Video

Seedance 2.5 video

Seedance 2.5 — geração de vídeo com áudio sincronizado, referências de imagem, vídeo e áudio. 480p/720p/1080p, 4–30s.

Category: Create · seedance-2-5

How to use & limits

Three modes: text-to-video, image-to-video (first/last frame) and multimodal reference (images, videos, audio).
Up to 30 seconds in one continuous shot — twice Seedance 2.
image_urls (up to 2, first/last frame) is mutually exclusive with any reference_* field.
reference_image_urls: up to 30; reference_video_urls: up to 10; reference_audio_urls: up to 10.
In reference mode the total files (image+video+audio) stays ≤50; cite them in the prompt as @Image1, @Video1, @Audio1.
Resolution: 480p or 720p; integer duration 4–30s; optional audio.

Capabilities

What this model supports, straight from the schema — no pricing, no infrastructure detail.

Capability	Value
`video_edit` Video edit	—
`featuredModes` FeaturedModes	create
`text_to_video` Text-to-video	Yes
`image_to_video` Image-to-video	Yes
`audio_generation` Audio generation	Yes
`first_last_frame` First + last frame	Yes
`max_prompt_length` Max prompt length	20000
`reference_to_video` Reference-to-video	Yes
`multimodal_reference` Multimodal reference	Yes

Parameters

Fields accepted in params (or first-class, where applicable) for POST /generations.

Name	Label	Type	Required	Default	Options	Min / Max	Description
`prompt`	Prompt	textarea	Required	—	—	—	Video description. Cite references as @Image1, @Video1, @Audio1.
`image_urls`	Image references	multi_select	Optional	—	—	— – 2	Up to 2 images (first/last frame); excludes the reference_* fields.
`reference_image_urls`	Reference images	multi_select	Optional	—	—	— – 30	Up to 30 reference images; excludes image_urls.
`reference_video_urls`	Reference videos	multi_select	Optional	—	—	— – 10	Up to 10 reference videos; excludes image_urls.
`reference_audio_urls`	Reference audio	multi_select	Optional	—	—	— – 10	Up to 10 audio files (reference audio optional).
`resolution`	Resolution	select	Required	720p	480p · 720p	—	Resolution: 480p or 720p.
`aspect_ratio`	Aspect ratio	select	Optional	16:9	auto · 21:9 · 16:9 · 4:3 · 1:1 · 3:4 · 9:16	—	Aspect ratio: auto (default), 1:1, 21:9, 4:3, 3:4, 16:9 or 9:16.
`duration`	Duration	number	Required	5	—	4 – 30	Duration in seconds, integer 4–30.
`generate_audio`	Generate audio	boolean	Optional	false	—	—	Generates an audio track with the video.

Example request

bash

curl -X POST https://caranguejo.art/api/v1/dev/generations \
  -H "Authorization: Bearer $CK" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedance-2-5",
  "prompt": "A 20-second continuous take moving through a night market, handheld camera, steam rising from the stalls.",
  "params": {
    "resolution": "720p",
    "duration": 20,
    "aspect_ratio": "16:9",
    "generate_audio": true
  }
}'

javascript

const res = await fetch("https://caranguejo.art/api/v1/dev/generations", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + process.env.CK,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "seedance-2-5",
    "prompt": "A 20-second continuous take moving through a night market, handheld camera, steam rising from the stalls.",
    "params": {
      "resolution": "720p",
      "duration": 20,
      "aspect_ratio": "16:9",
      "generate_audio": true
    }
  }),
});
const { data } = await res.json();

Example response

json

{
  "id": "9f0c1a7e-…",
  "object": "generation",
  "model": "seedance-2-5",
  "type": "video",
  "status": "completed",
  "output": {
    "assets": [
      {
        "url": "https://media.caranguejo.art/outputs/example.mp4",
        "type": "video"
      }
    ]
  }
}

The job's real cost is returned as credits_charged on the completed response — check GET /balance for the account balance.

Common errors for this job type:

`insufficient_credits`	Account balance can't cover the job cost.
`content_policy_violation`	Prompt or media rejected by content policy.
`generation_timeout`	The job exceeded the maximum processing time.
`rate_limited`	Too many requests per minute.
`invalid_input`	A required parameter is missing or outside the model's schema.
`generation_failed`	Generic processing failure.