Directed motion
Describe camera movement, pacing and action in natural language for shots with a clear visual intention.
ByteDance AI Video
Create motion that feels alive with Seedance 2.5
Turn prompts, frames and reference media into expressive AI video. Build cinematic shots, social clips and product motion with flexible duration, adaptive framing and optional audio.
Image to Video
Seedance 2.5first_frame_url
Click to upload or drag and drop
last_frame_url (Optional)
Click to upload or drag and drop
Enter video description. Type @ to reference attached media (e.g. @Image1, @Video1, @Audio1).
Click or drop images here
Up to 30 images (JPG/PNG/WEBP), max 30MB eachClick or drop videos here
Up to 10 videos (MP4/MOV/MKV), max 200MB each, 30 seconds totalClick or drop audio here
Up to 10 files (MP3/WAV/AAC/OGG), max 15MB each, 30 seconds total. Audio requires at least one reference image or video.Estimated cost 600 gems
Your video will appear here
What is Seedance 2.5?
A flexible video creation model designed for motion, composition and cinematic direction. Start with a sentence, a frame, or a small set of references and shape the shot you want.
4–30sFlexible output duration
480p / 720pSpeed or quality
7 ratiosAdaptive and social-ready
AudioOptional generated sound
Why creators use Seedance 2.5
From a first visual idea to a finished clip, the workflow stays expressive and practical.
Frame continuity
Use first and last frames to guide transitions, poses and scene changes with stronger visual control.
Reference-aware creation
Bring in images, video and audio references when you need a consistent look, subject or atmosphere.
Longer creative range
Generate up to 30 seconds in one request for narrative beats, explainers and ad concepts.
Built for every format
Choose landscape, portrait, square, ultrawide or adaptive framing for the channel you publish on.
One simple studio
Prompt, configure, estimate cost and generate from one focused workspace with no extra setup.
How to create a video
Four steps from idea to downloadable result.
Write the direction
Explain the subject, action, camera and mood. Specific verbs and visual details lead to better results.
Add visual guidance
Upload a first frame, last frame or reference media. Choose one workflow based on the kind of control you need.
Set the shot
Select resolution, aspect ratio, duration, audio and output format. The studio updates your estimated cost.
Generate and refine
Start generation, review the result in the preview panel and iterate with a clearer prompt when needed.
Keep the constraints in mind
Frame workflows cannot be combined with reference media. Reference videos are limited to 30 seconds total.
Publish your best take
Use MP4 for broad compatibility or MOV when your downstream workflow calls for it.
Seedance 2.5 FAQ
Answers to common questions about inputs, settings and pricing.
What is Seedance 2.5?
Seedance 2.5 is ByteDance’s next-generation video model for creating motion-rich clips from text, first and last frames, and reference media.
What resolutions and durations are available?
Choose 480p or 720p and generate clips from 4 to 30 seconds. Adaptive aspect ratio is available when you want the model to follow your source media.
Can I generate audio?
Yes. Enable Generate audio to request synchronized sound. Audio uses a higher per-second rate.
Can I use reference videos?
Yes. You can attach up to 10 reference videos, with a combined duration of up to 30 seconds. Reference video duration is included in billing.
How does billing work?
Without video input, cost is the rate multiplied by output duration. With reference video input, cost is the rate multiplied by input duration plus output duration.
Are first and last frames compatible with reference media?
No. The first/last-frame workflow and reference-media workflow are mutually exclusive, following the provider API rules.
Ready to bring your next shot to life?
Start with a prompt or upload a frame and make a motion-rich clip in the Seedance 2.5 Studio.
Start creating with Seedance 2.5