Seedance 2.0
ByteDance's Seedance 2.0 video model, served through BytePlus ModelArk. Text to video, image to video from a first and optional last frame, and video guided by up to nine reference images, up to 4K.
- Model id:
bytedance/seedance-2.0 - Type: Video, from BytePlus ModelArk
- Modes: Text to video, Image to video, Reference to video
- Prompt: up to 4,000 characters
- Canceling: Free at any point. A running generation stops at its next status check.
Parameters
Set these in params. Anything left out takes the default, which is what the price estimate assumes.
| Parameter | Accepted values | Default |
|---|---|---|
duration_seconds | 5, 4, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | 5 |
resolution | 720p, 480p, 1080p, 4k | 720p |
aspect_ratio | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9 | 16:9 |
num_outputs | 1 only | 1 |
audio | true, false | false |
seed | 0 to 4294967295 | chosen by the provider |
output_format | mp4 | provider's |
References
Pass media in references, each with a role and an upload_id or HTTPS url (Uploads). When mode is left out it is inferred from the roles.
| Role | Used as | At most |
|---|---|---|
first_frame | First frame of the video | 1 |
last_frame | Last frame of the video | 1 |
reference_image | Subject or style reference | 9 |
Pricing
Billed per second of output video, varying by resolution. The full price list for your account is on the dashboard's billing page and in pricing from GET /v1/models/bytedance%2Fseedance-2.0. Each request reserves its maximum price and is charged for what was produced (Pricing and credits).
Examples
Text to video
import { RawFrame } from "@rawframe/sdk";
const rf = new RawFrame();
const generation = await rf.generations.createAndWait({
model: "bytedance/seedance-2.0",
prompt: "A lighthouse keeper climbing a spiral staircase at dusk, lantern light, slow tracking shot",
params: { duration_seconds: 5, aspect_ratio: "16:9", resolution: "1080p" },
});
console.log(generation.outputs?.[0]?.url);Vertical clip with audio
import { RawFrame } from "@rawframe/sdk";
const rf = new RawFrame();
const generation = await rf.generations.createAndWait({
model: "bytedance/seedance-2.0",
prompt: "Rain on a tin roof above a small noodle stall, steam rising, quiet chatter",
params: { duration_seconds: 8, aspect_ratio: "9:16", resolution: "720p", audio: true },
});
console.log(generation.outputs?.[0]?.url);FLUX 3 Video
Black Forest Labs' FLUX 3 video model. Text to video and image to video from a first and optional last frame, up to 20 seconds and 4K, with optional generated audio.
Seedance 2.5
ByteDance's Seedance video model, served through BytePlus ModelArk. Text to video, image to video from a first and optional last frame, and video guided by up to four reference images.