Seedance 2.0

Seedance 2.0-Modelle werden über eine einheitliche, asynchrone Job-API aufgerufen. Starte einen Task mit POST /api/generate und frage dann GET /api/generate/{taskId} ab, bis er fertig ist. Diese Familie stellt 3 Endpunkte bereit.

Überblick

Jeder Endpunkt teilt sich dieselbe Hülle — nur model und die input-Felder ändern sich. Führe einen beliebigen im Playground des Modell-Markts aus.

Seedance 2.0: one slug, multiple modes

bytedance/seedance-2, -fast, and -mini share one input schema — pick a mode by which fields you send (mutually exclusive groups):

Text-to-video: prompt only (optional reference_*)
Single-frame I2V: first_frame_url + prompt with aspect_ratio adaptive
First/last: first_frame_url + last_frame_url + prompt, also adaptive; no reference_*
Omni reference: reference_image_urls + optional video/audio; use @image1, @video1, @audio1 in prompt

On direct routes: mark portraits virtual (real is equivalent) for ingest; scenes/backgrounds/products default to skip (direct URL). On success, resultUrls are /api/media/{taskId}/0.mp4 proxy links playable in CN.

Portrait reference details

On direct routes, only portrait images are uploaded to the portrait library; scenes, videos, and audio stay as direct public URLs. Pair reference_image_urls with reference_portrait_kinds per slot:virtual (portrait library — real or AI; real is equivalent), skip (background/scene — default when omitted). Use first_frame_portrait_kind / last_frame_portrait_kind for single-frame and first/last modes.

Seedance 2 Referenzmedien-Limits

Diese Werte sind öffentlich dokumentierte Validierungsregeln der derzeit an 97AI.PRO angebundenen Upstream-Schnittstelle. Sie sind keine dauerhaften offiziellen Modelllimits. Bereiche können je nach Route abweichen; maßgeblich ist die API-Antwort.

Referenzbilder

Formate: JPEG, PNG, WEBP, BMP, TIFF, GIF
Breite / Höhe: 300-6000 px
Seitenverhältnis: 0.4-2.5
Dateigröße: < 30 MB

Referenzvideos

Formate: MP4, MOV
Auflösungen: 480p, 720p
Dauer pro Datei: 2-15 s
Anzahl / Gesamtdauer: Bis zu 3 / insgesamt höchstens 15 s
Breite / Höhe: 300-6000 px
Gesamtpixel: 409600-927408
Seitenverhältnis: 0.4-2.5
Dateigröße: <= 50 MB
Bildrate: 24-60 FPS

Referenzaudio

Formate: WAV, MP3
Dauer pro Datei: 2-15 s
Anzahl / Gesamtdauer: Bis zu 3 / insgesamt höchstens 15 s
Dateigröße: <= 15 MB
Abtastrate / Kanäle: Nicht veröffentlicht
Audio-Codec: Nicht veröffentlicht

Ausgabevideo

resolution: 480p, 720p, 1080p, 4k
aspect_ratio: 1:1, 4:3, 3:4, 16:9, 9:16, 21:9, adaptive
Exakte Pixelmaße: Nicht veröffentlicht; feste Breite und Höhe sind nicht garantiert

Authentifizierung

Erstelle einen API-Schlüssel unter /api-keys und sende ihn als Bearer-Token. Anfragen aus dem Browser bei angemeldeter Sitzung funktionieren auch über das Session-Cookie.

Authorization: Bearer <YOUR_API_KEY>

Task erstellen

POST

POST https://api.lithovas.com/api/generate

Body: { "model": "<slug>", "input": { … } }

Antwort: { "taskId": "<id>", "state": "waiting" }

Ergebnis abfragen

GET

GET https://api.lithovas.com/api/generate/<taskId>

Antwort: { "taskId", "state": "waiting" | "success" | "fail", "resultUrls": [ … ], "creditsConsumed", "failMsg", "balance" }

Success response example

JSON

{
  "state": "success",
  "resultUrls": [
    "https://www.lithovas.com/api/media/task_97ai_example/0.mp4"
  ],
  "creditsConsumed": 161,
  "balance": 9958,
  "_comment": "resultUrls are first-party /api/media proxy links playable in CN; the server refreshes upstream signatures on demand."
}

Asynchron

Ein 200 von „Task erstellen“ bedeutet nur, dass der Task angenommen wurde — nicht, dass er fertig ist. Frage diesen Endpunkt ab, bis state zu success oder fail wird. Fehlgeschlagene Tasks werden nicht berechnet.

Endpunkte

Modell	Task	model slug
Seedance 2	Image to Video	bytedance/seedance-2
Seedance 2 Fast	Image to Video	bytedance/seedance-2-fast
Seedance 2 Mini	Image to Video	bytedance/seedance-2-mini

Seedance 2 · Image to Video

POSTImage to Videobytedance/seedance-2

input-Felder

promptstringerforderlich

Text prompt (max 30000 characters). Use @image1, @video1, @audio1 when reference_* fields are set.

first_frame_urlstringoptional

First-frame image URL or asset://{assetId}. Mutually exclusive with reference_* fields.

last_frame_urlstringoptional

Last-frame image URL or asset://{assetId}. Requires first_frame_url.

first_frame_portrait_kindenum<string>optional

Portrait-library route: ingest hint for first_frame_url. Default skip (direct URL). Use virtual/real to upload portraits to the asset library.

last_frame_portrait_kindenum<string>optional

Portrait-library route: ingest hint for last_frame_url. Default skip (direct URL). Use virtual/real to upload portraits to the asset library.

reference_image_urlsarray<string>optional

Reference image URLs (max 9). Mutually exclusive with strict first/last frame mode.

reference_portrait_kindsarray<string>optional

Per-image ingest hint aligned with reference_image_urls: virtual (portrait library), real (alias), skip (direct URL; default when omitted).

reference_imagesarray<object>optional

Structured reference images: [{ url, portrait: "virtual"|"real"|"skip" }]. Alternative to reference_image_urls + reference_portrait_kinds.

virtual_portraitsarray<string>optional

Portrait URLs always uploaded to the virtual portrait library before generation.

real_portraitsarray<string>optional

Portrait URLs (including real-person photos) uploaded to the virtual portrait library before generation.

reference_video_urlsarray<string>optional

Reference video URLs (max 3). Never uploaded to the asset library.

reference_audio_urlsarray<string>optional

Reference audio URLs (max 3). Never uploaded to the asset library.

generate_audiobooleanoptional

Generate synchronized audio with the video.

return_last_framebooleanoptional

Return the generated video's last frame.

resolutionenum<string>optional

Output video resolution (480p–4K).

aspect_ratioenum<string>optional

Output aspect ratio. Use adaptive for single-frame or first/last-frame I2V.

durationintegeroptional

Video duration from 4 to 15 seconds.

output_formatenum<string>optional

Video output format.

web_searchbooleanoptional

Enable online search for the generation.

nsfw_checkerbooleanoptional

Enable content safety checking (97AI relay; not forwarded to upstream output moderation).

Beispiel

cURL

curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "bytedance/seedance-2",
  "input": {
    "duration": 5,
    "generate_audio": true,
    "output_format": "mp4",
    "resolution": "720p",
    "return_last_frame": false,
    "web_search": false,
    "nsfw_checker": false,
    "prompt": "镜头缓慢推近，电影感自然光，人物回头微笑",
    "aspect_ratio": "16:9"
  }
}'

Seedance 2 Fast · Image to Video

POSTImage to Videobytedance/seedance-2-fast

input-Felder

promptstringerforderlich

Text prompt (max 30000 characters). Use @image1, @video1, @audio1 when reference_* fields are set.

first_frame_urlstringoptional

First-frame image URL or asset://{assetId}. Mutually exclusive with reference_* fields.

last_frame_urlstringoptional

Last-frame image URL or asset://{assetId}. Requires first_frame_url.

first_frame_portrait_kindenum<string>optional

Portrait-library route: ingest hint for first_frame_url. Default skip (direct URL). Use virtual/real to upload portraits to the asset library.

last_frame_portrait_kindenum<string>optional

Portrait-library route: ingest hint for last_frame_url. Default skip (direct URL). Use virtual/real to upload portraits to the asset library.

reference_image_urlsarray<string>optional

Reference image URLs (max 9). Mutually exclusive with strict first/last frame mode.

reference_portrait_kindsarray<string>optional

Per-image ingest hint aligned with reference_image_urls: virtual (portrait library), real (alias), skip (direct URL; default when omitted).

reference_imagesarray<object>optional

Structured reference images: [{ url, portrait: "virtual"|"real"|"skip" }]. Alternative to reference_image_urls + reference_portrait_kinds.

virtual_portraitsarray<string>optional

Portrait URLs always uploaded to the virtual portrait library before generation.

real_portraitsarray<string>optional

Portrait URLs (including real-person photos) uploaded to the virtual portrait library before generation.

reference_video_urlsarray<string>optional

Reference video URLs (max 3). Never uploaded to the asset library.

reference_audio_urlsarray<string>optional

Reference audio URLs (max 3). Never uploaded to the asset library.

generate_audiobooleanoptional

Generate synchronized audio with the video.

return_last_framebooleanoptional

Return the generated video's last frame.

resolutionenum<string>optional

Output video resolution (480p or 720p).

aspect_ratioenum<string>optional

Output aspect ratio. Use adaptive for single-frame or first/last-frame I2V.

durationintegeroptional

Video duration from 4 to 15 seconds.

output_formatenum<string>optional

Video output format.

web_searchbooleanoptional

Enable online search for the generation.

nsfw_checkerbooleanoptional

Enable content safety checking (97AI relay; not forwarded to upstream output moderation).

Beispiel

cURL

curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "bytedance/seedance-2-fast",
  "input": {
    "duration": 5,
    "generate_audio": true,
    "output_format": "mp4",
    "resolution": "720p",
    "return_last_frame": false,
    "web_search": false,
    "nsfw_checker": false,
    "prompt": "镜头缓慢推近，电影感自然光，人物回头微笑",
    "aspect_ratio": "16:9"
  }
}'

Seedance 2 Mini · Image to Video

POSTImage to Videobytedance/seedance-2-mini

input-Felder

promptstringerforderlich

Text prompt (max 30000 characters). Use @image1, @video1, @audio1 when reference_* fields are set.

first_frame_urlstringoptional

First-frame image URL or asset://{assetId}. Mutually exclusive with reference_* fields.

last_frame_urlstringoptional

Last-frame image URL or asset://{assetId}. Requires first_frame_url.

first_frame_portrait_kindenum<string>optional

Portrait-library route: ingest hint for first_frame_url. Default skip (direct URL). Use virtual/real to upload portraits to the asset library.

last_frame_portrait_kindenum<string>optional

Portrait-library route: ingest hint for last_frame_url. Default skip (direct URL). Use virtual/real to upload portraits to the asset library.

reference_image_urlsarray<string>optional

Reference image URLs (max 9). Mutually exclusive with strict first/last frame mode.

reference_portrait_kindsarray<string>optional

Per-image ingest hint aligned with reference_image_urls: virtual (portrait library), real (alias), skip (direct URL; default when omitted).

reference_imagesarray<object>optional

Structured reference images: [{ url, portrait: "virtual"|"real"|"skip" }]. Alternative to reference_image_urls + reference_portrait_kinds.

virtual_portraitsarray<string>optional

Portrait URLs always uploaded to the virtual portrait library before generation.

real_portraitsarray<string>optional

Portrait URLs (including real-person photos) uploaded to the virtual portrait library before generation.

reference_video_urlsarray<string>optional

Reference video URLs (max 3). Never uploaded to the asset library.

reference_audio_urlsarray<string>optional

Reference audio URLs (max 3). Never uploaded to the asset library.

generate_audiobooleanoptional

Generate synchronized audio with the video.

return_last_framebooleanoptional

Return the generated video's last frame.

resolutionenum<string>optional

Output video resolution (480p or 720p).

aspect_ratioenum<string>optional

Output aspect ratio. Use adaptive for single-frame or first/last-frame I2V.

durationintegeroptional

Video duration from 4 to 15 seconds.

output_formatenum<string>optional

Video output format.

web_searchbooleanoptional

Enable online search for the generation.

nsfw_checkerbooleanoptional

Enable content safety checking (97AI relay; not forwarded to upstream output moderation).

Beispiel

cURL

curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "bytedance/seedance-2-mini",
  "input": {
    "duration": 5,
    "generate_audio": true,
    "output_format": "mp4",
    "resolution": "720p",
    "return_last_frame": false,
    "web_search": false,
    "nsfw_checker": false,
    "prompt": "镜头缓慢推近，电影感自然光，人物回头微笑",
    "aspect_ratio": "16:9"
  }
}'

Seedance 2.0 mode examples

Live-aligned examples below. One model slug switches modes by field groups; swap the model to bytedance/seedance-2-fast or -mini for other tiers.

Image-to-video (portrait + virtual)

cURL

curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "bytedance/seedance-2",
  "input": {
    "duration": 5,
    "generate_audio": true,
    "output_format": "mp4",
    "resolution": "720p",
    "return_last_frame": false,
    "web_search": false,
    "nsfw_checker": false,
    "prompt": "镜头缓慢推近，人物回头微笑，自然光",
    "first_frame_url": "https://frw-images.aiaipic.win/users/3514640099037941760/ai_generated/20260818/038f9f68-004f-4017-a09d-74b3da84e569.png",
    "first_frame_portrait_kind": "virtual",
    "aspect_ratio": "adaptive"
  }
}'

First / last frame (scene skip + adaptive)

cURL

curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "bytedance/seedance-2",
  "input": {
    "duration": 5,
    "generate_audio": true,
    "output_format": "mp4",
    "resolution": "480p",
    "return_last_frame": false,
    "web_search": false,
    "nsfw_checker": false,
    "prompt": "从首帧平滑过渡到尾帧，电影感运镜",
    "first_frame_url": "https://frw-images.aiaipic.win/users/3492453287637028864/image/20260805/c743c3df-581f-4e3f-9c8d-01029926bcfa_thumb.jpg",
    "first_frame_portrait_kind": "skip",
    "last_frame_url": "https://frw-images.aiaipic.win/users/3492453287637028864/image/20260805/9abd34e1-1f37-44ed-b482-386a44febf6a_thumb.jpg",
    "last_frame_portrait_kind": "skip",
    "aspect_ratio": "adaptive"
  }
}'

Omni reference (portrait virtual + scene skip)

cURL

curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "bytedance/seedance-2",
  "input": {
    "duration": 5,
    "generate_audio": true,
    "output_format": "mp4",
    "resolution": "720p",
    "return_last_frame": false,
    "web_search": false,
    "nsfw_checker": false,
    "prompt": " @image1与 @image2在 @image3的场景中，参考 @video1的运镜，背景音乐参考 @audio1",
    "aspect_ratio": "16:9",
    "reference_image_urls": [
      "https://frw-images.aiaipic.win/users/3514640099037941760/ai_generated/20260818/038f9f68-004f-4017-a09d-74b3da84e569.png",
      "https://frw-images.aiaipic.win/users/3514640099037941760/image/20260819/fb280368-8f54-41eb-aacf-cee1c189b29b.png"
    ],
    "reference_portrait_kinds": [
      "virtual",
      "skip"
    ],
    "reference_video_urls": [
      "https://frw-images.aiaipic.win/users/3492453287637028864/video/20260818/3524765235086888960.mp4"
    ],
    "reference_audio_urls": [
      "https://frw-images.aiaipic.win/users/3492453287637028864/audio/20260818/3524725649950380032.mp3"
    ]
  }
}'