Wan 3.0

cURLPythonTypeScript

Copy

curl -X POST https://api.dev.pika.art/v1/media/alibaba/wan3.0-video/text-to-video \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "prompt": "WIDE 16:9 CINEMATIC LETTERBOX PANORAMA — twice as wide as tall, like a cinema screen. NOT square, NOT vertical. A single continuous 10-second shot that travels from above the water to below it.\nTHE SCENE. A rectangular tiled bathing pool fills the frame from the far left edge to the far right edge as a long horizontal band, seen slightly from above and square-on; the pool's tiled steps and shallow ledges run along the left and right edges as symmetrical leading lines, the far tiled wall closing the top third, the still water filling the whole lower half. One woman is submerged in the pool up to her chin, only her head above the waterline, dead centre in frame, dark hair slicked flat and wet against her scalp with a centre parting, water beading on her forehead and running down her temples, chin level, facing camera, deadpan, entirely still. The water is pale and milky at the surface, perfectly calm, unbroken but for the meniscus curving where it meets her jaw. The pool is lined edge to edge in matte glazed square ceramic tiles in a soft chalky RED — a dusty brick-rose red at a gentle, low-to-moderate saturation, exactly as soft as a pale sage green, chalky and powdery rather than vivid: NOT scarlet, NOT crimson, NOT a bright saturated red, NOT a strong primary. The same soft tone across the far wall, the steps and the ledges, with pale grout lines and a faint mottled variation in the glaze.\nTHE MOTION. One unbroken shot, no cuts. FIRST BEAT: she holds absolutely still at the surface, deadpan, chin level, the water flat around her. She draws one slow breath in, her chest lifting, and closes her mouth. SECOND BEAT: she lowers herself straight down and submerges — sinking smoothly, not falling, the waterline climbing over her mouth, over her nose, over her open eyes, over her hair, until the milky surface closes above her and seals flat again. The camera SINKS WITH HER, descending in one continuous move and passing THROUGH the waterline in the middle of the shot — a brief blurred smear of surface and spray across the lens as it crosses — and comes out underwater, now fully submerged with her. THIRD BEAT: underwater. Her face fills more of the frame, lit softly from above, hair lifting and drifting slowly around her head in the water, the red tiles of the pool walls visible behind her but diffused and desaturated by the water. She holds her breath, cheeks faintly full, eyes open and steady on the camera, still deadpan. Then she parts her lips and slowly BLOWS OUT A STREAM OF AIR — a rising column of silver bubbles of mixed sizes tumbling and wobbling upward past her cheeks and forehead towards the surface, catching the light, the last few small ones trailing after. She keeps looking at the camera the whole time. Below the surface the water is clear enough to see her face and the tiled walls softly — hazy and diffused, never opaque, never black, never murky.\nColour: soft but vibrant — never oversaturated, never desaturated or washed out. Build one complementary pairing: pale milky cool water and bare skin against the soft chalky red tile. Colours true; no cast, no teal-and-orange or stylised tint. Contrast controlled, low-to-moderate. Do not let brown, tan, beige, khaki, sepia or muddy earthy tones spread through the frame. Lighting: bright, high-key and luminous like an airy daylight studio or a clean overcast day — light-filled and open, never dark, never moody, never low-key. A large soft close source from above, carrying down through the water as soft shafts. Shadows filled so texture holds in skin and tile; shadows soft but PRESENT. No bare flash, no harsh sun, no sharp-edged shadows. Light neutral and true, never coloured for mood. Skin with real photographic texture — visible pores, fine hairs, freckles, natural variation in tone, never smoothed or retouched or plastic. Anatomy correct and believable, face correctly formed and symmetrical, eyes level. Film texture: shot on real photographic film, medium-format or 35mm, fine organic grain across the whole frame, gentle halation where bright highlights meet darker tone, filmic and analogue, never clinical, never digitally sharp — no HDR, no clarity, no over-sharpening. Natural restrained grade, blacks open, slightly creamy finish, highlights rolling off softly. Deadpan, entirely straight-faced, quiet dry wit. Elevated high-end fashion campaign film. No text, no lettering, no logos, no branding, no watermark.\nAudio: above water — quiet tiled-room reverb, a faint lap of water against tile, one clear intake of breath. As the camera crosses the surface, the sound drops abruptly into a muffled underwater world: a low pressure hum, everything distant and dulled. Then the soft burble and rush of exhaled bubbles rising and popping. No music, no dialogue, no narration.",
  "resolution": "1080p",
  "ratio": "adaptive",
  "duration": 5,
  "audio": true,
  "watermark": false
}'

{
  "id": "media_8f3a2c91-5b7d-4e0a-9c26-31d4f2a8e6b0",
  "status": "queued"
}

cURLPythonTypeScript

Copy

curl https://api.dev.pika.art/v1/media/jobs/{request_id} \
  -H "X-API-Key: YOUR_API_KEY"

{
  "id": "media_8f3a2c91-5b7d-4e0a-9c26-31d4f2a8e6b0",
  "status": "running"
}

cURLPythonTypeScript

Copy

curl https://api.dev.pika.art/v1/media/jobs/{request_id}/content \
  -H "X-API-Key: YOUR_API_KEY"

{
  "url": "https://api.dev.pika.art/v1/files/video_8f3a2c91.mp4"
}