Seedance 2.5 Flash image to video

Quick answer: Seedance 2.5 Flash does image-to-video three ways: from a first frame, from a first and last frame, or from up to ten reference images. SceneMixer uses the reference route: the images are your characters, locations and props, and each Flash segment is generated from them plus the shot you wrote. To make a particular photo move, put it on a character or location card and write what happens.
Still from “The Last Envelope”, an AI short drama generated end-to-end by SceneMixer (6 characters, 1 episode)
SampleThe Last EnvelopeDigital HD1 episodeProduced end-to-end by SceneMixer from the scriptWatch the episodes

Three ways an image goes in

  • First frame: the clip starts on your image and moves from there.
  • First and last frame: the clip travels from one image to another.
  • References: up to ten images say who and what is in the clip, without fixing any one frame.

The first two suit a single shot. References suit a story, because the same face can appear in a hundred different shots.

How SceneMixer feeds images to Flash

When your script is read, every character, location and prop is drawn once as a reference image. Each Flash segment is sent the images for whoever and whatever is in it, and opens in the state the previous segment ended in. You never pick a frame by hand; you write the shot. How many references Flash takes

Making your own photo move

  1. In step 2, open the character, location or prop the photo should stand for.
  2. Press Upload & Replace and choose the file.
  3. Pick Optimize into a reference sheet for a snapshot, so its background and lighting do not ride into every shot, or Use this image as is for art made to be a sheet.
  4. Write the shot — what the person does, where the camera is — and generate the segment on Seedance 2.5 Flash.

Uploading is a paid-plan feature. Prepare the image like a sheet: one person, a plain background, 9:16 for people and 16:9 for places and props. What changes when you replace a sheet

What it will not do

  • There is no one-button “animate this photo” tool: a photo becomes a character or a place, and the shot says what moves.
  • Photos of a product can instead become an ad, which is a separate route with its own settings. Image to video in SceneMixer
  • Use only photos you have the right to use.

Sources

  • BytePlus on X, November 12, 2026 — the announcement, the speed claim and the USD 0.152 per second price at 720p.
  • IT Home, November 12, 2026 (Chinese) — Volcano Engine’s figures: about 0.99 yuan a second at 720p, 30-second takes, 10 images, 5 videos and 5 audio clips per request, 480p and 720p, the API date.
  • PANews — the same release in English, with the list of apps it launched in.
  • Dreamina’s Seedance 2.5 Flash page — ByteDance’s own app positions Flash for previews and frequent iteration.

Specifications are as announced on November 12, 2026 and checked on November 16, 2026; the figures for SceneMixer’s tiers on this page are read from the live price list each time the page is built.

FAQ

Does Seedance 2.5 Flash do image to video?

Yes: from a first frame, a first and last frame, or up to ten reference images.

How do I animate my own photo in SceneMixer?

Put it on a character or location card with Upload & Replace, write the shot, and generate the segment.

Is uploading a photo free?

Uploading your own image is a paid-plan feature. The reference sheets SceneMixer draws from your script need no upload.

Will the person look exactly like my photo?

Use this image as is keeps the photo itself as the reference; Optimize redraws it as a clean sheet in the project's style.

What size should the image be?

9:16 for people, 16:9 for places and props, one subject on a plain background.

Can I set the first frame of a clip?

SceneMixer works from references and the previous segment's ending rather than a hand-picked frame.

Put your image on a card

Upload one, write one shot, and generate one Flash segment.

Start a project

Updated November 16, 2026