30 seconds in one pass
Generate a continuous 30-second scene, with room for camera moves, dialogue, and a complete story beat.
Seedance 2.5 Direct the whole story.
Create text-to-video and image-to-video scenes with the Seedance 2.5 AI video generator. Guide the look, motion, and native audio with your references.
First frame
End frame
Seedance 2.5Three upgrades that matter for production video
Up to 50 multimodal references
Guide identity, style, sound, and motion with up to 50 images, videos, and audio references.
Localized region editing
Change a prop, outfit, or background without regenerating the whole shot.
How Seedance 2.5 delivers production-ready video
30 seconds in one generation
A diffusion process preserves frame-to-frame coherence, lighting continuity, and object persistence throughout a 30-second scene.
50 assets, one generation
Combine up to 50 multimodal references, including images, video, and audio, for consistent characters and on-brand product scenes.
Edit one region without starting over
Change only the selected area while keeping the timing, camera movement, and the rest of the scene.
Build a cinematic scene in one pass
Stack your references
Upload character sheets, style boards, Seedream image concepts, or 3D white models to set the look.
Generate the 30-second arc
Describe the subject, action, camera move, and timing for the full scene.
Redraw the details
Select a detail to change while keeping the approved footage intact.
Everything the creative journey needs
High-quality video continuation
Extend a shot while preserving its pacing, visual style, and continuity.
Synced audio and lip-sync
Generate synced audio, multilingual lip-sync, subtitles, and background music alongside the video.
Why Seedance 2.5 is built for real production
| Production pressure | The Seedance 2.5 advantage | Concrete outcome |
|---|---|---|
| Disjointed, short clips | Native 30-second generation | A complete, flowing scene without stitching |
| Character morphing | Up to 50 multimodal references | Flawless brand and character consistency |
| Starting over for small fixes | Localized region editing | Fix a prop or background while keeping the shot |
| Silent, flat visuals | Synced native audio | Dialogue and sound effects built right in |
- Best for
- Filmmakers, creative directors, and marketers who need multi-shot storytelling, strict brand consistency, and footage that can hold a full idea rather than only a quick visual test.
- Best first test
- Upload 10 reference images of a specific character, then write a prompt with the subject, light, camera action, frame ratio, and intended sequence length. Generate a 30-second scene to see temporal consistency hold.
- Not ideal for
- Quick, low-res 3-second clips where consistency does not matter.
Built for what production actually needs
References hold the shot
Guide composition, lighting, and motion with green-screen clips, reference images, and footage.
30 seconds stays on track
Keep character identity, lighting, and camera motion coherent across a longer take.
50 inputs stay useful
Combine images, video, audio, and style references to give each scene clear direction.
Cleanup gets lighter
Synced speech, music, and on-screen text reduce cleanup before editing.
Finally, a workflow that respects your time
| Review angle | What the user notices | Why it matters |
|---|---|---|
| Scene continuity | Lighting and character face never drift | No more throwing away 90% of your generations |
| Reference power | Upload 20 product photos at once | The model understands the exact shape of your product |
| Workflow relief | No stitching required in post-production | A usable 30-second sequence straight out of the prompt |
What's new versus Seedance 2.0
| Dimension | Seedance 2.0 | Seedance 2.5 |
|---|---|---|
| Native duration | 4-15 seconds natively; longer clips require extension or stitching. | 30-second standard generation, with longer-video modes on the roadmap. |
| Audio | Audio generation is supported in the current 2.0 family. | Synced audio generation built in. |
| Reference inputs | Up to 9 images, 3 videos, and 3 audio clips in Omni Reference. | Up to 50 multimodal references, including 3D white-model conditioning. |
| Editing | Whole-clip generation and extension workflows. | Targeted region editing, without regenerating the whole clip. |
| Availability | Available on YouArt today for hands-on workflow testing. | Available on YouArt today. |
Final specs are listed on the Seedance 2.5 model page.
Seedance 2.5 across industries
Digital advertising
Create campaign variations around the same product, brand style, and framing.
Entertainment & streaming
Create cinematic scenes at up to 4K resolution for films, trailers, and streaming content.
Retail & social commerce
Turn product photos into 30-second lifestyle videos for Instagram Reels and TikTok, with consistent colors, materials, and packaging.
Corporate communications
Create training and company videos with a consistent virtual presenter.
Who Seedance 2.5 is built for
Commercial directors
Plan camera moves, pacing, and lighting before the production shoot.
E-commerce teams
Use product photos to keep shapes and colors consistent across lifestyle scenes.
Narrative filmmakers
Create atmospheric B-roll with dialogue and ambient sound built in.
Social creators
Create complete vertical videos for TikTok and YouTube Shorts in one pass.
Pick Your Plan
Get access to Seedance 2.5 and all premium AI models with one membership.
Basic
For hobbyists and explorers
$9.99/mo
Select Plan- 1000 credits
- Up to ~200 images/month
- Up to ~332s video/month
- Intelligent creative agent
- Video editor
- Latest image models, including GPT Image 2.5, GPT Image 2 and Nano Banana Pro
- Latest video models, including Seedance 2
- Realistic face uploads
- Voice generation with ElevenLabs
- No watermark
- Unlimited template access
Pro
Most PopularFor creators and pro users
$29.99/mo
Select Plan- 3300 credits
- Up to ~1000 images/month
- Up to ~1100s video/month
- Intelligent creative agent
- Video editor
- Latest image models, including GPT Image 2.5, GPT Image 2 and Nano Banana Pro
- Latest video models, including Seedance 2
- Realistic face uploads
- Voice generation with ElevenLabs
- No watermark
- Unlimited template access
Max
For power users and teams
$149.99/mo
Select Plan- 18000 credits
- Up to ~6000 images/month
- Up to ~6000s video/month
- Intelligent creative agent
- Video editor
- Latest image models, including GPT Image 2.5, GPT Image 2 and Nano Banana Pro
- Latest video models, including Seedance 2
- Realistic face uploads
- Voice generation with ElevenLabs
- No watermark
- Unlimited template access
Team
For teams and studios
$329.99/mo
Select Plan- 36300 credits
- Up to ~12000 images/month
- Up to ~12100s video/month
- Realistic face uploads
- Share canvas, workflows, and assets with your team
- Up to 10 members per team
- Up to 5 teams
- Role-based management
- Team credit management and spending caps
- Per-member usage tracking
Seedance 2.5 questions
Seedance 2.5 is ByteDance's next-generation AI video model, designed to generate native 30-second clips at up to 4K resolution. It significantly improves upon previous versions by supporting up to 50 multimodal references, ensuring multi-shot storytelling with consistent characters and synced audio.
Seedance 2.5 questions
What is Seedance 2.5?
Seedance 2.5 is ByteDance's next-generation AI video model, designed to generate native 30-second clips at up to 4K resolution. It significantly improves upon previous versions by supporting up to 50 multimodal references, ensuring multi-shot storytelling with consistent characters and synced audio.
How does Seedance 2.5 compare to the previous version?
The primary differences are duration and control. While earlier models topped out around 15 seconds natively, the 2.5 release offers 30-second standard generation. It also upgrades the reference limit from 12 inputs to 50 and introduces localized region editing so you do not have to regenerate an entire clip to fix one detail.
Does Seedance 2.5 support 4K resolution?
Yes, the model supports high-definition output up to 4K resolution. This makes the generated videos suitable for broadcast production, digital signage, and high-end streaming content where visual fidelity is critical.
How do the 50 multimodal references work?
You can combine up to 50 different assets in a single generation prompt — a mix of images, video clips, audio files, Seedream concepts, and 3D white-model inputs. The model interprets these references together to coordinate characters, products, motion examples, visual style, light, and scene ratio accurately.
What is localized region editing in Seedance 2.5?
Localized region editing allows you to make targeted changes to a specific part of a generated video. Instead of rewriting the prompt and generating an entirely new clip, you select an element — like a piece of clothing or a background object — and have the model redraw just that area while preserving the rest of the shot.
How much does using Seedance 2.5 cost?
Pricing is based on a credit system within the platform. Credit costs for Seedance 2.5 are shown on its model page, and you can compare plans on the plans and pricing page.
Can I generate audio alongside the video?
Yes, the model features synced native audio generation, including dialogue, ambient sound effects, and background music in the same pass as the video. This significantly reduces the time spent on manual audio alignment in post-production.