ByteDance's new generation audio-visual creation model "Seedance 1.5 Pro" has officially launched on Douyin, offering ordinary users a new experience of "zero-barrier creation of audio-visual content".

image.png

The newly launched Seedance 1.5 Pro integrates the "text - image - sound" creation process:

  • Semantic + Audio-Visual Synchronization: No longer generate images first and then add sound. The model can deeply understand the text intention and generate matching images and sound effects, dialogue simultaneously, avoiding "audio-visual disconnection";
  • MORE NATURAL "SPEAKING": The generated character dialogue is no longer mechanical synthetic voice, but more natural in tone and rhythm, closer to real human expression;
  • Cinematic Narrative + Dynamic Camera: The video will have scene transitions and camera movement effects automatically, and complex actions (such as body interactions) can be accurately captured without manually adjusting special effects.

Ordinary users' operations are very simple: Open the Douyin App chat window, click the "Make Photo Move" feature, select the "1.5 Pro" model, upload a reference image (such as your own photo or hand-drawn sketch), and input a prompt (such as "Let this cat tell a bedtime story in a gentle tone, with a starry bedroom background"), and you can directly generate a complete audio-visual video. From "generating images and text" to "generating audio-visual videos", Seedance 1.5 Pro takes Douyin's creative capabilities another step forward — now whether it's making short films, product explanations, or turning static materials into dynamic content, everything can be done in one go within the chat window, truly realizing "giving voice to the visuals, making creation happen".