seedance 2.0 更新 info (从文生视频开放招募处了解) - 4.5B, 双流 DiT (dual-stream DiT) - 多镜头叙事能力、多主体同镜头特写 - 模型可生成 2K 视频（也支持 1080P / 720P） - 可输入 12 个参考文件（含文本/图像/音频/视频等模态）
10:32 AM Feb 7, 2026
Seedance 2.0 by ByteDance
SeeDance 2.0 - Revolutionary AI Video Generator with Native Multi-Shot Storytelling & 2K Cinema Quality
ByteDance's revolutionary 4.5B parameter Dual-Branch Diffusion Transformer for native multi-shot video storytelling. Generate cinematic 2K videos with simultaneous audio-visual generation, support for up to 12 multimodal reference files, and phoneme-level lip-sync in 8+ languages.
4.5B
Parameters
Dual-stream DiT
2K
Resolution
2048×1080
12
References
Multimodal files
8+
Lip-Sync
Languages
Seedance 1.5 Pro Text-to-Video
Lite Unified Batch
Pro
Preview renders here
Prompt
A neon-lit street chase through a futuristic megacity, cinematic lighting, dynamic camera cuts, high energy.
Duration
12s
Output
2K / 24fps
Seedance 2.0 Popular Reviews on X
See what creators and researchers are saying about Seedance-2 on X (Twitter).
seedance 2.0：具有惊人强大多镜头叙事能力、可生成 2K 视频、支持输入 12 个参考文件、支持音画同步生成、支持生成 8 种语言的配音口型同步。
5:38 AM Feb 7, 2026
Update on #Seedance2, the latest AI video generation model from #ByteDance: - 4.5B, dual-stream DiT; - Supports multi-shot narrative, multi-subject focus in single shots; - Generates 2K video (also 1080P / 720P); - Supports 12 reference files (text / image / audio / video modalities).
1:23 PM Feb 7, 2026
Seedance 2.0 by Bytedance and Doubao provides an image-to-video update. It can create the One Piece 世界场景。
6:03 AM Feb 7, 2026
Most exciting new text-to-video model? Seedance 2.0, currently open for beta testing in China.
1:44 PM Feb 7, 2026
This new Seedance 2.0 model from China can generate an entire film scene with sound effects, audio, and lip-sync all from a single prompt.
1:54 PM Feb 7, 2026
ByteDance launches Seedance 2.0, a new 4.5B parameter video generation model with large scale multi-shot and simultaneous audio and video generation. The model accepts multi-modal inputs, including text, images and audio, with a maximum of 12 references.
12:54 PM Feb 7, 2026
Seedance 2.0: 4.5B dual-stream DiT, 2K, 12 ref, audio/visual sync, multi-shot. Hot.
7:35 AM Feb 7, 2026
Seedance 2.0, 4.5B parameters, dual-stream DiT. Supports 2K resolution. Supports 12 multimodal input files. Supports audio/video joint generation. Supports 8 language lip sync. Features multi-shot narrative, multi-subject close-up shots. Generating video in 48s at 720p, around 4.5 min for 2K at 24fps? - some use case from a wechat group? The first is 12s. This is somewhat in line with expected 4.5B performance in 2025-2026.
5:37 AM Feb 7, 2026
Community Tutorials & Reviews
Watch creators break down Seedance 2.0 features, workflows, and real-world results.
What is Seedance 2.0
The Dual-Branch Diffusion Transformer powering cinematic AI video.
SeeDance-2, also known as Dreamina video, is a powerful AI video generation model by ByteDance. With 4.5B parameters and dual-stream DiT architecture, it delivers native multi-shot narrative, multi-subject close-ups, and simultaneous audio-video generation for lifelike cinematic outputs.
Seedance-2 supports 2K output, up to 12 multimodal references, and ultra-fast rendering at 720p. It's built for filmmakers, marketers, and creators who need consistent storytelling with natural dialogue and sound design.
Dual-Branch DiT
Separate attention streams for audio and video, fused for synchronized output.
Multi-Shot Stories
Native multi-shot narrative with smooth camera cuts and subject continuity.
Audio + Video Sync
Phoneme-level lip sync with spatial sound and ambient effects.
SeeDance 2.0 Features
Purpose-built for cinematic storytelling, high fidelity, and synchronized audio.
Native Multi-Shot Storytelling
Generate multi-shot scenes in a single prompt with automatic camera cuts, dynamic angles, and narrative pacing.
2K Cinema Resolution
Produce cinematic 2K output (2048×1080) with strong motion fidelity and vivid detail.
Phoneme-Level Lip Sync
Dialogue audio and lip motion are generated together for natural speech across 8+ languages.
12-File Multimodal Input
Upload up to 12 references across text, images, audio, and video for precise control.
Audio-to-Video Generation
Drive visuals directly from audio cues, combining music, SFX, and vocal tracks.
Character Consistency
Keep characters recognizable across shots and scenes for coherent storytelling.
Realistic Physics Simulation
Stable motion and believable physical interactions for more cinematic realism.
Natural Language Video Editing
Edit generated clips by describing desired changes in plain language.
How to Use Seedance-2
Generate cinematic videos in three simple steps.
Seedance-2 Text to Video
Turn a detailed prompt into a multi-shot cinematic sequence.
1
Input prompt
Describe your video in detail. Include scene, characters, actions, style, and mood.
2
Select mode
Choose between Pro or Lite version depending on your requirements.
3
Generate
Click generate and wait for your high-quality video to be produced.
Seedance-2 Image to Video
Animate a still image with motion and cinematic lighting.
1
Upload image
Upload a high-quality reference image.
2
Add prompt
Describe the motion and changes you want to see.
3
Generate
Your still image will be animated into a video clip.
Seedance-2 Pricing Plans
Choose the plan that fits your production volume.
Start Generating
Need custom enterprise pricing? Contact us.
FAQ
Questions, answered
Everything you need to know about Seedance-2.
Is Seedance-2 available now?
Seedance-2 is currently available for testing in select regions. Global rollout is expected soon.
What's the difference between Seedance-2 Pro and Lite?
Pro version offers higher quality and longer duration, while Lite provides faster generation and lower cost.
Does Seedance-2 generate audio?
Yes, Seedance-2 can generate synchronized audio including speech, ambient sounds, and music.
What resolution does Seedance-2 support?
Seedance-2 supports up to 2K resolution (2048x1080).
Get started
Ready to create your first Seedance-2 film sequence?
Generate multi-shot scenes with natural audio, consistent characters, and cinematic resolution.