Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.anyfast.ai/llms.txt

Use this file to discover all available pages before exploring further.

Seedance 2.0 Fast is ByteDance’s latest video generation model available through Anyfast API. It supports text-to-video, image-to-video, multimodal reference input, video editing, video extension, and synchronized audio generation.

​
Key capabilities

FeatureDescription
Text-to-videoGenerate video from text prompts
Image-to-video (first frame)Use an image as the first frame
Image-to-video (first + last frame)Use two images as first and last frames
Multimodal referenceCombine images, videos, and audio as references (1–9 images, up to 3 videos, up to 3 audio clips)
Video editingModify elements in an existing video using reference images
Video extensionExtend and concatenate reference videos
Audio generationAuto-generate synchronized voice, sound effects, and background music
Web searchEnhance generation with real-time internet content (text-to-video only)
Return last frameRetrieve the last frame of generated video

​
Output specifications

PropertyValue
Resolution480p, 720p, 1080p
Aspect ratio16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive
Duration4–15 seconds
Formatmp4
Frame rate24 fps

​
Workflow

1. POST /v1/video/generations  →  task_id
2. Poll GET /v1/video/generations/{task_id}  →  status
3. When status = "succeeded"  →  download video URL (valid 24 hours)

​
Examples

​
Text-to-video

curl https://www.anyfast.ai/v1/video/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-fast",
    "content": [
      {
        "type": "text",
        "text": "A cat playing piano in a sunlit room, cinematic lighting"
      }
    ],
    "generate_audio": true,
    "ratio": "16:9",
    "duration": 8
  }'

​
Multimodal reference (image + video + audio)

Reference assets in the prompt with @image1, @video1, @audio1 — numbered per media type by their order in the content array.
Important: In the content array, after the text prompt, asset items must follow the order: image → video → audio.
cURL
curl https://www.anyfast.ai/v1/video/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-fast",
    "content": [
      {
        "type": "text",
        "text": "The character from @image1 dances in the scene from @video1, with @audio1 as background music"
      },
      {
        "type": "image_url",
        "image_url": {"url": "https://example.com/character.jpg"},
        "role": "reference_image"
      },
      {
        "type": "video_url",
        "video_url": {"url": "https://example.com/clip.mp4"},
        "role": "reference_video"
      },
      {
        "type": "audio_url",
        "audio_url": {"url": "https://example.com/bgm.mp3"},
        "role": "reference_audio"
      }
    ],
    "generate_audio": true,
    "ratio": "16:9",
    "duration": 11
  }'

​
Video editing

cURL
curl https://www.anyfast.ai/v1/video/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-fast",
    "content": [
      {
        "type": "text",
        "text": "Replace the water bottle in @video1 with the perfume bottle from @image1, keep camera movement unchanged"
      },
      {
        "type": "image_url",
        "image_url": {"url": "https://example.com/perfume.jpg"},
        "role": "reference_image"
      },
      {
        "type": "video_url",
        "video_url": {"url": "https://example.com/original.mp4"},
        "role": "reference_video"
      }
    ],
    "generate_audio": true,
    "ratio": "16:9",
    "duration": 5
  }'

​
Web search enhanced (text-to-video only)

cURL
curl https://www.anyfast.ai/v1/video/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-fast",
    "content": [
      {
        "type": "text",
        "text": "Macro shot of cherry blossoms in spring, petals falling slowly"
      }
    ],
    "generate_audio": true,
    "ratio": "16:9",
    "duration": 11,
    "tools": [{"type": "web_search"}]
  }'

​
Parameters

ParameterTypeRequiredDescription
modelstringYesseedance-fast
contentarrayYesInput content array (text, image_url, video_url, audio_url items)
content[].typestringYestext, image_url, video_url, or audio_url
content[].textstringText itemsText prompt (max 500 Chinese chars / 1000 English words)
content[].image_url.urlstringImage itemsImage URL, Base64 data URI, or asset://<ID>
content[].video_url.urlstringVideo itemsVideo URL or asset://<ID> (mp4/mov, max 50 MB, 2–15s)
content[].audio_url.urlstringAudio itemsAudio URL, Base64 data URI, or asset://<ID> (wav/mp3, max 15 MB)
content[].rolestringConditionalfirst_frame, last_frame, reference_image, reference_video, reference_audio
generate_audiobooleanNoGenerate synchronized audio. Default: true
resolutionstringNo480p, 720p, or 1080p. Default: 720p
ratiostringNo16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive. Default: adaptive
durationintegerNo4–15 seconds. Default: 5
toolsarrayNo[{"type": "web_search"}] for web search (text-to-video only)
watermarkbooleanNoAdd watermark. Default: false

​
Input modes

ModeContent itemsrole values
Text-to-video1× text—
Image-to-video (first frame)text (optional) + 1× image_urlfirst_frame or omit
Image-to-video (first + last frame)text (optional) + 2× image_urlfirst_frame + last_frame
Multimodal referencetext (optional) + image/video/audioreference_image, reference_video, reference_audio
Video editingtext + image_url + video_urlreference_image + reference_video
Video extensiontext + video_url(s)reference_video
Note: First frame, first+last frame, and multimodal reference are mutually exclusive — do not mix them in the same request.

​
Referencing assets in prompts

Inside the text prompt, you can refer to media items using @<type><N> placeholders — numbered per media type by their order in the content array:
PlaceholderRefers to
@image1, @image2, …The 1st, 2nd, … image_url item
@video1, @video2, …The 1st, 2nd, … video_url item
@audio1, @audio2, …The 1st, 2nd, … audio_url item
Example: "The character from @image1 walks through the scene in @video1 with @audio1 as background".
Note: Assets in the content array must follow the order: image → video → audio. @image<N>, @video<N>, and @audio<N> references are numbered per media type by their position in the array.

​
Resolution pixel values

Resolution16:94:31:13:49:1621:9
480p864x496752x560640x640560x752496x864992x432
720p1280x7201112x834960x960834x1112720x12801470x630
1080p1920x10801664x12481440x14401248x16641080x19202208x944

API Reference

View the interactive API playground for Seedance 2.0 Fast.