Seedance 2
Seedance 2
Seedance 2 video generation with text-to-video, image-to-video, and multimodal reference support
- Endpoint
- POST /api/v1/videos/generate
- model
- seedance2, seedance2-fast
- Output
- Video
- Credits
- from 30
Aufgabe senden
/api/v1/videos/generateParameter
modelstringErforderlich"seedance2" for Pro quality or "seedance2-fast" for Fast quality
seedance2seedance2-fastmodestringOptional"standard", "real", or "wild" rendering mode. channel is accepted as an alias.
standardrealwildtypestringOptional"text-to-video", "image-to-video", or "media-to-video" (auto-detected from media_urls/image_urls when omitted)
text-to-videoimage-to-videomedia-to-videopromptstringErforderlichText prompt (3-2500 chars)
media_urlsstring[]OptionalReference media URLs. Supports images, videos (MP4/MOV) and audio (MP3/WAV); detected by file extension. Video and audio are billed per second by their length, which is measured when you submit.
image_urlsstring[]OptionalImage-only reference URLs. media_urls takes precedence when both are provided.
input_imagestringOptionalDeprecated. Alias for image_urls[0]
aspect_ratiostringOptionalStandard16:9"1:1", "21:9", "4:3", "3:4", "16:9", or "9:16" (default: 16:9)
1:121:94:33:416:99:16durationstringOptionalStandard4"4" through "15" seconds (default: 4)
resolutionstringOptionalStandard720p"720p" or "1080p" (default: 720p). "480p" is additionally available only when mode is omitted. Resolution values select quality presets; actual encoding profiles are tuned per mode.
720p1080p480pfallbackbooleanOptionalAllow automatic service fallback when available (default behavior)
truefalseseedintegerOptional-1 to 4294967295. Fixes the generation seed for reproducibility. Supported by explicit "standard", "real", and "wild" modes, including real-mode asset:// inputs. When mode is omitted, the parameter is accepted but ignored.
Seedance prompt guide
Seedance prompts work best as concrete director instructions. Describe the subject, action, scene, camera motion, visual style and constraints, then say what each reference file is for.
- For image-to-video, the first image is the opening frame and an optional second image is the closing frame. For reference media, pass images, videos and audio in media_urls.
- Describe each reference's role in the prompt in plain words ("the supplied cup", "the camera move from the supplied video"); do not refer to files by number or id.
- For edits say "strictly edit the supplied source video"; to continue a clip say "continue from the supplied previous clip".
- For complex scenes, list the shots in order, then a style and constraint package: stable faces, natural motion, no deformation, no watermark, no logo and no subtitles unless intended.
Anfrage
curl -X POST https://www.bananapro.site/api/v1/videos/generate \
-H "Authorization: Bearer sk-your-api-key" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance2",
"mode": "standard",
"type": "text-to-video",
"prompt": "A cinematic drone shot over a futuristic coastal city at sunrise",
"aspect_ratio": "16:9",
"duration": "8",
"resolution": "1080p",
"seed": 12345
}'Antwort200
{
"success": true,
"data": {
"task_id": "task_seedance2_123",
"credits_used": 175,
"remaining_credits": 825,
"model": "seedance2",
"mode": "standard"
}
}Die credits_used-Werte in diesen Beispielen dienen nur zur Veranschaulichung. Der tatsächliche Verbrauch wird beim Senden berechnet und von der API zurückgegeben.
Aufgabe abfragen
/api/v1/videos/{task_id}status
pending- Accepted and waiting to start. Keep polling.
processing- Running. Keep polling.
completed- Finished. Read video_url; output holds the full result.
failed- Ended without a result. error_message says why and credits_refunded shows what was returned.
Poll every 5 to 10 seconds and stop at completed or failed, or register a webhook to be notified instead. Failed tasks are refunded automatically.
Anfrage
curl https://www.bananapro.site/api/v1/videos/task_abc123 \
-H "Authorization: Bearer sk-your-api-key"Antwort200
{
"success": true,
"data": {
"task_id": "task_abc123",
"model": "seedance2",
"status": "completed",
"output": { "video_url": "https://..." },
"video_url": "https://...",
"error_message": null,
"credits_used": 175,
"credits_refunded": 0,
"created_at": "2026-10-04T10:00:00.000Z",
"updated_at": "2026-10-04T10:01:12.000Z",
"completed_at": "2026-10-04T10:01:12.000Z"
},
"request_id": "req_abc123"
}Auf das Ergebnis warten
TASK_ID=task_abc123
while true; do
TASK=$(curl -s https://www.bananapro.site/api/v1/videos/$TASK_ID \
-H "Authorization: Bearer sk-your-api-key")
STATUS=$(echo "$TASK" | jq -r '.data.status')
if [ "$STATUS" = "completed" ] || [ "$STATUS" = "failed" ]; then
echo "$TASK" | jq
break
fi
sleep 10
donePreise
| Model / Resolution | 4s | 8s | 12s | 15s |
|---|---|---|---|---|
| seedance2-fast / 720p | 30 | 65 | 95 | 120 |
| seedance2 / 720p | 40 | 80 | 120 | 150 |
| seedance2 / 1080p | 90 | 175 | 265 | 330 |
Prices are for the standard and wild modes with text/image inputs. The real mode costs 1.2x before final credit rounding. Omitting mode uses a separate fixed price table with slightly different totals. Video or audio references add per-second media-reference pricing.
Funktionen
- Text-to-video generation
- Image-to-video generation
- Image, video, and audio reference inputs
- Fast and Pro model options
- Standard, real-person, and wild rendering modes
- 4-15 second outputs