About Seedance 2.0 Mini - Image to Video
ByteDance Seedance 2.0 Mini animates a starting frame into video with an optional end-frame transition, a cost-effective option built for high-volume video creation. Supports 480p and 720p output, durations from 4-15 seconds, and multiple aspect ratios.
Ready to build with Seedance 2.0 Mini - Image to Video?
Try Seedance 2.0 Mini - Image 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-2-0-mini-image-to-video",
"prompt": "Slow cinematic dolly-in as warm golden-hour light sweeps across the scene, drifting dust and a gentle camera push, 35mm film grain, shallow depth of field.",
"input_image": "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/ox_zoom_out_1926_1076.png",
"input_image_has_face": false,
"tail_image_url_has_face": false,
"generate_audio": true,
"aspect_ratio": "16:9",
"duration": -1,
"resolution": "720p",
"watermark": false
}'Request parameters
Every field Seedance 2.0 Mini - Image to Video accepts in the request body. See the API reference for response formats.
POST
https://hub.oxen.ai/api/ai/videos/generate| Field | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | The text prompt describing the desired motion and action for the video. |
input_image | stringuri | Yes | — | The URL of the starting frame image. Formats: JPEG, PNG, WebP. Max 30 MB. |
input_image_has_face | boolean | No | false | Turn this on when the start frame contains a real human face. Content filters may block the request if this is not enabled. |
tail_image_url | stringuri | No | — | Optional URL of the end-frame image for first+last-frame transitions. |
tail_image_url_has_face | boolean | No | false | Turn this on when the end frame contains a real human face. Content filters may block the request if this is not enabled. |
generate_audio | boolean | No | true | Whether to generate synchronized audio. |
aspect_ratio | string | No | "16:9" | adaptive21:916:94:31:13:49:16 |
duration | integer | No | -1 | Range: 4 – 15 |
resolution | string | No | "720p" | 480p720p |
watermark | boolean | No | false | Whether to add an 'AI generated' watermark to the output. |