Generate up to 30 seconds of native 4K video with up to 50 multimodal references in a single run. Currently, in preview — join the waitlist for early access.
Examples
Explore a few of the scenarios Seedance 2.5 is built for — from cinematic product reveals to multi-character shorts and synthetic data for AI research.
Seedance 2.5 is an AI video generator built for creators and production teams. Write a prompt, attach up to 50 multimodal references, and get a native 4K video with synchronized audio, all from a single generation.
It is designed for real production work: advertising, e-commerce, short-form storytelling, and synthetic data for embodied AI and autonomous driving.
From a single prompt to a finished 4K clip, skip the storyboarding, shooting, and stitching, and turn your idea into a polished video in one generation.
Overview
Seedance 2.5 is the newest release in the Seedance family of video generators and the successor to Seedance 2.0. It is a unified multimodal model that accepts text, image, audio, and video as input, and produces native video with synchronized audio in a single generation pass.
Compared with Seedance 2.0, Seedance 2.5 brings longer single-shot duration, larger reference capacity, higher resolution, and tighter prompt control.
Features
Seedance 2.5 generates up to 30 seconds of video in a single run, doubling the 15-second limit of Seedance 2.0. Longer native clips reduce the need to stitch multiple short segments, producing more coherent motion and narrative flow.
A single generation can include up to 50 reference assets, any mix of images, videos, and audio. This is the largest reference capacity in its class. Provide a cast of characters, products, or style references and let the model orchestrate them into a single scene.
Generations can be produced at up to 3840 × 2160 natively, without an external upscaling step. Output is suitable for direct use in advertising, e-commerce, and short-form content pipelines.
Subjects, actions, layout, and stylistic instructions are followed approximately 20% more reliably than in Seedance 2.0. Better adherence reduces the number of regenerations needed to land on a usable result.
Combine text prompts with image, video, and audio references in a single generation. Output videos include a native audio track synchronized with the visuals.
Compare
| Capability | Seedance 2.0 | Seedance 2.5 |
|---|---|---|
| Max single-shot duration | 15 s | 30 s |
| Max resolution | up to 4K | 4K native |
| Multimodal references | ~12 | up to 50 |
| Prompt adherence | baseline | ~20% improvement |
| Native synchronized audio | Yes | Yes |
| Input modalities | text / image / video / audio | text / image / video / audio |
| Pricing | published | pending official release |
Seedance 2.0
15 s
Seedance 2.5
30 s
Seedance 2.0
up to 4K
Seedance 2.5
4K native
Seedance 2.0
~12
Seedance 2.5
up to 50
Seedance 2.0
baseline
Seedance 2.5
~20% improvement
Seedance 2.0
Yes
Seedance 2.5
Yes
Seedance 2.0
text / image / video / audio
Seedance 2.5
text / image / video / audio
Seedance 2.0
published
Seedance 2.5
pending official release
Input formats: Text (UTF-8, Chinese & English) · Image (JPEG, PNG, WebP) · Video (MP4, MOV) · Audio (WAV, MP3).
Output format: MP4 (H.264 / H.265), AAC synchronized audio, up to 30 s, up to 3840 × 2160.
Workflow
Write a prompt in Chinese or English. Be specific about subject, action, camera movement, lighting, and mood for best results.
Upload up to 50 reference assets. Use images for subject identity and style, video clips for motion or composition cues, and audio for music or voice guidance.
Choose a clip length up to 30 seconds and a resolution up to 4K. Pick an aspect ratio that matches your delivery channel (16:9, 9:16, 1:1).
Start the generation, wait for it to finish, then download the final MP4 with synchronized audio, ready to publish or drop into your editor.
Pricing
Seedance 2.5 has not yet been officially released, and pricing has not been published. Pricing is expected to follow per-second conventions consistent with Seedance 2.0, and this page will be updated once the official rates are announced. In the meantime, you can join the waitlist below to be notified when pricing goes live.
FAQ
For hobbyists and beginners starting with Seedance.
Billed annually, shown as a monthly rate
$0.025 / credit
Plan benefits
Best for
For most creators who need steady AI video output.
Billed annually, shown as a monthly rate
$0.025 / credit
Plan benefits
Best for
For heavy creators who need faster production capacity.
Billed annually, shown as a monthly rate
$0.017 / credit
Plan benefits
Best for
For ultra-high usage with expandable production volume.
Billed annually, shown as a monthly rate
$0.015 / credit
Plan benefits
Best for