Seedance 2.0 Fast 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": "Modern Rural Aesthetics, Cinematic Commercial quality, shot on Sony A7S3 or cinema camera, 4K/8K ultra-high resolution, Extreme Macro photography, natural and transparent lighting, healing ASMR atmosphere, no period drama aesthetics.\n\nScene: A well-organized modern farmhouse open-concept kitchen, lush vegetable garden visible in the background, bright sunny day.\n\nCharacter: Modern lifestyle creator, long black hair casually pinned up with a single wooden hairpin, wearing a comfortable deep-blue cotton-linen set, fresh minimal makeup, focused and serene expression.\n\nShot 1 [00:00-00:05] - The Freshness: High-definition close-up. Morning sunlight hits the plants in side-backlight. The creator's bare hands pluck a vivid red tomato covered in glistening dewdrops from a vine. Razor-sharp focus capturing the fine fuzz on the tomato's surface and a water droplet sliding down. Background is premium blurred green bokeh.\n\nShot 2 [00:05-00:10] - The Craft: Indoor kitchen stove, full of lived-in warmth yet spotlessly clean. The creator chops vegetables with practiced, fluid efficiency. Macro lens captures the blade splitting through the ingredient with juice splashing mid-air. Cut to clay stove firebox with dancing orange flames, warm and authentic light.\n\nShot 3 [00:10-00:15] - The Moment: Wide shot transitioning to medium shot. A beautifully plated home-cooked dish placed on a natural wood table in the courtyard. The creator sits quietly, tucks a loose strand of hair behind her ear, and lifts a bite with chopsticks. Steam rises slowly in backlighting. Still and serene, evoking effortless modern slow-living.",
11    "duration": 5,
12    "resolution": "720p",
13    "aspect_ratio": "16:9",
14    "generate_audio": False,
15    "seed": -1,
16}
17job = client.submit_async("seedance-2.0-fast", **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-fast", **payload)