Seedance 2.0
Seedance 2.0 supports four input modalities—images, videos, audio, and text—enabling richer expression and more controllable generation.
Input
Prompt
Audio
Duration(s)
Resolution
BytePlus Fallback
Aspect Ratio
- auto
- 16:9
- 9:16
- 1:1
- 4:3
- 3:4
- 21:9
Billed at 95% of official token usage
Result
View HistorySeedance
| Model & Modality | Credits / Gen | Our Price (USD) | Official Price (USD) | DISCOUNT |
|---|---|---|---|---|
seedance-2, 480p with video input videoByteDance | 9 ~ 10.8 per second (input + output) | $0.0402 | $0.04221 | - 5% |
seedance-2, 480p no video input videoByteDance | 15 ~ 17.8 per second | $0.067 | $0.07035 | - 5% |
seedance-2, 720p with video input videoByteDance | 19 ~ 23.4 per second (input + output) | $0.0848 | $0.0896 | - 5% |
seedance-2, 720p no video input videoByteDance | 32 ~ 38.3 per second | $0.1429 | $0.15 | - 5% |
seedance-2, 1080p with video input videoByteDance | 48 ~ 57.9 per second (input + output) | $0.2143 | $0.225 | - 5% |
seedance-2, 1080p no video input videoByteDance | 78 ~ 95.2 per second | $0.3482 | $0.365 | - 5% |
seedance-2, 4k with video input videoByteDance | 98 ~ 119.5 per second (input + output) | $0.4375 | $0.4593 | - 5% |
seedance-2, 4k no video input videoByteDance | 159 ~ 194.2 per second | $0.7098 | $0.7434 | - 5% |
| Model & Modality | Credits / Gen | Our Price (USD) | Official Price (USD) | DISCOUNT |
|---|---|---|---|---|
seedance-2 fast, 480p with video input videoByteDance | 7 ~ 8.4 per second (input + output) | $0.0313 | $0.033 | - 5% |
seedance-2 fast, 480p no video input videoByteDance | 12 ~ 14.5 per second | $0.0536 | $0.05628 | - 5% |
seedance-2 fast, 720p with video input videoByteDance | 15 ~ 18.7 per second (input + output) | $0.067 | $0.07035 | - 5% |
seedance-2 fast, 720p no video input videoByteDance | 26 ~ 30.8 per second | $0.1161 | $0.122 | - 5% |
Seedance 2.0 API
Seedance 2.0 supports four input modalities—images, videos, audio, and text—enabling richer expression and more controllable generation.
Prompt:
A female star performs energetic dance moves on stage, with the camera rhythmically pushing, pulling, panning, and tilting.
Key Features of Seedance 2.0
A fully controllable multi-modal AI video model. Reference anything. Edit anything. Create anything.
Multi-Modal Input
Upload up to 9 images, 3 videos (15 seconds total), and 3 audio files. Seamlessly combine text, images, videos, and audio to express your creative vision with unmatched flexibility.
Reference Anything
Reference motion, visual effects, camera movements, characters, scenes, or sounds from any uploaded asset. Simply describe what you want in natural language — Seedance understands.
Superior Consistency
Maintain frame-to-frame consistency for faces, outfits, text, environments, and visual styles. No character drift. No style breakage.
Precise Motion & Camera Replication
Upload a reference video to accurately replicate choreography, cinematic camera moves, and complex action sequences — no detailed prompting required.
Video Extension & Editing
Extend existing footage, merge multiple clips, or edit specific segments with ease. Replace characters, add elements, or modify actions while preserving the rest of the video.
Built-in Audio Generation
Generate context-aware sound effects and background music automatically. Sync visuals to uploaded audio or music beats for perfectly timed results.
Experience the Power of Seedance 2.0 Multi-Modal AI Video Creation
Combine images, videos, audio, and text to effortlessly generate cinematic content with precise reference control, seamless video extension, and natural language guidance. Make your creations more flexible and let your imagination soar.
Immersive 2K Visual Experience
Seedance 2.0 can generate ultra-clear 2K videos, capturing every texture and subtle motion in each frame. AI automatically enhances lighting and color, making visuals more natural and vibrant. Whether it’s a short film, social media clip, or brand content, Seedance 2.0 preserves original quality while ensuring smooth playback. Ultra-fast rendering allows creators to quickly obtain high-quality video outputs.
Accelerated Creation, Extended Video Length
With an intelligent AI workflow, Seedance 2.0 boosts production efficiency by 30% and supports videos up to three times longer than traditional clips, perfect for tutorials, presentations, or storytelling. Even in longer sequences, visuals remain smooth and clear, saving time while maintaining professional-quality output.
Cross-Platform Smart Adaptation, Streamlined Workflow
Seedance 2.0 automatically adjusts video size, resolution, and aspect ratio, making it compatible with any platform without extra effort. It integrates seamlessly with other tools and APIs, speeding up exports and simplifying the production process. Creators can focus on their ideas while Seedance 2.0 ensures consistently high-quality videos, ready for any platform now and in the future.
Improvements in Seedance 2.0 API Compared to Earlier Versions
Seedance 2.0 supports image, video, audio, and text inputs. Unlike previous versions, it allows precise control of actions, effects, camera movements, characters, scenes, and audio through natural language, enabling truly controllable video creation.
| Model | 2.0 | 1.5-pro | 1.0-pro | 1.0-pro-fast | 1.0-lite |
|---|---|---|---|---|---|
Positioning | Multimodal AI video, supporting images, videos, audio, and text, with precise natural language control. | High-precision audio-video synchronization, cinematic motion and emotion, supports start-and-end frame control | Fully featured, unique multi-shot storytelling, supports start-and-end frame control | Fully featured, unique multi-shot storytelling, supports start-and-end frame control | Fully featured, unique multi-shot storytelling, supports start-and-end frame control |
Resolution | 2K | 1080P | 1080P | 1080P | 1080P |
Frame Rate | 24fps | 24fps | 24fps | 24fps | 24fps |
Video Length | 15s | 12s | 12s | 12s | 12s |
Audio-Visual Generation | Supported | Supported | Not supported | Not supported | Not supported |
Text-to-Video | Supported | Supported | Supported | Supported | Not supported |
Frequently Asked Questions
What is Seedance 2.0?
Seedance 2.0 is a revolutionary multi-modal AI video generation model that supports images, videos, audio, and text inputs, allowing you to reference actions, effects, camera movements, characters, scenes, and sounds through natural language for highly controllable video creation.What inputs are supported?
Seedance 2.0 supports up to 9 images, 3 videos (total ≤15 seconds), 3 audio files (MP3, total ≤15 seconds), and text prompts, with a maximum of 12 files combined for maximum creative flexibility.What content can be referenced?
Almost any element from your uploaded content can be referenced, including actions, visual effects, transitions, camera movements, character styles, scene composition, and audio, simply by describing it in the prompt, e.g., "use @video1's camera movement and @image1's character style."How does video extension work?
Seedance 2.0 can seamlessly extend existing videos while maintaining consistency in action, style, and content for smooth transitions.How does the audio feature work?
Seedance 2.0 has built-in audio generation to create context-aware sound effects and background music, and also allows uploading audio files to synchronize video with beats or rhythm, ideal for music and dance content.What video lengths and resolutions are supported?
Seedance 2.0 generates videos of 4–15 seconds, supports multiple aspect ratios (16:9, 9:16, 4:3, 3:4, 21:9, 1:1), and outputs up to 1080p resolution for professional production needs.How is character consistency maintained?
Seedance 2.0 ensures consistency in faces, costumes, text, scenes, and visual style, keeping characters stable across frames and shots while avoiding drift or inconsistent styles.How is privacy and security ensured?
All uploaded content and generated videos are securely stored using industry-standard encryption, kept completely private, never shared, and deleted after 7 business days, so please download in advance.
