Skip to content
ByteDance logo

Seedance 2.0

Text-to-VideoByteDanceProxied

ByteDance's next-generation video model with a unified multimodal architecture. Generates high-quality video with synchronized audio from text, images, video clips, and audio inputs. Supports multimodal references (up to 9 images, 3 videos, 3 audio files), native audio generation, video editing, video extension, intelligent duration, and adaptive aspect ratio.

Model Info
More informationlink
PricingView pricing in the Cloudflare dashboard

Usage

TypeScript
const response = await env.AI.run(
'bytedance/seedance-2.0',
{
prompt: 'A golden retriever running through a field of sunflowers on a sunny day',
aspect_ratio: '16:9',
duration: 5,
resolution: '720p',
},
)
console.log(response)

Examples

High Resolution Cinematic — Cinematic video in 1080p
TypeScript
const response = await env.AI.run(
'bytedance/seedance-2.0',
{
prompt:
'A dramatic drone shot flying through misty mountain peaks at sunrise, cinematic lighting with volumetric fog',
aspect_ratio: '16:9',
duration: 10,
resolution: '1080p',
},
)
console.log(response)
Image to Video — Generate video from a reference image
TypeScript
const response = await env.AI.run(
'bytedance/seedance-2.0',
{
image:
'data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAACAAAAAgCAYAAABzenr0AAAAnklEQVR42u2XQRLAIAgD8/839i/26qFCACm0ozPe1KwcQsAoXvgcAABxpwFowl4QWITHxW0LCBhxVngF4gKIirMQyBRnIJAtrkE8AuwWnyFEgKzfS1UA+3sWTju3BGAu7gKYIfBW+Q/AAQgBeMCkt1wVsLZjcwUYG2Z9wGLHZitWk1DEisubUYt2XB5IWkSyFqG0RSxvMZi0Gc1+Ox3fm00ZJ5mGVtkAAAAASUVORK5CYII=',
prompt: 'The character begins walking forward through the scene',
aspect_ratio: '16:9',
duration: 5,
resolution: '720p',
},
)
console.log(response)
Portrait Video — Vertical video for social media
TypeScript
const response = await env.AI.run(
'bytedance/seedance-2.0',
{
prompt: 'Abstract ink drops spreading through water, vivid colors mixing in slow motion',
aspect_ratio: '9:16',
duration: 5,
resolution: '720p',
},
)
console.log(response)

Parameters

aspect_ratio
stringrequireddefault: 16:9enum: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, 9:21Video aspect ratio. Ignored if an image is used.
camera_fixed
booleanrequireddefault: falseWhether to fix camera position
duration
integerrequireddefault: 5maximum: 12minimum: 4Video duration in seconds
fps
numberrequireddefault: 24const: 24Frame rate (frames per second)
generate_audio
booleanWhether to generate audio with the video
image
stringReference image (HTTP(S) URL or base64 data URI) for image-to-video
last_frame_image
stringReference image (HTTP(S) URL or base64 data URI) for last-frame guidance. Only works if an image start frame is also given.
prompt
stringrequiredmaxLength: 2000Text prompt describing the video to generate
reference_video
stringReference video (HTTP(S) URL or base64 data URI) for style/motion guidance
resolution
stringrequireddefault: 720penum: 480p, 720p, 1080pVideo resolution
seed
integermaximum: 9007199254740991minimum: -9007199254740991Random seed for reproducible generation
watermark
booleanrequireddefault: falseWhether to add a watermark to the output video

API Schemas (Raw)

Input
Output