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.
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.
https://hub.oxen.ai/api/ai/videos/generate| Field | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | 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_images | array<string> | No | — | Place reference images here when they show faces, people, or characters. Content filters may block the request otherwise. |
input_images | array<string> | No | — | Reference images that guide the generated video. |
input_face_videos | array<string> | No | — | Place reference videos here when they show faces, people, or characters. Content filters may block the request otherwise. |
input_videos | array<string> | No | — | Reference videos that guide the generated video. |
input_audios | array<string> | No | — | Reference audios that guide the generated video. Audio-only input is supported. |
omni_reference_task_type | string | No | "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_audio | boolean | No | true | Whether to generate synchronized audio. |
aspect_ratio | string | No | "adaptive" | adaptive21:916:94:31:13:49:16 |
duration | integer | string | No | "auto" | Range: 4 – 30 |
resolution | string | No | "720p" | 480p720p |
output_format | string | No | "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 |
watermark | boolean | No | false | Whether to add an 'AI generated' watermark to the output. |