Unified Seedance 2.5 generation from text, start/end frames, multimodal references, or an input video, with native audio and 480p–4K output.
Added Aug 7, 2026
Starting Price
From $0.720 per video
Final price depends on the selected settings and is shown before generation.
Model Type
both
Settings
Generation controls available for this model.
Output Format
Default Duration
5
27 duration options
Aspect Ratio
Default
16:9
Options (6)
Ultra-wide (21:9), Landscape (16:9), Classic (4:3), Square (1:1) +2 more
Used for text and multimodal-reference generation; image and video inputs determine framing.
Duration
Default
5
Options (27)
4 seconds, 5 seconds, 6 seconds, 7 seconds +23 more
Output duration from 4 to 30 seconds
Generate Audio
Default
Yes
Generate synchronized sound effects, ambience, and speech.
Operation
Default
auto
Options (5)
Automatic (from inputs), Text / references to video, Image to video, Video edit +1 more
Automatically infer the operation from inputs, or explicitly select video extension.
Resolution
Default
720p
Options (4)
480p, 720p, 1080p, 4K
Output resolution
Benchmarks
Benchmarks
Human preference benchmarks sourced from LMArena.
Text to Video
#7 / 48
Arena Score
1473.9
Votes
8,001
Confidence Interval
1465.4 - 1482.5
Image to Video
#4 / 48
Arena Score
1477.4
Votes
15,729
Confidence Interval
1470.2 - 1484.6
Video Edit
#2 / 10
Arena Score
1409.8
Votes
429
Confidence Interval
1383.3 - 1436.2
Published 2026-09-22 · Matched as dreamina-seedance-2.5-720p
LMArena DatasetExamples
Loading examples…
Related video models
Compare Seedance 2.5 with similar models from the same provider or model family.
Seedance Upscaler
bytedance-seedance-upscalerEnhance existing videos with ByteDance’s Seedance super-resolution for cleaner 1080p, 2K, or 4K output with strong temporal consistency. Supports clips up to 10 minutes.
BytePlus Video Enhancement Pro
bytedance-video-enhancement-proApply stronger BytePlus video restoration and enhancement for footage with real people. Pro improves skin texture and fine detail while supporting upscaling to 2K or 4K, frame interpolation up to 120 FPS, denoising, deblocking, deblurring, sharpening, and color and contrast enhancement.
BytePlus Video Enhancement Standard
bytedance-video-enhancement-standardPost-process videos with BytePlus restoration and enhancement. Upscale to 2K or 4K, interpolate up to 120 FPS, repair noise, blocking, blur, scratches, and jitter, and improve color and contrast across AI video, UGC, short drama, and archival footage.
Avatar Omni Human 1.5
bytedance-avatar-omni-human-1.5Animate a portrait using ByteDance's cognitive avatar model. Upload a static image and an audio track for expressive lip-sync and emotion.
Seedance 2.5 Talking Avatar
bytedance/seedance-2.5/talking-avatarTurn a portrait and voice recording into an expressive talking-avatar video with natural lip sync, facial motion, and optional direction for gestures or presentation style. Supports up to 120 seconds at 480p or 720p.
Seedance 2.5 Spicy
bytedance/seedance-2.5-spicyUncensored Seedance 2.5 image-to-video generation with optional prompt, end frame, native audio, and 480p–4K output.