Picsart API Platform
← All models

Seedance 2.5 Video Edit

NewPremiumHot

ByteDance · Video · Video → Video

Edit video — replace subjects, add or remove objects, restyle scenes with reference images.

Model ID: seedance-2.5-video-editWorkflow: seedance
Video InputMulti-Image InputAudio1080pSource length
Try on Playground ↗

Overview

Alongside the unified model APIs, we expose compatibility APIs that take each vendor's original parameters exactly as the vendor defines them — nothing renamed, nothing reshaped on the way through.

That makes them the shortest path onto Picsart if you already work with the vendor directly: the request bodies you've already written keep working as they are. You keep their parameter names and defaults, and you get the vendor's full parameter set rather than the subset that is shared across every model.

The cost is that a request is written for one vendor — switching models later means rewriting it, and results come back in the vendor's own shape. When you'd rather write once and change models freely, use the unified API.

Make a request

Call the workflow with ai.apis.run() in TypeScript, or hit /workflows/{workflow}/execute directly — params is passed through untouched either way.

These endpoints are addressed by workflow name rather than model id: the one in this model's header, since one model runs as one workflow. Authentication is unchanged — your Picsart API key as a bearer token (see Authentication).

ts
import { createClient, ApiRunMode } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY,
  apiUrl: 'https://api.picsart.com',
});

// Calls the 'seedance' workflow directly — params are sent as-is.
const { result, usage } = await ai.apis.run('seedance', {
  content: [
    {
      type: "text"
    }
  ]
}, {
  mode: ApiRunMode.SYNC,
});

console.log(result); // workflow-specific output
console.log(usage?.credits); // credits charged

Async (submit & poll)

This model can run longer than the sync limit (~20s). In TypeScript, ai.apis.run(…, { mode: ApiRunMode.ASYNC }) polls for you; over HTTP, submit and poll yourself.

ts
import { createClient, ApiRunMode } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY,
  apiUrl: 'https://api.picsart.com',
});

// mode: ASYNC submits the job and polls under the hood — you just await.
const { result } = await ai.apis.run('seedance', {
  content: [
    {
      type: "text"
    }
  ]
}, {
  mode: ApiRunMode.ASYNC,
});

console.log(result);

Parameters

13 parameters, sent inside params. These are the vendor's own names, so they line up one-for-one with the vendor's documentation. Required ones must be supplied; the rest fall back to their defaults.

ParameterTypeRequiredDefaultDetails
model
Model name that will be resolved to the actual endpoint
stringnoseedance_1_0_pro
seedance_1_0_proseedance_1_0_pro_fastseedance_1_5_proseedance_2_0seedance_2_0_without_moderationseedance_2_0_fastseedance_2_0_miniseedance_2_5seedance_2_5_without_moderation
content
Input content items. All models support text and image_url. v2 models also support video_url and audio_url, enabling edit-video and extend-video flows via reference_video role. Limits for v2 (2.0): max 9 images, 3 videos, 3 audios; audio cannot be the only modality. Limits for 2.5: max 30 images, 10 videos, 10 audios; audio-only input is allowed. Roles: first_frame, last_frame (v1+v2), reference_image/reference_video/reference_audio (v2 only). Asset references (asset://<id>) are accepted as URL values for v2.
ContentItem[]no——
└type
Type of content item
stringyes—
textimage_urlvideo_urlaudio_urldraft_task
└text
Text content (only when type is text)
stringno——
└image_url
Image URL object (only when type is image_url)
objectno——
└url
URL of the image
stringyes——
└video_url
Video URL object (only when type is video_url). Only supported by v2 models.
objectno——
└url
URL of the video
stringyes——
└audio_url
Audio URL object (only when type is audio_url). Only supported by v2 models.
objectno——
└url
URL of the audio
stringyes——
└draft_task
Draft task object (only when type is draft_task). seedance_2_5 only: renders the final 1080p video from a previously generated 480p draft. The final reuses the draft's prompt, inputs, ratio, duration and audio; anything else sent with it is passed to the vendor as-is, which rejects what a final does not take (other content items, ratio, duration, generate_audio, draft: true, a resolution other than 1080p). resolution defaults to 1080p.
objectno——
└id
Task id of a succeeded Seedance 2.5 draft. Valid for 7 days.
stringyes——
└video_input
Whether the draft was generated from a video input (editing / extension). Required: the vendor does not report a draft's inputs, so this is what bills the final video as video-to-video. Pass back the draft_task object a draft: true request returned, unchanged.
booleanyes——
└signature
Signature the worker issued with the draft. Required: it proves id and video_input are the ones the draft was generated with — an altered reference is rejected.
stringyes——
└role
Role of the content item (first_frame, last_frame, reference_image, reference_video, reference_audio)
stringno—
first_framelast_framereference_imagereference_videoreference_audio
draft
Draft mode, step 1 (seedance_2_5 only): generate a cheap 480p preview to check scene structure, shots and motion. resolution defaults to 480p (the vendor rejects any other). The result carries a draft_task object — pass it back unchanged within 7 days as a single { type: "draft_task", draft_task } content item (step 2) to render the final video with the same model, at 1080p. Billed as a regular 480p generation. When saved to Drive (options.drive), the file also carries the reference as its seedance~draftTask attribute (JSON-encoded) and its expiry as seedance~draftExpiresAt, so the final can be rendered from the Drive file later.
booleanno——
resolution
Video resolution (480p, 720p, 1080p, 4k). 1080p supported by seedance_1_0_pro, seedance_1_0_pro_fast, seedance_2_0 and seedance_2_5 (NOT seedance_2_0_fast, NOT seedance_2_0_mini). 4k supported by seedance_2_0 only (H.265/HEVC, 10-bit). seedance_2_5 supports 480p, 720p and 1080p. Affects billing.
stringno—
480p720p1080p4k
ratio
Video aspect ratio. "adaptive" lets the model choose based on input. For seedance_2_5, first/last-frame generation and video-to-video editing/extension tasks (a video input) require "adaptive" — the worker forces it for those (output proportions follow the input), so any explicit ratio is ignored there — unless omni_reference_task_type is set to anything but "auto", in which case the ratio is sent as-is. Text-to-video and reference-to-video keep the provided ratio.
stringno—
16:94:31:13:49:1621:9adaptive
output_format
Output video container format. seedance_2_5 only. "mp4" (default) is the general-purpose H.264/AAC container; "mov" is a professional H.264 4:4:4 / PCM container with higher color fidelity and larger files. "mp4_8bit" is an mp4 guaranteed to be 8-bit H.264: only 1080p comes back from the vendor as 10-bit H.265/HEVC (which most browsers and editors cannot decode), so at 1080p the video is re-encoded — adding processing time to the request — and at every other resolution the value changes nothing, the vendor already delivers 8-bit.
stringno—
mp4movmp4_8bit
omni_reference_task_type
Task type hint, seedance_2_5 only. Omni-reference tasks are one of three subtasks: reference-to-video, video editing and video extension, each with its own parameter constraints. "auto" (vendor default) lets the model infer the subtask from the inputs and prompt; a request incompatible with the inferred one fails asynchronously, after the task was created (InvalidParameter.TaskTypeConstraint). An explicit value makes the vendor validate that subtask's constraints at submit, rejecting a non-conforming request immediately; with an explicit value the worker also stops forcing ratio to "adaptive", so the provided ratio goes out as-is and an incompatible one fails at submit. "reference": generate a new video from reference images / videos / audio — no ratio or duration constraint. "edit": edit an original video's visuals or audio — content needs at least one reference_video of 4–30 seconds, ratio must be "adaptive" and duration -1. "extend": extend an original video forward or backward — content needs at least one reference_video and ratio must be "adaptive".
stringno—
autoreferenceeditextend
duration
Duration in seconds: 3-12 (v1), 4-15 (v2 / 2.0), 4-30 (2.5), or -1 for auto (seedance_1_5_pro and v2 only). Sent to the vendor as-is and billed as-is (charged per second). When omitted or -1, the vendor picks the length (following the source video for a video input) and billing follows the input video's duration, or the default when there is none. For seedance_2_5 editing tasks the vendor may require -1.
object | objectno——
generate_audio
Include synchronized audio. Supported by seedance_1_5_pro and v2 models. v2 defaults to true when omitted; pass false to disable. Affects billing.
booleanno——
return_last_frame
Return the last frame of the generated video as a separate image (populates last_frame_url). Supported by all models, including v2 (seedance_2_0 / seedance_2_0_fast / seedance_2_0_mini) — used for last-frame / face-chaining flows.
booleanno——
watermark
Whether to add AI generated watermark
booleannofalse—
camerafixed
Fix the camera during generation. v1 models only, ignored for v2.
booleanno——
options
Options controlling safety checks and drive integration
objectno——
└safety_checks
Safety check settings
objectno——
└enabled
Whether to run content moderation. Defaults to true.
booleanno——
└drive
Save result to Picsart Drive
objectno——
└name
File name in Picsart Drive
stringyes——
└attributes
Custom attributes to attach to the file
objectno——
└folder
Target folder in Picsart Drive
objectno——
└inputs_transformation
Input transformation settings
objectno——
└downscale_oversized_images
Whether to downscale oversized input images. Defaults to false.
booleanno——

Response

Over HTTP the output arrives inside a status envelope, at response.result. ai.apis.run() unwraps that envelope for you and resolves to { result, usage } instead. Either way the resultitself is the vendor's own shape.

json
{
  "result": {
    "video_url": "https://cdn.picsart.com/…/result.mp4",
    "last_frame_url": "https://cdn.picsart.com/…/result.jpg",
    "output_format": "…",
    "draft_task": {},
    "mimeType": "video/mp4",
    "driveFile": {}
  },
  "usage": {
    "credits": 2
  }
}