Gå til indhold

FLUX 3 Max Text to Video

Integrer

Model-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"

Filer som eksemplet: 0,425 $ 425 API-kreditter dine filer måles før kørslen Kør den på denne side

Hent API-nøgle
Black Forest Labs Tekst til video Indbygget lyd5–20 sop til 1080p #audio#long-clips#1080p

Black Forest Labs' videomodel med klip på 5 til 20 sekunder med lyd i 720p eller 1080p.

Eksempler

Output · ~30 s

PromptFour-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-kreditter

Prompt fra @umesh_ai på X

Opret en anmodning

Kontrollerne genereres fra modellens skema. Koden og prisen opdateres, når du ændrer dem.

•påkrævet

Tekstbeskrivelse af den ønskede video.

duration 5 s

Længden på outputvideoen målt i sekund.

resolution

Opløsning for outputvideoen.

aspect_ratio

Den genererede videos højde-bredde-forhold, hvor `auto` matcher det første billede, medmindre inputtet er en tekstprompt; i så fald vælges 16:9.

Avanceret reasoning_level · seed
reasoning_level standard high

Reasoning-indsats styrer afvejningen mellem genereringshastighed og det arbejde, harness'et bruger på at forstå prompten: større indsats tager længere tid.

Genereringsseed; der bruges en tilfældig værdi, hvis den udelades.

POST /run/blackforestlabs/flux-3-max/text-to-video?wait=20 pris → 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"

Kør denne anmodning

Din nøgle forbliver i denne browser: Den sendes kun til Doitong API og gemmes kun i localStorage, hvis du markerer Husk. Hent en API-nøgle

Om FLUX 3 Max Text to Video

FLUX 3 Max bringer FLUX-udseendet til video: detaljerede, velbelyste billeder, naturlig bevægelse og genereret lyd. Den analyserer prompten før rendering (høj eller lav indsats), understøtter klip på 5 til 20 sekunder og otte billedformater fra 9:16 til 21:9 i 720p eller 1080p. En seed gør kørsler reproducerbare.

Parametre

NavnType StandardTilladt Beskrivelse
promptpåkrævet
Typestring
Tekstbeskrivelse af den ønskede video.
durationvalgfri
Typeenum
Standard5
567891011121314151617181920
Længden på outputvideoen målt i sekund.
resolutionvalgfri
Typeenum
Standard720p
720p1080p
Opløsning for outputvideoen.
reasoning_levelvalgfri
Typeenum
Standardhigh
lowhigh
Reasoning-indsats styrer afvejningen mellem genereringshastighed og det arbejde, harness'et bruger på at forstå prompten: større indsats tager længere tid.
aspect_ratiovalgfri
Typeenum
Standardauto
auto21:92:116:94:31:13:49:16
Den genererede videos højde-bredde-forhold, hvor `auto` matcher det første billede, medmindre inputtet er en tekstprompt; i så fald vælges 16:9.
generate_audiovalgfri
Typeboolean
Standardtrue
Styrer, om videoen indeholder genereret lyd.
seedvalgfri
Typeinteger | null
Genereringsseed; der bruges en tilfældig værdi, hvis den udelades.
påkrævet

Output

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"
  }
}
Dine filer, dit valgHver outputs[].url er en kopi på vores lagring: gemt for altid (betales pr. GB-måned) eller 7 dage gratis, afhængigt af din kontoindstilling eller ?storage=.
Samme struktur for alle modellertype, url, content_type, width, height og duration for billeder, video og lyd. output er modellens eget resultatobjekt.
Outputfelter
video
object {url, content_type, file_name, file_size, width, height, fps, duration, num_frames}Video produceret af modellen.
seed
integerSeed-værdi anvendt under genereringen.
timings
objectTidsdata, hvor promptudvidelse, dekodning og upload er udeladt fra `inference`, som kun måler modellens videodenoising i sekund.

Flere modeller: Tekst til video

Til AI-agenter: Denne side som Markdown findes på https://doitong.com/da/developers/models/blackforestlabs/flux-3-max/text-to-video.md. Alle modeller og vejledninger: https://doitong.com/developers/llms.txt