Seedance 2.0720pMultimodalText / Image / Reference

Seedance 2.0 — Next-Generation AI Video Model

Seedance 2.0 delivers cinematic AI video generation with 720p output, 4–15 second durations, and three input modes: text, image, and multimodal reference.

720p
Max Resolution
15s
Max Duration
6
Model Variants
<3s
Time to First Response

Overview

Seedance 2.0 is ByteDance's latest video generation model, delivering major improvements in visual quality, motion realism, and creative control. Through Seedance2API you get access to the complete Seedance 2.0 model matrix with competitive pricing and a developer-friendly interface.

Core Capabilities

Text-to-Video

Generate cinematic videos from natural language descriptions. Seedance 2.0 understands complex scenes, camera movement, and artistic styles. Optionally enable the web_search parameter to let the model autonomously look up fresh information for time-sensitive content.

Image-to-Video

Animate 1–2 static images: 1 image as a first-frame driver, or 2 images as first-last-frame transition. Ideal for e-commerce product showcases, social media content, and creative projects.

Multimodal Reference-to-Video

In a single request, combine up to 9 images + 3 videos + 3 audio clips as reference assets, and assign each asset a role using natural language in your prompt. This is the core differentiator versus Sora 2, Kling 3.0, and Veo 3.1.

The 6 Model Variants

Input typeStandard (stable quality)Fast (faster & cheaper)
Text onlyseedance-2.0-text-to-videoseedance-2.0-fast-text-to-video
1–2 imagesseedance-2.0-image-to-videoseedance-2.0-fast-image-to-video
Multimodalseedance-2.0-reference-to-videoseedance-2.0-fast-reference-to-video

See Models Overview for full details.

Supported Parameters

ParameterOptions
quality480p, 720p (default)
duration415 seconds, default 5
aspect_ratio16:9, 9:16, 1:1, 4:3, 3:4, 21:9, adaptive
generate_audiotrue (default) / false
InputsText prompt + optional image_urls / video_urls / audio_urls
model_params.web_searchText-to-video family only, default false

API Example

import requests

response = requests.post(
    "https://api.evolink.ai/v1/videos/generations",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "seedance-2.0-text-to-video",
        "prompt": "A cinematic aerial shot of a coastal city at sunset, golden hour lighting",
        "quality": "720p",
        "duration": 10,
        "aspect_ratio": "16:9"
    }
)

Pricing (Pre-Launch)

Final pricing will be announced when Seedance 2.0 fully launches. The figures below are pre-launch indicative rates billed per second. Refer to the pricing page for current rates.

QualityDurationApprox. per generation
480p5sfrom $0.02
480p10sfrom $0.04
720p5sfrom $0.03
720p10sfrom $0.05

Fast variants deliver lower per-second cost at the same quality and duration.

Start Building with Seedance 2.0

Get your free API key and generate your first video.