Seedance 2.0 Serverless API

 1# pip install "segmind>=1.1.0"
 2# export SEGMIND_API_KEY="YOUR_API_KEY"
 3from segmind import SegmindClient, InferenceFailed, InferenceTimeout
 4
 5# Async (v2) — recommended for long-running / video models.
 6# run() blocks up to 600s; submit_async + job.wait(timeout=...) sets a longer
 7# deadline and keeps the request_id so you can re-poll later.
 8client = SegmindClient()                      # reads SEGMIND_API_KEY
 9payload = {
10    "prompt": "Generate a 16:9 aspect ratio video featuring top attractive Asian male and female leads, created according to the following shot script:\nShot 1 | 0s–1s\nMedium shot, static camera. Camera is stable, no movement. The man and woman sit inside a red convertible, looking forward in profile, expressions cold and composed. No effects. Dark tones dominate, atmosphere heavy and somber.\nShot 2 | 1s–2s\nWide/full shot, static camera. Camera stable, no movement. The woman sits on the car door, the man leans against the car body removing his jacket, gesture bold and dramatic. Hard cut transition. Red and black contrast, full of street rebellious energy.\nShot 3 | 2s–3s\nClose shot, static camera. No movement. The male lead wears sunglasses and stares directly into the camera; the female lead lightly brushes her hair aside. Hard cut transition. Red-black tones, mood cold and fierce.\nShot 4 | 3s–4s\nExtreme close-up, static camera. Fixed position. The car's rearview mirror reflects the female lead's face, her gaze distant and dreamy. Mirror reflection effect. Cool color tones, emphasizing loneliness.\nShot 5 | 4s–5s\nMedium shot, low-angle (upward tilt), static camera. Fixed position. The male lead in a white tank top smokes a cigarette, tilts his head looking into the distance, expression indifferent. No effects. Cool gray background, mood listless and detached.\nShot 6 | 5s–7s\nMedium shot, side tracking shot. Camera moves laterally at the same speed as the vehicle, conveying a sense of motion. Both are on a night drive, the woman turns her head to look at the man, expression natural and relaxed. Background dynamic blur. Night scenery with neon lights, mood relaxed and easy.\nShot 7 | 7s–9s\nMedium shot, front-facing tracking shot. Camera retreats at vehicle speed, strong sense of forward momentum. The female lead steers with one hand and makes a gesture; the male lead lounges casually in his seat. Background car light bokeh blur. Rich colors, mood free and uninhibited.\nShot 8 | 9s–14s\nClose shot, static camera. Fixed position. The female lead tilts her head back against the seat; the male lead wears sunglasses and gazes ahead, expression distant and detached. Subtitles appear at the bottom of the frame. Red-black palette, mood returns to solitude and exhaustion.",
11    "duration": 10,
12    "resolution": "720p",
13    "aspect_ratio": "16:9",
14    "generate_audio": False,
15    "seed": 42,
16}
17job = client.submit_async("seedance-2.0", **payload)
18print(job.request_id)                         # available immediately
19try:
20    result = job.wait(timeout=900, interval=2.0)
21    print(result["status"])                  # COMPLETED
22    print(result.get("output"))              # model output (e.g. video URL)
23except InferenceTimeout as e:
24    print("still running:", e.request_id)    # re-poll later with this id
25except InferenceFailed as e:
26    print("failed:", e.detail)
27
28# Fast models (<=600s) can use the one-liner instead:
29# result = segmind.run("seedance-2.0", **payload)