01
Text to Video
Direct a complete sequence from a written scene, action, camera, and sound brief.
Now available on LinkModel
Seedance 2.5
Thirty seconds. One continuous story. Sound included.
ByteDance's multimodal video model turns text, images, video, and audio references into controlled 4–30 second sequences with native sound.
Seedance 2.5 showcase
Seedance 2.5
30-second narrative canvas
0s
10s
20s
30s
30 sec
Maximum standard duration
480p / 720p
Verified standard output
30 + 10 + 10
Image, video, and audio references
A/V
Native picture and sound
Price comparison
Run Seedance 2.5 for less on LinkModel
Save 5% vs ByteDance official pricing—and up to 45.7% vs other providers. All prices below are for a 5-second generation.
| Generation spec | ByteDanceOfficial reference | AtlasCloudProvider | WaveSpeedProvider | LinkModelOur price |
|---|---|---|---|---|
| 480p16:9 | $0.514Official baseline | $0.67030.4% more | $0.9075.1% more | $0.48835.0% less |
| 720p16:9 | $1.156Official baseline | $1.502830.0% more | $1.8055.7% more | $1.09825.0% less |
AtlasCloud: 480p normalized to 5 seconds; 720p calculated at 1.3× ByteDance official. WaveSpeed: published 5-second list prices. Taxes and volume discounts excluded.
Creation modes
Three ways to create
The inputs you can use are determined by the task types exposed on the available LinkModel endpoint. The page only opens a workflow the live catalog supports.
02
Image to Video
Animate a visual starting point while preserving its subject and art direction.
03
Reference to Video
Guide identity, movement, style, and sound with multimodal references.
Endpoint dependent
Timeline proof
Thirty seconds, directed beat by beat
Treat a generation like an edit: establish context, develop movement, stage the turn, and land the final frame.
Direction canvas / 00:30
A/V synchronized
One continuous scene, with each change assigned a moment.
0s
Establish
Introduce the subject, environment, and opening camera language.
10s
Develop
Advance motion and story without resetting the visual context.
20s
Transform
Use timestamp direction to stage a controlled change or reveal.
30s
Resolve
Land the sequence with a deliberate final beat instead of an abrupt cut.
Production controls
More room to direct, fewer resets
Compose references, sound, events, and continuity as parts of one production brief.
Reference stack
Multimodal reference control
Use up to 30 images, 10 videos, and 10 audio clips to shape subject, style, motion, and sound.
Audio direction
Audio-driven creation
Let audio participate in the creative direction, including workflows driven by audio alone.
Timed beats
Timestamp direction
Place actions and changes at explicit moments across a longer sequence.
Continuity
Longer narrative continuity
Build a complete 4–30 second story unit with more room for setup, development, and resolution.
Use cases
Create campaign films, character stories, and more
Apply the longer timeline to creative work that needs setup, movement, and resolution in one generation.
Campaign films
Turn a creative brief and brand references into a complete short-form narrative.
Character stories
Use repeated visual and audio references to guide identity across a longer scene.
Music-led visuals
Build motion and scene changes around an audio reference or track.
Product narratives
Stage a product reveal with timed actions, camera direction, and environmental sound.
API quickstart
One API, an asynchronous workflow
Submit a generation request, poll the task until it completes, then retrieve the generated video from the result. The same LinkModel video API keeps that lifecycle consistent across supported models.
Quickstart
Make your first request
curl -X POST https://api.linkmodel.ai/api/v1/video-generation \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2-5",
"prompt": "A continuous cinematic sequence with synchronized ambient audio"
}'Model family
Explore the Seedance family
Seedance 2.5 is the primary destination. Other family versions remain visible as catalog context, with actions shown only when that exact model is available.
Featured model
seedance-2-5
The primary Seedance workflow for longer multimodal sequences with native picture and sound.
- 30 sec
- Maximum standard duration
- 480p / 720p
- Verified standard output
- 30 + 10 + 10
- Image, video, and audio references
- A/V
- Native picture and sound
Seedance family
Family catalog
seedance-2-0
Availabletext-to-videoimage-to-video
FAQ
Frequently asked questions
Is Seedance 2.5 available through LinkModel?
The page shows Try and API links only when Seedance 2.5 is present in the live LinkModel catalog. Catalog availability may vary by deployment.
How long and at what resolution can Seedance 2.5 generate?
The verified standard workflow supports 4–30 second output at 480p or 720p. Higher-resolution claims belong to specific third-party endpoints and are not presented here as a general model specification.
What reference material can Seedance 2.5 use?
The official guide documents up to 30 image references, 10 video references, and 10 audio references, including creation driven by audio alone.
Can I call Seedance 2.5 through an API?
When the model is available in LinkModel's catalog, use the existing asynchronous video-generation API and the model identifier shown on its model detail page.
Seedance on LinkModel
Run your next Seedance 2.5 generation for less.
Start with LinkModel's available endpoint and pay 5% below ByteDance official pricing.
Live catalog endpoint