Seedance 2.0
ByteDance's multimodal AI video generator supports text, image, audio, and video inputs, with model-dependent controls for duration, audio, and reference files.
Why Seedance 2.0?
A unified multimodal architecture that generates audio and video together, with unprecedented creative control over AI video generation.
Multimodal Input
Seedance 2.0 supports text, image, audio, and video as input — four modalities for AI video generation. Upload up to 9 images, 3 videos, and 3 audio files to guide generation with pixel-level precision.
Character Consistency
Use references and detailed prompts to guide characters and scenes across longer AI-generated shots. Results vary by scene and input.
Dual-Channel Audio
Seedance 2.0 generates synchronized dual-channel stereo audio — dialogue, sound effects, and background music — natively aligned with your AI-generated video content.
Smart Editing & Extension
Edit existing AI-generated videos by replacing characters, modifying scenes, or extending clips. Seamlessly continue your story with stable visual continuity using Seedance 2.0's targeted editing.
Physics-Accurate Motion
Seedance 2.0 is designed to handle multi-subject movement, gravity, fluids, and material behavior. Results vary with the prompt and source media.
Director-Level References
Reference composition, camera movement, motion rhythm, and visual effects from your input assets in Seedance 2.0. Upload storyboards, reference videos, and audio clips — your references become your creative direction for AI video generation.
See What Seedance 2.0 Can Create
From cinematic storytelling to product commercials — real AI video generation examples powered by Seedance 2.0.
Product Commercial
The character in the painting looks guilty, darting glances left and right before leaning out of the picture frame. Very swiftly, they extend a hand outside the frame, grab a cola, take a sip, and reveal a look of deep satisfaction. Hearing footsteps approach, the character hastily puts the cola back just as a Western cowboy walks by and picks it up. The ending shot pushes in on a top-lit close-up of the cola against a pure black background, with artistic subtitles and a voiceover appearing at the bottom: "Yikou Cola, an absolute must-try!"
Extend the Video Length
Extend the video length. The camera follows a man in orange riding a brown horse. He speeds up and gallops to a large tree with orange flowers ahead, breaks off two blossoms from the branch. Then others ride into the frame one after another. The camera pushes in to shoot the man in orange clothes dismounting from the horse, then the camera quickly circles around him. He turns to walk toward a woman in white riding a white horse and presents the flowers to her. Style: Chinese classical lady painting, 3D, cheerful folk music, shadow puppet style, with black, white, and orange as the main color palette.
Multimodal All-Round Reference
Refer to the shooting script in @Image 1, and draw on the storyboard, shot scale, camera movement, visuals and copy in @Image 1. The character is from @Image 2, the scene is from @Image 3, and the props are from @Image 4. Create a 15-second healing short film.
Wuxia-Style Audiovisual Blockbuster
A Wuxia-style audiovisual blockbuster. A white-clad swordsman and a straw-caped blademaster face off in a bamboo forest. The camera slowly pushes in between them, shifting focus between raindrops and sword hilts. The atmosphere is extremely oppressive; only the sound of rain can be heard. Suddenly, a crack of thunder flashes, and both charge simultaneously. A fast-panning profile shot captures their mud-splattering footsteps. The precise moment their weapons clash, the footage switches to ultra-slow motion, clearly displaying the ring-shaped shockwaves of rainwater blasted away by the blades, along with bamboo leaves sliced by sword aura. Normal speed resumes as they land back-to-back. The straw-caped blademaster's bamboo hat splits open, and the scene cuts abruptly.
1920s Jazz Club Charleston Dance
1920s jazz club-style Charleston dance. A female dancer in a gold fringe dress and a male dancer in a striped suit perform a high-intensity routine. Moves include hyper-fast syncopated footwork, aerial catches, and exaggerated arm swings. The camera uses dynamic tracking, interspersed with close-ups of footwork. Emphasis is on physical details the fringe swinging wildly with every kick, the sheen of sweat on their skin, and the smoky, vintage film grain cinematic texture. A background jazz band and cheering audience amplify the frenzied party atmosphere.
Girl Hangs Laundry Gracefully
A girl hangs laundry gracefully. After finishing, she takes another piece of clothing from the bucket and shakes it vigorously.
Key Capabilities of Seedance 2.0
Explore Seedance 2.0 video generation inputs, controls, and supported workflows
4-Modality AI Video Generation
Unlike Seedance 1.5 Pro which supports only text and image input, Seedance 2.0 accepts four input modalities — text prompts, images, audio files, and video clips. Upload up to 15 reference files simultaneously for precise control over your AI-generated video.
Native Audio-Visual Joint Generation
Seedance 2.0 can generate synchronized audio with supported outputs, including dialogue, sound effects, and background audio when the selected mode provides those controls.
Targeted Video Editing
Seedance 2.0 introduces targeted editing for AI-generated videos — replace specific characters, modify individual scenes, or extend clips without regenerating the entire video. Seedance 1.5 Pro requires full regeneration for any change.
Storyboard-to-Video Generation
Upload a storyboard or shooting script as a reference image and Seedance 2.0 will follow the shot scale, camera movement, and visual composition. The AI video generator transforms your creative direction into a polished video automatically.
Motion and Scene Dynamics
Seedance 2.0 is designed for scenes involving gravity, fluid motion, cloth, and multiple subjects. Output quality depends on the prompt, references, and selected settings.
Character & Scene Consistency
Use references and detailed prompts to guide character identity, wardrobe, and environment across multiple shots. Consistency can vary by scene and source material.
Technical Specifications
Seedance 2.0 delivers professional-grade AI video generation with flexible configuration options.
15 seconds
480P / 720P / 1080P
16:9, 9:16, 1:1, 4:3, 3:4, 21:9
Dual-channel stereo (native)
Up to 15 (9 images + 3 videos + 3 audio)
Text + Image + Audio + Video
ByteDance via APImart
Seedance 2.0 vs Seedance 1.5 Pro
Compare supported inputs and output controls with the previous model generation.
| Feature | Seedance 2.0 | Seedance 1.5 Pro |
|---|---|---|
| Max Duration | 15s | 12s |
| Max Resolution | 1080P | 1080P |
| Audio Output | Dual-channel Stereo | Mono (coordinated) |
| Reference Files | 15 (9 img + 3 vid + 3 aud) | 3 |
| Input Modalities | 4 (Text + Image + Audio + Video) | 2 (Text + Image) |
| Character Consistency | Yes | Good |
| Physics Accuracy | Yes | Baseline |
| Video Extension | Yes | No |
| Targeted Editing | Yes | No |
| Storyboard-to-Video | Yes | No |
Ready to Create with Seedance 2.0?
Start creating with Seedance 2.0 using the models and output options currently available.
Turing AI