All models
Seedance 2.0 · by ByteDance
Seedance 2.0 AI Video Generator
Seedance 2.0 is ByteDance's proven all-rounder and OpenGradient's default video model: top-tier motion and coherence, native synced audio and dialogue, clips up to 15 seconds, and every aspect ratio from 21:9 cinema to 9:16 vertical. Its successor, Seedance 2.5, sits one click away in the same picker. Generate with either online on OpenGradient — no app, no API keys, free to start.
Free credits to start · no card · lands with Seedance 2.0 preselected
Real clips generated on OpenGradient
Capabilities
What you can make with Seedance 2.0
One prompt in, a finished clip out — picture and soundtrack generated together, up to 15 seconds at a time.
Multi-shot cinematic scenes
Direct subject, camera, lighting and pacing in a single prompt — timestamped shot lists included. Seedance holds characters and environments coherent across cuts.
Audio born with the video
Dialogue with natural lip-sync, ambience and effects are generated alongside the frames — no separate sound pass, no silent drafts.
Every frame that matters
Six aspect ratios from 21:9 widescreen to 9:16 vertical, with durations from 5 to 15 seconds — among the longest single clips of any video model.
First & last frame control
In image-to-video mode, pin the first and last frame to chain clips seamlessly, or feed reference images for character consistency across shots.
Seedance 2.0 at a glance
Modes
Text to video + Image to video
Clip length
5s – 15s
Aspect ratios
16:9 · 9:16 · 1:1 · 4:3 · 3:4 · 21:9
Audio
Synced audio & dialogue
Moderation
Provider-filtered
Variants
6 live on OpenGradient
The Seedance lineup, live on OpenGradient
Where it fits
How people use Seedance 2.0
The safest first pick for almost any brief — and the model OpenGradient's AI video director reaches for by default.
Social-first clips
Vertical 9:16 hooks for TikTok, Reels and Shorts with sound baked in — no separate audio edit before posting.
Dialogue scenes
Characters that actually speak: monologues, voice memos and two-line exchanges with believable lip-sync.
Product launches
Hero shots, feature demos and transformation reveals in 16:9 or 21:9 for landing pages and campaigns.
Explainers & B-roll
Cutaways, animated concepts and supporting footage for courses, onboarding and founder updates.
More AI video models on OpenGradient
Questions, answered
Frequently asked
- What is Seedance 2.0?
- Seedance 2.0 is ByteDance's Seedance video model, and OpenGradient's default. It turns text prompts or images into clips with synced audio — dialogue, ambience and effects generated together with the picture. Seedance 2.5, the newer generation, is in the same picker when you need longer clips.
- What can I create with it?
- Cinematic multi-shot scenes, talking characters, product films, social clips and B-roll. It supports six aspect ratios (21:9, 16:9, 4:3, 1:1, 3:4, 9:16) and durations from 5 to 15 seconds per clip; the Movie Editor sequences clips into longer films.
- How do I use Seedance 2.0 on OpenGradient?
- Open OpenGradient's Video Studio from the button on this page — it lands with Seedance 2.0 preselected. Type a prompt (or upload an image in image-to-video mode), pick an aspect ratio and duration, and generate. The studio is visible without an account; generating takes a free sign-up.
- What is Seedance 2.0 Mini?
- A smaller Seedance variant at roughly half the price, with the same aspect ratios, durations and synced audio. It's in the same model picker — use it for drafts and volume work, then re-render keepers on the flagship.
- Seedance 2.0 or Seedance 2.5?
- Seedance 2.5 is the newer generation: clips up to 30 seconds instead of 15, prompts up to 10,000 characters, and up to 30 reference images in image-to-video. Seedance 2.0 stays the studio default and the cheaper render for clips of 15 seconds or less. Both are one click apart in the picker.
- What does a clip cost?
- Per-clip prices depend on the model and duration and are shown before you generate. 1,000 credits = $1; packs start at $10; you get free credits to start — no card needed.
- How does Seedance 2.0 compare to Veo, Kling and Wan?
- Seedance is the best all-rounder and OpenGradient's default video model. Veo 3.1 pushes realism and resolution further, Kling v3 Pro specializes in motion fidelity, and the Wan line runs unrestricted. All of them share one model picker here, so you can audition the same prompt across models for cents — including against Seedance 2.5.
Make your first Seedance clip
Free to start, no card, no API keys. Type a prompt and hear your first clip in minutes.