?

The per-modality limits are not additive. You can use up to 9 images, 3 videos, and 3 audio files, but the combined total must not exceed 12 reference assets.

Can audio be used as the only reference?

No. Audio-only reference is not supported. At least one image or video reference is required.

What resolutions does Seedance 2.0 Fast support?

Seedance 2.0 Fast generates natively at 480p and 720p. SeeGen AI also supports 1080p, 2K, and 4K through automatic upscaling.

How much does Seedance 2.0 Fast API cost?

Without video input, the base rate is 16 credits/sec at 480p and 32 credits/sec at 720p. With video input, the base rates are 12 and 24 credits/sec respectively.

What is the difference between Seedance 2.0 Fast and Mini?

Seedance 2.0 Fast is optimized for faster generation, while Seedance 2.0 Mini is the lowest-cost Seedance 2.0 option. Both generate natively at 480p and 720p.