Seedance 2.5 Image to Video: AI Image-to-Video Generator

Animate images to video with Seedance 2.5. Early-access build with 720p output, and 30-second clips. Try free — pay per generation.

Tutorial

📝

Overview

About this model

Seedance 2.5 Image-to-Video is the early-access build of ByteDance's next-generation Seedance model, animating a single still image into video. It supports clips up to 30 seconds at 720p output. A lower-cost 480p variant is also available, and dedicated First & Last Frame and Omni Reference endpoints cover keyframe transitions and multi-reference blending.

1Product marketing: Turn a single product photo into a moving showcase clip with natural camera motion.
2Photo animation: Bring a portrait or landscape photo to life with subtle, realistic motion.
3Social content: Animate existing photography into short-form video for ads and social posts.
4Concept visualization: Preview how a static design or render would look in motion.
💰

Pricing & Value

Cost analysis

muapiapp$0.60/sec (720p) or $0.30/sec (480p)

Pay-per-generation pricing with no subscription.

Fal.aiNot available

Seedance 2.5 is not listed on Fal.ai.

ReplicateNot available

Seedance 2.5 is not listed on Replicate.

* Competitor pricing is estimated based on similar model architectures and usage tiers.

⚙️

Technical Details

Configuration schema

Promptstring

Text prompt describing the desired motion and style.

Default ValueAnimate the park scene with gentle wind moving the trees, subtle water ripples, and a slow cinematic push forward.
Image URLstring

URL of the input image to animate into video.

Default Valuehttps://samplelib.com/jpeg/sample-city-park-400x300.jpg
Durationint

The duration of the generated video in seconds.

Default Value5
Aspect RatioEnum (7 options)

Aspect ratio of the output video.

Default Value16:9
Seedint

Random seed for reproducible generation. Use -1 for random.

Default Value42
📖

Implementation Guide

Developer documentation

How to Use Seedance 2.5 Image-to-Video

  1. Prepare an Image

    • Use a clear, high-resolution image URL that is publicly accessible.
  2. Write a Motion Prompt

    • Describe the camera movement and animation you want.
    • Example: "Animate the park scene with gentle wind moving the trees, subtle water ripples, and a slow cinematic push forward."
  3. Configure Output

    • Set duration from 4 to 30 seconds.
    • Choose aspect_ratio and optionally seed.
  4. Submit via the API

curl -X POST https://api.muapi.ai/api/v1/seedance-2.5-image-to-video \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Animate the park scene with gentle wind moving the trees, subtle water ripples, and a slow cinematic push forward.",
    "image_url": "https://example.com/park.jpg",
    "duration": 5
  }'
  1. Poll and Download
    • Poll GET /api/v1/predictions/{request_id}/result until status is completed, then retrieve the video URL from output.

Common Questions

Frequently asked

What does Seedance 2.5 Image-to-Video do?

It animates a single input image into video, guided by an optional text prompt describing the desired motion.

What resolution does it output?

720p by default. A cheaper 480p variant is available separately.

Does it support 1080p?

Not yet. This early-access build currently supports 480p and 720p; native 1080p support is planned for a future update.

How long can generated videos be?

Between 4 and 30 seconds, configurable via the `duration` parameter.

Can I animate a start and end frame together?

Yes — use the dedicated Seedance 2.5 First & Last Frame endpoint, which accepts two images and generates a smooth transition between them.

Can I combine multiple images, videos, and audio?

Yes — use the Seedance 2.5 Omni Reference endpoint, which blends up to 30 images, 10 videos, and 10 audio files into one guided generation.