ByteDance/bytedance-seedance-2-5-flash-reference-to-video/Released Nov 2026

Seedance 2.5 Flash - Reference to Video

Fast, low-cost directing with references: images, videos and audio clips guide one generation, or edit and extend a video you already have.

Commercial use
Video

About Seedance 2.5 Flash - Reference to Video

ByteDance Seedance 2.5 Flash generates video from a text prompt guided by reference images, videos, and audio, as the faster, lower-cost tier of Seedance 2.5, with synchronized audio on by default. It takes up to 10 reference images, 5 reference videos, and 5 reference audio clips, including audio-only input, and renders coherent 480p or 720p video up to 30 seconds long.

Beyond new videos it edits a reference video from a description of what to change, and extends a video with new footage. Use it for fast iteration and high-volume work; Seedance 2.5 renders the same prompts at 1080p and 4k.

See what this model can do

A handful of real prompts and their outputs.

Image references
Dachshund Sets Sail
"Character, prop and place each come from a separate reference image."
Video edit
Dawn Deck to Night Blizzard
"The source clip on top, the edit below: new weather, time of day and jacket color."
Video extension
A Whale Joins the Scene
"The original clip, then five more seconds in the same paper style."
Face reference
Weekend Forecast
"One portrait keeps his face and outfit while he speaks a new line."
Audio reference
Marionette Keeps the Beat
"A steel pan recording is the soundtrack and sets the dance timing."

Ready to build with Seedance 2.5 Flash - Reference to Video?

Try Seedance 2.5 Flash - Reference to Video in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.

curl -sSf -X POST https://hub.oxen.ai/api/ai/videos/generate \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $OXEN_API_KEY" \
    -d '{
  "model": "bytedance-seedance-2-5-flash-reference-to-video",
  "prompt": "A cat sitting on a chair",
  "omni_reference_task_type": "reference",
  "generate_audio": true,
  "aspect_ratio": "adaptive",
  "duration": "auto",
  "resolution": "720p",
  "output_format": "mp4",
  "watermark": false
}'

Request parameters

Every field Seedance 2.5 Flash - Reference to Video accepts in the request body. See the API reference for response formats.

POSThttps://hub.oxen.ai/api/ai/videos/generate
FieldTypeRequiredDefaultDescription
promptstringYes
—
The text prompt used to generate the video. Use @Image1, @Image2, @Video1, @Audio1, etc. to reference inputs. Face-containing media is indexed before non-face media within its type.
input_face_imagesarray<string>No
—
Place reference images here when they show faces, people, or characters. Content filters may block the request otherwise.
input_imagesarray<string>No
—
Reference images that guide the generated video.
input_face_videosarray<string>No
—
Place reference videos here when they show faces, people, or characters. Content filters may block the request otherwise.
input_videosarray<string>No
—
Reference videos that guide the generated video.
input_audiosarray<string>No
—
Reference audios that guide the generated video. Audio-only input is supported.
omni_reference_task_typestringNo"reference"Reference mode creates a new video guided by your references. Edit and extend require an input video. Auto will choose based on your prompt.
referenceeditextendauto
generate_audiobooleanNotrueWhether to generate synchronized audio.
aspect_ratiostringNo"adaptive"
adaptive21:916:94:31:13:49:16
durationinteger | stringNo"auto"
Range: 4 – 30
resolutionstringNo"720p"
480p720p
output_formatstringNo"mp4"Output video format. mp4 for broad compatibility, mov for high color precision in professional post-production workflows. For video editing and extension, mov input and output is recommended.
mp4mov
watermarkbooleanNofalseWhether to add an 'AI generated' watermark to the output.