ByteDance/bytedance-seedance-2-0-reference-to-video/Released Apr 2026
Seedance 2.0 - Reference to Video
Turn your references into beautiful, unrestricted video. Express your creativity to the fullest with real faces, real action, and audio up to 4k, for up to 30% less than other providers.
Commercial use
Video
About Seedance 2.0 - Reference to Video
ByteDance Seedance 2.0 (Pro) generates video from a text prompt guided by reference images, videos, and/or audio. Supports 480p, 720p, 1080p, and 4k output.
See what this model can do
A handful of real prompts and their outputs.
Cinematic
Desert Highway at Golden Hour
"Slow camera move, warm low sun, shallow depth of field."
Realistic characters
Close-Up Portrait at Dawn
"Photorealistic skin, soft natural light."
Action
Martial Arts Fight Scene
"Choreographed combat, dynamic camera, rain and neon."
Commercial
Product Commercial
"Studio lighting, slow rotation, premium look."
UGC
UGC Testimonial
"Handheld selfie, natural delivery."
3D Animation
3D Animated Character
"studio-quality 3D render, expressive motion, vibrant colors."
Ready to build with Seedance 2.0 - Reference to Video?
Try Seedance 2.0 - 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-2-0-reference-to-video",
"prompt": "A lone ox walks down an empty desert highway at golden hour, dust drifting behind it, slow cinematic camera move, warm low sunlight, shallow depth of field.",
"generate_audio": true,
"aspect_ratio": "16:9",
"duration": -1,
"resolution": "720p",
"watermark": false
}'Request parameters
Every field Seedance 2.0 - Reference 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 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. Up to 9 total reference images and up to 15 total references across all types may be used. |
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. Up to 3 total reference videos and up to 15 total references across all types may be used. |
input_audios | array<string> | No | — | Reference audios that guide the generated video. Up to 3 total reference audios and up to 15 total references across all types may be used. |
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" | 480p720p1080p4k |
watermark | boolean | No | false | Whether to add an 'AI generated' watermark to the output. |