Text into footage,
get clips viacallback

1 · Submit · POST /v1/videos/generations

curl https://lumen.mengfanlab.top/v1/videos/generations \
  -H "Authorization: Bearer sk-lumen-•••" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2",
    "prompt": "a cat running on the grass, cinematic",
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "duration": 5
  }'

# 返回任务 id:
# { "id": "v1a2b3...", "status": "processing", "created": 1700000000 }

2 · Query status · GET /v1/videos/generations/{id}

curl https://lumen.mengfanlab.top/v1/videos/generations/v1a2b3... \
  -H "Authorization: Bearer sk-lumen-•••"

# 处理中: { "id": "...", "status": "processing" }
# 成功:   { "id": "...", "status": "succeeded", "data": [ { "url": "https://video..." } ] }
# 失败:   { "id": "...", "status": "failed", "error": { "message": "..." } }

# 首尾帧 / 参考图 / 参考视频:都传 URL,生成模式自动判定
curl https://lumen.mengfanlab.top/v1/videos/generations \
  -H "Authorization: Bearer sk-lumen-•••" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2",
    "prompt": "让画面中的角色挥手",
    "image_url": "https://your.img/first.png",
    "last_image_url": "https://your.img/last.png",
    "reference_image_urls": ["https://your.img/ref1.png"],
    "reference_video_url": "https://your.vid/ref.mp4"
  }'

• · image_url is the first frame (or first_frame_url), last_image_url is the last frame (or last_frame_url).
• · reference_image_urls is the reference image array (or reference_images); reference_video_url is the reference video (or video_url).
• · Models differ in support for first/last frame / reference image / reference video; unsupported inputs are ignored by the respective upstream. See the console model notes.

Status values: queued / processing / succeeded / failed / cancelled. On succeeded it returns data:[{url}], on failed it returns error.

Submit with a webhook

curl https://lumen.mengfanlab.top/v1/videos/generations \
  -H "Authorization: Bearer sk-lumen-•••" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2",
    "prompt": "a cat running",
    "duration": 5,
    "webhook_url": "https://your.app/callback",
    "webhook_secret": "your-secret"
  }'

What you will receive

POST https://your.app/callback
Content-Type: application/json
X-Lumen-Signature: sha256=<hmac_hex>
X-Lumen-Timestamp: 1700000000

{ "id": "v1a2b3...", "status": "succeeded", "data": [ { "url": "https://video..." } ] }

Verify (use the same secret on the raw body)

# Python: 对收到的原始 body 用同一 secret 验签
import hmac, hashlib

def verify(raw_body: bytes, signature_header: str, secret: str) -> bool:
    expected = "sha256=" + hmac.new(secret.encode(), raw_body, hashlib.sha256).hexdigest()
    return hmac.compare_digest(expected, signature_header)

• · Signature = HMAC-SHA256(webhook_secret, raw response body), as hex, placed in X-Lumen-Signature: sha256=<hex>.
• · Always verify against the raw bytes received; do not deserialize and re-serialize first.
• · Video generation takes a while, so a webhook is easier than polling; without it, use GET polling to fetch the result.