bytedance-seedance-2-0（字节跳动种子 2 0）

ByteDance Seedance 2.0 (Fast)

ByteDance Seedance 2.0 on the EachLabs Predictions API. Seedance 2.0 generates cinematic video with native synchronized audio (sound effects, ambient sound, lip-synced speech), realistic physics, and director-level camera control.

Two model slugs:

The "Fast" tier prioritizes rapid turnaround for high-throughput pipelines while keeping the family's character consistency and physics.

When to use

• User asks for "Seedance 2.0", "ByteDance video", or wants a Seedance-style look.
• Native audio required in the same pass (dialogue, SFX, ambience) — no separate TTS/lipsync step.
• Cinematic motion, realistic physics, or director-level camera language ("slow push in", "rack focus").
• Durations of 4–15 seconds at 480p or 720p.
• Image-to-video with an end frame to control where the clip lands.

For a wider video-model comparison (Veo, Kling, Sora, Pixverse, Hailuo, etc.) see eachlabs-video-generation.

Authentication

Header: X-API-Key: <your-api-key>

Set the EACHLABS_API_KEY environment variable. Get your key at eachlabs.ai/dashboard/api-keys.

Prediction Flow

1. (Recommended) Check schema — GET https://api.eachlabs.ai/v1/model?slug=bytedance-seedance-2-0-text-to-video-fast (or the i2v slug).
2. POST https://api.eachlabs.ai/v1/prediction with model, version: "0.0.1", and input.
3. Poll GET https://api.eachlabs.ai/v1/prediction/{id} until status is "success" or "error", or use a webhook.
4. Extract the video URL from output (string).

Quick Start — Text to Video

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "bytedance-seedance-2-0-text-to-video-fast",
    "version": "0.0.1",
    "input": {
      "prompt": "Cinematic slow push-in on a lone astronaut standing at the edge of a Martian canyon at dusk, dust drifting across their boots, distant wind, subtle helmet reflections",
      "resolution": "720p",
      "duration": "6",
      "aspect_ratio": "16:9",
      "generate_audio": true
    }
  }'

Typical processing time: ~120 seconds.

Quick Start — Image to Video

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "bytedance-seedance-2-0-image-to-video-fast",
    "version": "0.0.1",
    "input": {
      "prompt": "Camera slowly pushes from wide to medium close-up as the lion roars at golden hour. Warm amber light rakes across the mane. Narrator (weathered British male, 50s): \"He has ruled this land for seven years.\"",
      "image_url": "https://your-cdn.example.com/lion.jpg",
      "resolution": "720p",
      "duration": "8",
      "aspect_ratio": "16:9",
      "generate_audio": true
    }
  }'

Typical processing time: ~150 seconds.

Start-to-end transition

Pass end_image_url to lock the final frame and let the model interpolate motion between the two:

{
  "model": "bytedance-seedance-2-0-image-to-video-fast",
  "version": "0.0.1",
  "input": {
    "prompt": "Smooth parallax zoom through the scene, crossfading into the second look",
    "image_url": "https://your-cdn.example.com/frame-start.jpg",
    "end_image_url": "https://your-cdn.example.com/frame-end.jpg",
    "duration": "6",
    "resolution": "720p"
  }
}

Polling

curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "X-API-Key: $EACHLABS_API_KEY"

Webhook (alternative to polling)

Pass "webhook_url": "https://your.host/path" in the create body. EachLabs POSTs:

{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}

status is "succeeded" or "failed". Return 2xx within 30 seconds.

Parameters (both slugs share most of these)

Pricing

Dynamic, charged per second of output video:

Audio generation does not change cost. A 6-second 720p clip ≈ $1.45; a 10-second 480p clip ≈ $1.13.

Prompt Tips

• Timeline prompting: sequence beats with time or cut words — "Wide shot: … Cut to close-up: … Finally: …". Seedance 2.0 respects temporal structure better than single-sentence prompts.
• Dialogue with native audio: write the line in quotes and describe the speaker ("Weathered British male narrator, 50s, calm authoritative voice, says: …"). Lip-sync and ambience are generated in the same pass.
• Camera language: use real film vocabulary ("slow push-in", "rack focus", "dolly left", "handheld", "crane up"). The model follows director-level cues.
• Physics cues: mention weight, momentum, and material interactions ("dust scatters as boot lands", "fabric settles after the spin") to unlock the realistic-physics behavior.

Rate Limits & Limits

Errors

Error body: {"status": "error", "message": "...", "details": "..."}

Security Constraints

• No arbitrary URL loading: image_url / end_image_url must point to your own HTTPS-reachable storage (S3, GCS, CDN). Do not forward user-pasted URLs without validation.
• No third-party API tokens: never forward provider tokens through input — authentication is exclusively via the EachLabs API key.
• Validate before calling: resolve the live request_schema via GET /v1/model?slug=<slug> before constructing input.

Parameter Reference

See references/MODELS.md for the full per-slug table with defaults and options.