HiAPI
seedance-2.0 详情页 Hero:右侧悬浮玻璃胶片带与棱镜分光镜头雕塑,暖奶油与冰蓝、珊瑚、薰衣草渐变,左侧柔光留白,发光立体字写出模型名。

ByteDance

Seedance 2.0

seedance-2.0

ByteDance's multimodal video generation model, supporting text-to-video, image-to-video, and reference-based video generation, and capable of producing multi-shot, cinematic short films with native synchronized audio

Route

Try seedance-2.0

Input

Output

video
Fill in the parameters and run — results show up here.

Pricing

seedance-2.0 per second

Specifications 480P 720P 1080P 4K
Without Reference Videos $0.136 $0.293 $0.729 $1.486
With Reference Videos $0.082 $0.179 $0.443 $0.915

Positioning Overview

Seedance 2.0 is a multimodal video generation model launched by ByteDance. It supports combined input of text, images, reference videos, and reference audio, and generates videos of 4–15 seconds with native audio at up to 4K in a single run. The model emphasizes multi-shot storytelling and character consistency, and first/last frames and reference materials can be used to constrain the visual direction. It is suitable for developers who need to quickly produce advertising clips, short social videos, and narrative previsualizations, and can be called through the unified HiAPI.ai interface with billing based on output seconds.

Core Highlights

  • Multimodal material-driven generation — Text, up to 9 reference images, 3 reference videos, and 3 reference audio clips can be mixed to constrain visual style, motion, and sound with real materials.
  • First and last frame control of shot start and end — Specify the first-frame and last-frame images so the generated video starts from a specified frame and ends on a specified frame, making it easy to connect shots and achieve precise transitions.
  • Native audio generated in sync — Audio synchronized with the visuals is generated by default, and reference audio can be layered in to guide timbre and rhythm, reducing post-production audio-visual alignment work.
  • Up to 4K and adaptive aspect ratio — Resolution ranges from 480p to 4k, aspect ratios support 1:1 to 21:9 and adaptive mode that follows the source image ratio, so one call can serve multi-platform delivery.

Capability Description

Three generation modes: Supports text-to-video, image-to-video, and reference-to-video. The same interface switches based on material combinations, making it easy to cover needs from concept to final cut within one workflow.

Multi-reference material constraints: Reference images, reference videos, and reference audio can be passed in simultaneously. Reference images plus first/last frames must not exceed 9 in total, and reference videos and audio must each not exceed 3 segments with total duration each not exceeding 15 seconds.

Duration and resolution control: Duration can be specified between 4–15 seconds, and resolution can be 480p, 720p, 1080p, or 4k. Billing is based on output seconds, making it easy to control costs according to delivery specifications.

Last-frame return: When return_last_frame is enabled, the last frame of the generated video is returned and can be used directly as the first-frame input for the next segment, chaining multiple generation segments together.

Web search enhancement: The web_search switch can enable web retrieval during generation to supplement the prompt with up-to-date information, which is suitable for creative content that depends on current events or news.

Use Cases

  • Advertising and brand teams: text scripts plus reference images — Quickly generate multi-shot brand clips and output 1080p or 4k videos with audio for social delivery and official website assets.
  • Narrative short-video creators: first/last frames plus character reference images — Lock shot start and end with first/last frames and maintain character consistency with reference images to produce coherent storyboard clips for short dramas or story-based content.
  • Creative previsualization: reference video plus reference audio — Use existing clips and voiceover to guide style and rhythm and generate dynamic preview videos for directors and clients to confirm direction before formal production.
  • Developer integration: batch video output billed by second — Submit generation tasks in batches through the unified HiAPI.ai interface, control budgets based on output seconds, and integrate into content production pipelines.

Limitations and Selection Advice

The maximum duration of a single generation is 15 seconds, so long videos need to be generated in segments and then spliced. The number of reference materials is limited: reference images plus first/last frames must not exceed 9 in total, reference videos and audio must each not exceed 3 segments with total duration each not exceeding 15 seconds, and complex projects need to be split. Last-frame return requires enabling the switch, and the last frame depends on the first frame being provided at the same time. If the requirement is ultra-long continuous shots or a traditional post-production workflow with frame-by-frame precise control, dedicated editing and compositing solutions should be evaluated; when longer final videos are needed, it is better to generate in segments and then edit.

  • New model seedance-2.0-fast video generation model now available
  • New model New model available: seedance-2.0-mini
  • Route change The seedance-2.0 ext route now exposes only its supported 72…

Frequently asked questions

View all FAQs →
  • What type of video model is Seedance 2.0?

    It is prompt-led and can also use endpoint frames or image, video, and audio references according to the active contract.

  • Which output settings does Seedance 2.0 support?

    4-15 seconds, 480p, 720p, 1080p, 4k, and 1:1, 4:3, 3:4, 16:9, 9:16, 21:9, adaptive.

  • Can it generate sound or use audio references?

    Optional image, video, and audio references; generated audio

  • How is Seedance 2.0 billed?

    Billing follows output duration and the live tier. Resolution, mode, or audio differences are reflected by the page price and task record.

Related Models

View all models →

Same Type