API One Doc

Seedance 2.0 Video Generation

ByteDance Seedance 2.0 full series — supports text-to-video, keyframe video, reference video/audio, and face consistency enhancement.

ByteDance's Seedance 2.0 (Jimeng Video) full model series. Supports text-to-video, image-to-video (first/last frame / reference image), video reference, audio reference, and face consistency (-face variants). One of the most capable short video generation solutions available.

  • Base URL: https://apione.org
  • Endpoint: POST /v1/videos/generations
  • Authentication: Authorization: Bearer sk-xxxxxxxxxxxx
  • Result Query: GET /v1/api/result?id={task_id} (see Async Result Query)

Video generation is always asynchronous. Video links are valid for 24 hours — save them promptly.

Model Comparison

Featuredoubao-seedance-2.0doubao-seedance-2.0-fastdoubao-seedance-2.0-facedoubao-seedance-2.0-fast-face
Text-to-video
First-frame reference
Last-frame reference
First + last frame
Video reference
Audio reference
Auto audio
Face consistency
Max resolution1080p1080p1080p1080p
Use caseGeneralBulk/previewCharacter videoCharacter video (fast)

doubao-seedance-2.0 (Standard)

Most complete feature set. Supports video reference, audio reference, and auto audio generation.

Key Parameters:

FieldTypeDefaultDescription
modelstringFixed doubao-seedance-2.0
promptstringVideo description (recommended for text-to-video)
sizestringAspect ratio: 16:9 / 9:16 / 1:1 / 4:3 / 3:4 / 21:9 / adaptive
imagesarrayImage URLs (max 1), for image-to-video
durationinteger5Duration in seconds, range 4~15
metadata.generate_audiobooleanfalseAuto-generate background audio
metadata.resolutionstring720p480p / 720p / 1080p
metadata.image_with_rolesarrayRole-based image control (first_frame / last_frame / reference_image)
metadata.video_urlsarrayReference video URLs (max 1)
metadata.audio_urlsarrayReference audio URLs (max 1)

Text-to-video example:

curl --request POST \
  --url https://apione.org/v1/videos/generations \
  --header 'Authorization: Bearer sk-xxxxxxxxxxxx' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "doubao-seedance-2.0",
    "prompt": "A cat lazily lying on a sun-lit windowsill, yawning occasionally",
    "size": "16:9",
    "duration": 5,
    "metadata": {
      "generate_audio": true,
      "resolution": "1080p"
    }
  }'

First + last frame transition:

curl --request POST \
  --url https://apione.org/v1/videos/generations \
  --header 'Authorization: Bearer sk-xxxxxxxxxxxx' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "doubao-seedance-2.0",
    "prompt": "Day gradually transitions to night, lights come on",
    "size": "16:9",
    "duration": 8,
    "metadata": {
      "image_with_roles": [
        { "url": "https://example.com/daytime.jpg", "role": "first_frame" },
        { "url": "https://example.com/nighttime.jpg", "role": "last_frame" }
      ]
    }
  }'

doubao-seedance-2.0-fast

Same as standard, just replace model with doubao-seedance-2.0-fast. Faster generation, lower cost.

doubao-seedance-2.0-face / doubao-seedance-2.0-fast-face

Face consistency enhancement. Provide a clear portrait reference image in images for best results.

curl --request POST \
  --url https://apione.org/v1/videos/generations \
  --header 'Authorization: Bearer sk-xxxxxxxxxxxx' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "doubao-seedance-2.0-face",
    "prompt": "Character faces the camera and smiles, nodding gently",
    "images": ["https://example.com/portrait.jpg"],
    "size": "9:16",
    "duration": 5,
    "metadata": {
      "resolution": "1080p"
    }
  }'

On this page