Seedance 2.5 text-to-video

Seedance 2.5 AI Video Generator

Create a cinematic video up to 30 seconds long from a prompt, first and last frames, or multimodal reference media with Seedance 2.5.

Input

Model
0 / 20000

Be specific about the subject, action, camera movement and visual style.

Reference media

Use first and last frames, or add up to 50 multimodal references. These two workflows cannot be combined.

Resolution
Aspect ratio
Video duration
Generate synchronized audio
Use web search

Output

Your video will appear here

Add a prompt and optional reference media, then choose your output settings.

The model, explained

What is Seedance 2.5?

Seedance 2.5 is ByteDance's next-generation cinematic video model. It creates coherent shots up to 30 seconds long while following the subjects, action, camera direction, and atmosphere in your prompt.

Choose first and last frames for a controlled transition, or use up to 50 image, video, and audio references to guide characters, products, motion, timing, and sound.

FramePack brings the Seedance 2.5 workflow into one place with secure uploads, 480p and 720p output, synchronized audio, asynchronous progress, and downloadable results.

Built for cinematic video

Why use Seedance 2.5?

A longer, more controllable workflow for turning ideas and multimodal references into directed AI video.

Prompt-led direction

Describe the subject, action, camera movement, pacing, and atmosphere in one focused prompt.

Up to 50 references

Upload up to 30 images, 10 videos, and 10 audio files to guide identity, timing, motion, and sound.

Synchronized audio

Enable native synchronized audio when the scene needs sound that follows the generated action.

Up to 30 seconds

Choose a 4–30 second duration, seven aspect ratios, 480p or 720p output, and optional web search.

2.5 by default, 2.0 available

Start with Seedance 2.5, or switch to the retained 2.0, Fast, and Mini models for different quality, speed, and cost tradeoffs.

Safety checks enabled

Every request is sent with safety checking enabled for a safer generation workflow.

Three simple steps

How to create a Seedance 2.5 video

Start with a clear idea, add only the references that help, and let Seedance build the scene.

  1. 01

    Describe the scene

    Write the subject, action, camera direction, pacing, and visual style you want to see.

  2. 02

    Upload reference media

    Add first and last frames, or upload image, video, and audio references to guide the result.

  3. 03

    Choose settings and generate

    Select the aspect ratio, resolution, duration, audio, and search settings. Submit, then preview and download the finished video.

Seedance prompting tips

Specific prompts and purposeful references help the model keep the generated movement coherent.

  • Name the main subject first, then describe one clear action and the environment around it.
  • Mention camera movement only when it contributes to the shot, such as a push-in, orbit, pan, or handheld follow.
  • Use a first and last frame for a controlled transition, or use multimodal references when you want broader visual guidance.
  • Turn on synchronized audio when dialogue, ambience, or sound effects are an important part of the scene.
  • Seedance 2.5 supports 480p or 720p and up to 30 seconds. The retained 2.0 models support up to 15 seconds, while standard 2.0 also offers 1080p and 4K.

Questions, answered

Seedance 2.5 FAQ

What does Seedance 2.5 do?

Seedance 2.5 turns a text prompt and optional frame or multimodal references into a cinematic video up to 30 seconds long.

How is my generation processed?

Your settings and uploaded references are validated by our server and submitted as an asynchronous generation task. The page follows the task until the result is ready.

Can I use frames and other reference media together?

First and last frames are mutually exclusive with reference images, video, and audio. Choose the workflow that best matches the control you need for the shot.

How long does a Seedance video take?

Generation time varies with duration, resolution, generation-service capacity, and queue length. The output panel shows the latest task progress while FramePack processes the video.

Bring your scene to life

Write a focused prompt, upload the references that matter, and create a cinematic Seedance video online.

Create with Seedance 2.5