Guides

Seedance video

Make video from a prompt, a starting frame or up to 30 reference images, in chat or through the API.

seedance-2.5 is the premium video model. Give it a prompt and it generates a clip; give it a starting frame or a few reference images and it animates from them, holding your subject consistent across cuts. Clips can run up to 30 seconds with synchronized audio.

Start from a strong input

The biggest lever on quality is what you feed in. A detailed first frame or reference image gives the model real structure to animate, so the result looks the way you intended. A plain text prompt works well for open, generic scenes, but when you want a specific character or look, bring an image.

Three ways to make a clip

The mode is chosen automatically by how many reference images you attach:

  • No references (text to video). Describe the whole scene. Best for open, cinematic shots where any subject will do.
  • One reference (image to video). Your image becomes the first frame. Describe the motion, not the scene, since the scene is already set.
  • Two or more references, up to 30 (reference to video). The images are subject and style references rather than a starting frame. Cite them in the prompt to say what each one is for.

Citing references with @image

When you attach more than one reference, refer to each in the prompt by its number: @image1, @image2, and so on, in the order you added them.

"@image1 walks through the alley lit like @image2, slow dolly in"

In chat, the reference builder numbers each thumbnail; tap a slot to drop its @image token into the prompt at your cursor. In the API, send the images as input_reference and cite them the same way. Order matters: the first image you attach is @image1.

In chat

Select Seedance 2.5 in the composer and a reference builder appears above it:

  • Add references with the tile, up to 30. Each becomes a numbered slot.
  • Tap a slot to cite it (@image1, and so on) in your prompt.
  • Set the duration and size in the toolbar. The price updates live as you change them.

Audio is generated automatically. For a silent clip, drop the audio track in the in-chat video editor after it renders.

In the API

Seedance runs on the async /v1/videos endpoint like every video model: submit a job, poll until it finishes, then download the MP4. Pass model: seedance-2.5, a size and seconds, and send references as multipart input_reference fields. See Videos for the full request and polling flow.

First and last frame

With a single starting image you can also set the last frame, and Seedance animates the transition between them. It is the cleanest way to get a controlled morph, or to continue a clip: feed the previous clip's final frame as the first and a target frame as the last.

In chat, once one reference is set an End slot appears next to it; add an image there for the last frame. In the API, send a second multipart field, last_reference, alongside the single input_reference (the first frame):

curl https://api.roteo.ai/v1/videos \
-H "x-api-key: $ROTEO_API_KEY" \
-F model=seedance-2.5 \
-F "prompt=smooth morph from the first frame to the last" \
-F size=1280x720 \
-F seconds=5 \
-F input_reference=@first.jpg \
-F last_reference=@last.jpg
bash · 8 lines

A last frame works only with exactly one input_reference (the first frame); sending it with none or with several references returns 400.

Duration, size, and cost

  • Duration (seconds): 5, 8, 12, 16, 20, 24, or 30.
  • Size: 1280x720 or 854x480 landscape, 720x1280 or 480x854 portrait.
  • Cost is per delivered clip and scales with duration and size, so a long clip at the largest size costs the most. A failed job is free. Live pricing is in the dashboard.

Writing good prompts

  • Detail is free. The bill depends only on the clip's duration and size, never on how long the prompt is.
  • With a first frame, describe the motion, not the scene. The frame already fixes the look.
  • For a multi-scene story, script the sequence. One clip can carry cuts, camera moves (push in, pull back, defocus), transitions, ambient sound, even an end-card text reveal. Write them in order and cite @image1, @image2 where each reference belongs.
  • Use rich reference images. A detailed photo animates well; a flat logo or solid color gives the model nothing to work with and can stall.
Seedance video | Roteo