Pāriet uz saturu

FLUX 3 Max Text to Video

Integrēt

Modeļa id blackforestlabs/flux-3-max/text-to-video
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/blackforestlabs/flux-3-max/text-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Four-way CCTV-style split-screen showing the same real-time event inside a convenience shop. Divide the frame into four equal security-camera views with timestamps. Top left: wide ceiling-corner view covering aisles, entrance, and cashier. Top right: overhead view above the central aisle. Bottom left: camera facing the checkout counter. Bottom right: camera near the entrance looking inward. At the 2-second mark, a customer takes a boxed item from a shelf, accidentally bumps a display, catches one falling bottle, then places the box on the checkout counter. The cashier turns, scans it, and hands over a receipt as another shopper crosses behind them. All four views must remain perfectly synchronized, showing identical people, movements, object positions, occlusions, timestamps, lighting, and physical reactions. Use realistic low-resolution CCTV footage, slight lens distortion, fixed cameras, and no cinematic camera movement.",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "generate_audio": false
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Faili, piemēram, paraugā: 0,425 $ 425 API kredīti jūsu faili tiek izmērīti pirms izpildes Izpildīt šajā lapā

Iegūt API atslēgu
Black Forest Labs Teksts uz video Vietējais audio5–20 slīdz 1080p #long-clips#1080p

Black Forest Labs videomodelis: 5 līdz 20 sekunžu klipi ar skaņu 720p vai 1080p izšķirtspējā.

Piemēri

Izvade · ~30 s

UzvedneFour-way CCTV-style split-screen showing the same real-time event inside a convenience shop. Divide the frame into four equal security-camera views with timestamps. Top left: wide ceiling-corner view covering aisles, entrance, and cashier. Top right: overhead view above the central aisle. Bottom left: camera facing the checkout counter. Bottom right: camera near the entrance looking inward. At the 2-second mark, a customer takes a boxed item from a shelf, accidentally bumps a display, catches one falling bottle, then places the box on the checkout counter. The cashier turns, scans it, and hands over a receipt as another shopper crosses behind them. All four views must remain perfectly synchronized, showing identical people, movements, object positions, occlusions, timestamps, lighting, and physical reactions. Use realistic low-resolution CCTV footage, slight lens distortion, fixed cameras, and no cinematic camera movement.

5 s720p16:9generate_audio: false0,213 $ · 213 API kredītu

X lietotāja @umesh_ai uzvedne

Izveidot pieprasījumu

Vadīklas tiek ģenerētas no modeļa shēmas. Kods un cena tiek atjaunināti, kad tos maināt.

•obligāts

Vēlamā video teksta apraksts.

duration 5 s

Izvades video ilgums sekundēs.

resolution

Izvades video izšķirtspēja.

aspect_ratio

Ģenerētā video proporcijas; `auto` atbilst pirmajam attēlam, ja vien ievade nav teksta uzvedne, kurai tiek izvēlēta 16:9.

Papildu reasoning_level · seed
reasoning_level noklusējums high

Spriešanas intensitāte nosaka kompromisu starp ģenerēšanas ātrumu un darbu, ko ietvars velta uzvednes izpratnei: lielāka intensitāte aizņem vairāk laika.

Ģenerēšanas sēkla; ja nav norādīta, tiek izmantota nejauša vērtība.

POST /run/blackforestlabs/flux-3-max/text-to-video?wait=20 cena → 0,425 $
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/blackforestlabs/flux-3-max/text-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Four-way CCTV-style split-screen showing the same real-time event inside a convenience shop. Divide the frame into four equal security-camera views with timestamps. Top left: wide ceiling-corner view covering aisles, entrance, and cashier. Top right: overhead view above the central aisle. Bottom left: camera facing the checkout counter. Bottom right: camera near the entrance looking inward. At the 2-second mark, a customer takes a boxed item from a shelf, accidentally bumps a display, catches one falling bottle, then places the box on the checkout counter. The cashier turns, scans it, and hands over a receipt as another shopper crosses behind them. All four views must remain perfectly synchronized, showing identical people, movements, object positions, occlusions, timestamps, lighting, and physical reactions. Use realistic low-resolution CCTV footage, slight lens distortion, fixed cameras, and no cinematic camera movement.",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "generate_audio": false
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Palaist šo pieprasījumu

Jūsu atslēga paliek šajā pārlūkprogrammā: tā tiek nosūtīta tikai uz Doitong API un saglabāta (localStorage) tikai tad, ja atzīmējat Atcerēties. Iegūt API atslēgu

Par FLUX 3 Max Text to Video

FLUX 3 Max pārnes FLUX izskatu uz videoklipiem: detalizēti, labi izgaismoti kadri, dabiska kustība un ģenerēts audio. Tas analizē uzvedni pirms renderēšanas (augsta vai zema intensitāte), atbalsta 5 līdz 20 sekunžu klipus un astoņas malu attiecības no 9:16 līdz 21:9, 720p vai 1080p izšķirtspējā. `seed` nodrošina atkārtojamus rezultātus.

Parametri

NosaukumsTips NoklusējumsAtļauts Apraksts
promptobligāts
Tipsstring
Vēlamā video teksta apraksts.
durationneobligāts
Tipsenum
Noklusējums5
567891011121314151617181920
Izvades video ilgums sekundēs.
resolutionneobligāts
Tipsenum
Noklusējums720p
720p1080p
Izvades video izšķirtspēja.
reasoning_levelneobligāts
Tipsenum
Noklusējumshigh
lowhigh
Spriešanas intensitāte nosaka kompromisu starp ģenerēšanas ātrumu un darbu, ko ietvars velta uzvednes izpratnei: lielāka intensitāte aizņem vairāk laika.
aspect_rationeobligāts
Tipsenum
Noklusējumsauto
auto21:92:116:94:31:13:49:16
Ģenerētā video proporcijas; `auto` atbilst pirmajam attēlam, ja vien ievade nav teksta uzvedne, kurai tiek izvēlēta 16:9.
generate_audioneobligāts
Tipsboolean
Noklusējumstrue
Nosaka, vai video ietver ģenerētu audio.
seedneobligāts
Tipsinteger | null
Ģenerēšanas sēkla; ja nav norādīta, tiek izmantota nejauša vērtība.
obligāts

Izvade

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "blackforestlabs/flux-3-max/text-to-video",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 425,
    "usd": "0.425",
    "charged": 425,
    "refunded": 0
  },
  "input": {
    "prompt": "A red panda walks along a mossy log in a sunlit forest, pauses to sniff the air, then climbs over a branch",
    "duration": 5,
    "resolution": "720p"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200,
      "width": 1024,
      "height": 768,
      "fps": 1.0,
      "duration": 5,
      "num_frames": 1
    },
    "seed": 42,
    "timings": {}
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Jūsu faili, jūsu izvēleKatrs outputs[].url ir kopija mūsu krātuvē: tiek glabāta mūžīgi (maksa par GB mēnesī) vai 7 dienas bez maksas — atbilstoši konta iestatījumam vai ?storage=.
Vienāda struktūra katram modelimtype, url, content_type, width, height un duration gan attēliem, gan video un audio. output ir paša modeļa rezultāta objekts.
Izvades lauki
video
object {url, content_type, file_name, file_size, width, height, fps, duration, num_frames}Modeļa izveidotais video.
seed
integerĢenerēšanas laikā izmantotā sēklas vērtība.
timings
objectLaika dati, kuros `inference` neietver uzvednes paplašināšanu, dekodēšanu un augšupielādi un mēra tikai video trokšņa samazināšanu modelī sekundēs.

Vairāk modeļu: Teksts uz video

AI aģentiem: šī lapa Markdown formātā ir pieejama https://doitong.com/lv/developers/models/blackforestlabs/flux-3-max/text-to-video.md. Visi modeļi un ceļveži: https://doitong.com/developers/llms.txt