What is Seedance 2.0?

Seedance 2.0 is ByteDance's next-generation video creation model. Built with a unified multimodal audio-video joint generation architecture, it supports four input modalities: text, image, audio, and video.

How does it handle complex motions?

With outstanding motion stability and physical restoration capabilities, Seedance 2.0 performs excellently in multi-subject interaction and complex motion scenes, reaching industry-leading SOTA levels in generation usability. It strictly follows real-world physical laws, eliminating common AI glitches.

Can I use multiple reference images?

Yes. Users can simultaneously input up to 9 images, 3 video clips, 3 audio clips, plus natural language instructions. The model can reference composition, motion, camera movement, visual effects, and audio from these assets.

How good is the audio generation?

Seedance 2.0 integrates two-channel stereo technology for high-fidelity, immersive sound. It supports multi-track parallel output for background music, ambient foley, and voiceovers, achieving seamless alignment between sound and motion without needing a separate audio pass.

BYTEDANCE SEED|Lanzamiento oficial de Seedance 2.0

La nueva generación de creación de video

Una arquitectura unificada de generación conjunta multimodal de audio y video. Experimenta una estabilidad de movimiento líder en la industria, fidelidad física y audio inmersivo de doble canal.

Experiencia audiovisual fotorrealista

Impulsado por mejoras importantes en las capacidades fundamentales y el rendimiento multimodal, Seedance 2.0 brinda a los usuarios una experiencia creativa totalmente nueva.

Prompt: T2V prompt: Camera follows a man in black sprinting through a crowded street, a group chasing close behind. The shot cuts to a side tracking angle as he panics and crashes into a roadside fruit stall, scrambles to his feet, and keeps running.

Stable Rendering of Complex Motions

Seedance 2.0 delivers a remarkable leap in generation quality, achieving unprecedented naturalness and physical plausibility. It synthesizes high-fidelity and precisely timed complex interactive scenes, eliminating physical glitches commonly seen in earlier AI-generated videos.

Multimodal 'All-Round Reference'

Supports combined input of texts, images, videos, and audio. The model accurately understands multimodal input and generates output by referencing visual composition, camera language, motion rhythm, and sound characteristics.

Prompt: R2V Prompt: 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.

Prompt: T2V Prompt: A Wuxia-style audiovisual blockbuster. A white-clad swordsman and a straw-caped blademaster face off in a bamboo forest... Suddenly, a crack of thunder flashes, and both charge simultaneously. A fast-panning profile shot captures their mud-splattering footsteps.

Dual-channel Audio Capabilities

Integrating two-channel stereo technology enables high-fidelity, immersive sound generation. The model supports multi-track parallel output for background music, ambient sound effects, and character voiceovers, all seamlessly aligned with the visual rhythm.

Greater Controllability & Editing

Seedance 2.0 features prompt-driven camera planning, allowing it to automatically plan camera language and design visual presentation templates. It also supports video extension functionality that can generate continuous shots based on user prompts.

Prompt: R2V Prompt: 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... He turns to walk toward a woman in white riding a white horse and presents the flowers to her.

Explora las posibilidades

Explora nuestra selección destacada para inspirar tu próxima gran idea. Activa el audio para escuchar la generación de sonido nativo.

Prompt-Driven Camera Planning

T2V prompt: Year of the Horse Spring Festival family footage. The camera quickly pans across a row of solo portraits of family members like flipping through an album, and each photo 'comes to life' the moment the camera passes over it...

Immersive Foley & ASMR

T2V prompt: Immersive first-person hand ASMR video. Close-up shot, under warm, soft lighting. A pair of slender hands gently triggers different objects in sequence: the light scratching of frosted glass, rubbing of plush fabric...

Commercial Scenario Adaptability

I2V Prompt: 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...

High-Intensity Motion & Rhythm

T2V Prompt: 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...

¿Listo para transformar tus ideas en realidad?

Aprovecha la potencia de Seedance 2.0 directamente dentro de Frameloop. Crea tus guiones, añade tus recursos y genera videos cinemáticos con audio nativo en minutos.