ToolPic

Seedance 2.5 Image to Video - Animate Any Photo

Bring still images to life with Seedance 2.5 image-to-video. Reference up to 50 images, describe the motion, and copy the API request for 4K animated results.

Describe your scene — Seedance 2.5 generates up to 30 seconds of native audio-visual output.

Tip: put spoken dialogue in "double quotes" for better synced audio.

10s
Optimized Seedance prompt

a cinematic scene. with natural ambient sound.

API request body (ModelArk)
{
  "model": "dreamina-seedance-2-5-260628",
  "content": [
    {
      "type": "text",
      "text": "a cinematic scene. with natural ambient sound."
    }
  ],
  "resolution": "720p",
  "ratio": "16:9",
  "duration": 10,
  "generate_audio": true,
  "camera_fixed": false,
  "output_format": "mp4"
}

Your files are processed locally in your browser. Nothing is uploaded to any server.

How to Animate an Image

1

Reference Your Image

Switch to image-to-video mode and point to your picture in the prompt as @image1. Seedance 2.5 can accept up to 50 references for characters, products, and style.

2

Describe the Motion

Explain how the image should move — a slow turn, falling leaves, a camera push-in. Keep the subject consistent and let the motion do the storytelling.

3

Copy the Request

Copy the generated prompt and JSON body, add your image URLs to images_list, and send it to your Seedance 2.5 provider to render the animation.

Image-to-Video FAQ

How many reference images can Seedance 2.5 use?

Up to 50 multimodal references in a single request. You can combine a character image, a product shot, a style board, and a motion reference so the model keeps everything consistent across the clip.

How do I reference an image in the prompt?

Use the @image1, @image2 syntax inside the prompt text and list the actual image URLs in the images_list field of the request. The builder inserts the @image1 tag for you when you switch to image-to-video mode.

Will my character stay consistent?

Seedance 2.5 is built for character and brand consistency. Providing a clear reference image and describing motion rather than changing the subject gives you the most stable, on-model results.