Motion study with audio
“A night market food stall at rush hour, wok flames flaring, steam rolling through lantern light, sizzling and crowd chatter, handheld camera easing past.”
video model
Generate long-form AI video with Seedance 2.5
Seedance 2.5 is ByteDance’s newest video model in Made, generating clips up to 30 seconds in a single pass with native audio at 480p to 1080p — the longest single-shot ceiling in the Made library.
$0.473 / second at provider cost for members — see the full price breakdown
What you need to start
Describe the shot, motion, and sound, or add a start image. An optional end frame can guide the final composition.
Loading...
Original results
Seedance 2.5 examples made in Made
These examples use media produced for Made. Prompts are included when the production record allows them.
Image-to-video
“The wheel spins up, clay rising under wet hands, water flicking, soft workshop ambience.”
Creative scene
“Storm waves break against a lighthouse, spray bursting over the rail, wind and surf roaring, slow aerial pull-back.”
Scene brief
“Set the scene as a still before describing motion and sound.”
Start-frame control
“Use this image as the opening composition.”
Composition brief
“Establish framing and mood, then hand the motion to the model.”
Where Seedance 2.5 fits best
Best uses
- Single-pass clips up to 30 seconds
- Scenes where synchronized ambient audio matters
- Animating a still with an optional end frame
- Sequences that would otherwise need stitching
Limits to know
- It is one of the more expensive per-second models in Made, so draft on a cheaper model and reserve 2.5 for keeper takes.
- Long clips multiply cost and generation time; a 30-second take costs six times a 5-second one.
Specifications in Made
These are the controls exposed by Made, which may be narrower than a provider’s full API.
- Aspect ratios
- auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16
- Resolution
- 480p, 720p, 1080p
- Duration
- 4–30 seconds
- Output formats
- MP4 with native audio
- Reference images
- 2
- Processing
- Longer durations and higher resolutions extend generation time; progress appears in the generation view.
How to use Seedance 2.5 in Made
- 1
Write the shot with sound
Describe subject motion, camera movement, and the ambient audio you want in the clip.
- 2
Anchor with images if needed
Add a start image — and optionally an end frame — when the composition is already decided.
- 3
Choose length deliberately
Pick a duration from 4 to 30 seconds; cost scales with every second, so use long takes for keepers.
- 4
Review picture and audio
Check continuity, motion, and the generated soundtrack before downloading.
Compare relevant models
video
WAN 3.0 Prime
WAN 3.0 Prime is the premium tier of Alibaba’s WAN 3.0 video family, generating clips from 2 to 30 seconds with synchronized audio at up to 1080p, including 30 fps image-to-video.
Explore model →video
MiniMax H3 Max
MiniMax H3 Max is a speed-focused, post-trained variant of the H3 video model, generating 5 to 15 second clips at 480P or 768P with strong prompt adherence — often in a few seconds.
Explore model →video
WAN 2.2 Turbo
WAN 2.2 Turbo is Made’s fast iteration option for short text-to-video and image-to-video clips, with portrait and landscape output controls.
Explore model →Continue with a related tool
AI Video Generator
Turn any image into a captivating video. Upload a photo, describe the motion you want, and watch AI bring it to life with realistic movement, cinematic camera work, and professional quality.
Open tool →AI Image Generator
Create scroll-stopping product photos and marketing visuals in seconds. Describe your shot, pick your style, and get professional images ready for your store, social feed, or ad campaign.
Open tool →It generates up to 30 seconds in a single pass with native synchronized audio — the longest single-shot ceiling currently available in Made.