Available on Runway
Seedance 2.5
Bring up to 50 references across text, image, video and audio and generate high-quality, multi-shot video up to 30 seconds.
State-of-the-art video generation
Length
Up to 30 seconds in one generation
Native 30-second output, with high-quality extension for longer clips. Room for a full ad or scene, not just a snippet.
Inputs
Up to 50 references
Combine up to 50 inputs — product shots, a style guide, a voiceover, clips — into one coherent video.
Editing
Localized editing
Prompt a change to an existing video and everything you didn't ask to change stays consistent with the original.
Direction
Complex shots in one pass
Multiple scenes, camera angles and pacing shifts come out of one generation, with no separate clips to stitch together.
From idea to finished video in minutes
01
Add your references
Bring up to 50 references across images, video clips and audio — a product photo, a color palette, a camera style, a voiceover. Whatever helps tell your story.
02
Describe what you want
Write a prompt, then choose your aspect ratio, resolution and duration, up to 30 seconds per video.
03
Generate and download
Generate, and your video comes back with visuals and sound, ready to download and share.
Create with Seedance 2.5
For marketers
Finished ads the same day
Go from idea to a finished ad without a shoot to book. Up to 30 seconds gives you room for a full spot: drop in product images, add a script and generate a version for every channel.
For filmmakers
From concept to finished footage
Take projects from early concepts to finished footage. Direct with reference clips, images and audio for consistent characters, intentional camera work and synchronized sound.
For creators
Content ready to post
Combine reference images, voice and a prompt to make polished, on-brand content that's ready to post.
Start creating with Seedance 2.5
Describe the video you want and Runway builds it, references and all.
Runway Dev
Build with the Seedance 2.5 API
Put Seedance 2.5 inside your own product with Runway Dev, alongside the best models from Runway and other labs. Generate video with optional audio from the text to video, image to video and video to video API endpoints.
Use the APIMore models on Runway
Runway gives you access to the world's leading video, image and audio models — Runway's own frontier models plus the best from Google, OpenAI, Kling, ByteDance and more — all in one workspace.
Wan 3.0
Alibaba video generation with native audio, 2 to 30 seconds, up to 1080p.
MiniMax H3
MiniMax's Hailuo 3: multimodal references, keyframes and 2K output.
Aleph 2.0
Runway's flagship in-context video editing model — change only what you ask for.
Kling 4.0
Kling's 30-second video model, with image and video references, keyframes and editing.
