Seedance 2.0 AI Video Generator

Create social clips, product shots, and storyboards from text or multimodal references—up to 9 images, 3 videos, and 3 audio clips—with Seedance 2.0, synchronized native audio, and selectable 480p–4K output.

From 6 credits
480p–4K video + audio
Text + image to video
ByteDance · Seedance 2.0 docs ↗

Seedance 2.0 Video Examples

Official Seedance 2.0 demonstration of a continuous pizza-shop cinematic push-in

Cinematic pizza shop take

Prompt

Single continuous cinematic shot, no music. From outside the glass window, the dim camera slowly pushes inward into a pizza shop. A bearded white male employee is baking pizza. He removes the pizza from the oven with a metal tray, places it into a red takeaway box, closes the lid, then hands it to a customer with a warm smile. Final shot: over-the-shoulder perspective.

Key Features of Seedance 2.0

Grounded motion, multimodal references, directed briefs, and multi-shot native audio—each with a matching demo. Prefill from any row; nothing runs until you generate.

Motion & physics

Complex motion that stays grounded. Weight, momentum, multi-subject action, and camera paths that hold together—so hero shots and storyboards stay coherent under pressure.

Seedance 2.0 demonstration of complex gymnastics motion with stable physics

How to Use Seedance 2.0

1
1. Start from text or references
Write a text brief, add one owned image, or use Multi Reference (up to 9 images, 3 videos, and 3 audio clips). Prefill from an Example or Key Feature if you want—nothing runs until you generate.
Write a text brief, add one owned image, or use Multi Reference (up to 9 images, 3 videos, and 3 audio clips). Prefill from an Example or Key Feature if you want—nothing runs until you generate.
2
2. Write the scene, sound, and settings
Describe action, camera, and sound in plain language. Tag each file with @ImageN, @VideoN, or @AudioN when you upload references, then set duration, ratio, and resolution.
Describe action, camera, and sound in plain language. Tag each file with @ImageN, @VideoN, or @AudioN when you upload references, then set duration, ratio, and resolution.
3
3. Generate and review
Confirm the credit estimate, generate, then check motion and synced audio before downloading or refining the brief.
Confirm the credit estimate, generate, then check motion and synced audio before downloading or refining the brief.

Create with Seedance 2.0 ↑

Seedance 2.0 Pricing

From 26 credits per video (from $0.43) on the published route. Every run uses credits, with the exact quote shown before submission.

Compare Seedance 2.0How Seedance 2.0 compares to other models

Seedance 2.0

This model

4–15s cinematic clips with selectable 720p–4K

4–15s26–1260 credits

Seedance 2.5 →ByteDance

4–30s one-takes, packs up to 50 files, and clay-render blocking

4–30s38–1320 credits

MiniMax H3 →MiniMax

Multimodal reference, first/last frames, and instruction-led edits

4–15s12–128 credits

Attribute	This modelSeedance 2.0	ByteDanceSeedance 2.5 →	MiniMaxMiniMax H3 →	KuaishouKling 3.0 →
Best for	4–15s cinematic clips with selectable 720p–4K	4–30s one-takes, packs up to 50 files, and clay-render blocking	Multimodal reference, first/last frames, and instruction-led edits	5/10/15s cinematic shots from text or an owned frame
Inputs	Text · Up to 9 images · 3 videos · 3 audio	Text · Up to 30 images · 10 videos · 10 audio	Text · First/last frame · Up to 9 images · 3 videos · 3 audio	Text · Image + end frame
Output	480p–4K video + audio	480p–1080p video + audio	768p–2K video + audio	720p–4K video + audio
Duration	4–15s	4–30s	4–15s	5–15s
Native audio	Yes	Yes	Yes	Yes
Credits	26–1260 credits	38–1320 credits	12–128 credits	39–385 credits

Seedance 2.0 FAQs

What is Seedance 2.0?

Seedance 2.0 is ByteDance’s video model for cinematic clips from text or owned multimodal references—images, videos, and audio. On MixVio, the reviewed public routes return one private video with synchronized native audio. Seedance 2.5 is the longer 4–30 second family route with a larger reference pack and 480p–1080p output.

What inputs and file limits does Seedance 2.0 support?

Use Text to Video for a scene brief, Image to Video for one owned start frame (optional end frame on supported routes), or Multi Reference for owned packs: up to 9 images (≤30 MB each), 3 videos (MP4/MOV, ≤200 MB each), and 3 audio clips (MP3/WAV, ≤15 MB each)—up to 12 files total. Still images need 300–6,000 px on each side and a 2:5–5:2 crop; oversized photos are fitted automatically. Reference videos need 300–6,000 px per side, a 2:5–5:2 aspect ratio, 409,600–8,295,044 total pixels, and 24–60 FPS. Each video or audio clip must be 2–15 seconds. All reference videos combined may total 15 seconds; all reference audio combined may total 15 seconds. Audio references require at least one image or video. End frame is unavailable with multi packs or video/audio refs.

How do I tag references with @ImageN, @VideoN, and @AudioN?

After you upload files, mention each one by index in the prompt—@Image1, @Video1, @Audio1, and so on—and say what it should do. Example: “Use @Image1 as the first frame. Match the fight timing in @Video1. Follow the beat of @Audio1.” Vague lines like “use the references” often mix roles. Numbering follows upload order in the generator.

Can I edit or extend an existing video with Seedance 2.0?

You can upload an owned clip in Multi Reference, tag it with @VideoN, and describe restaging, motion transfer, or what should happen next in the prompt. MixVio still returns one new private 4–15 second video per run. There is no separate public extend tool, in-place timeline editor, or dual-direction length control on the current Seedance routes.

Does Seedance 2.0 generate native audio?

Yes. Public Seedance 2.0 routes return video with synchronized native audio. Describe dialogue, ambience, sound effects, or music in the brief, then review the mix, speech, and lip sync before publishing.

Which ratios, resolutions, and durations are supported?

Text and image routes support Auto, 21:9, 16:9, 4:3, 1:1, 3:4, and 9:16. Each run produces one 4–15 second clip. Mini and Fast offer 480p or 720p; Standard adds 1080p and 4K, including multimodal packs. First-frame image-to-video can set aspect ratio on 2.0 routes. The generator shows the exact compatible choices for the selected route.

How do I keep character or product consistency?

Upload clear owned references of the subject, tag them with @ImageN (and @VideoN when motion must match), and name the same identity, wardrobe, and product details in the prompt. Seedance 2.0 is strong at holding look and motion across a short clip, but fine details can still drift—especially on long action or many scene changes. Review faces, logos, and labels before publishing.

How many credits does Seedance 2.0 use?

Seedance 2.0 is available on the Free plan when your balance covers the quote. This page defaults to Standard and reserves from 6 credits. Typical anchors: 6 credits for 4 seconds at 480p on Mini, 70 for 5 seconds at 720p on Standard, 168 for 5 seconds at 1080p on Standard, 140 for 10 seconds at 720p on Standard, and 1,020 for 15 seconds at 4K on Standard. The generator shows the exact reservation before submission. Failed runs cost no credits.

Is Seedance 2.0 free?

It is available on the Free plan, but generation is not zero-credit. The exact quote depends on duration and resolution, and failed runs cost no credits. Free delivery limits still apply.

How does Seedance 2.0 compare with Seedance 2.0 Fast and Mini?

Seedance 2.0 Standard is the full-quality family route with selectable 480p, 720p, 1080p, or 4K output from 26 credits. Seedance 2.0 Fast is the lower-latency 480p/720p draft tier from 16 credits, and Seedance 2.0 Mini is the lower-cost 480p/720p route from 6 credits. All three support 4–15 second durations. This page defaults to Standard; switch Mini or Fast in the generator when the cut needs a lower-cost or lower-latency draft.

How does Seedance 2.0 compare with Seedance 2.5, MiniMax H3, and Kling 3.0?

Stay on Seedance 2.0 for 4–15 second cinematic clips with native audio, multimodal packs, and selectable 480p–4K. Seedance 2.5 is the longer 4–30 second family route with a larger reference pack and 480p–1080p—MixVio does not publish 4K on 2.5. MiniMax H3 targets instruction-led edits at 768p or 2K. Kling 3.0 Standard offers 5/10/15 second cinematic shots. Compare live credits, inputs, duration, and audio in the comparison table before generating.

Can I use Seedance 2.0 videos commercially?

Paid-plan outputs may be used commercially, subject to the Terms of Service and current ByteDance terms. You must have rights to every prompt, reference, likeness, brand asset, voice, and sound direction. Prompts and references pass MixVio moderation and Provider safety checks; some requests may be rejected. Review identity, logos, dialogue, lip sync, and audio before publishing. MixVio does not guarantee exclusivity or trademark clearance.

Can I use real faces or celebrity likenesses?

Only use faces, voices, and likenesses you own or are authorized to use. Public figures, deceptive impersonation, deepfake-style face swaps, minors, and other prohibited content can be blocked by MixVio moderation or Provider safety checks. When a request is allowed, still review identity and consent before any commercial or public use.

Start your Seedance 2.0 scene.
Private. Credits shown first.

Start from text or an owned image, then generate with Seedance 2.0 selected.