Passer au contenu

FLUX 3 Max Text to Video

Intégrer

Identifiant du modèle 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://api.doitong.ru/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://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

const API = "https://api.doitong.ru/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/blackforestlabs/flux-3-max/text-to-video?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "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
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");

import os
import requests

API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "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,
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/blackforestlabs/flux-3-max/text-to-video", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])

# 1. Connect once (Claude Code; Cursor, VS Code, Claude Desktop: https://doitong.com/fr-CA/developers/docs/mcp)
claude mcp add --transport http doitong-models https://api.doitong.ru/v1/mcp \
  --header "Authorization: Bearer $DOITONG_API_KEY"

# 2. Your agent calls the "run" tool with:
{
  "model_id": "blackforestlabs/flux-3-max/text-to-video",
  "input": {
    "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
  }
}

Appelez le modèle FLUX 3 Max Text to Video (blackforestlabs/flux-3-max/text-to-video) par l’intermédiaire de Doitong API. Documentation pour les agents : https://doitong.com/fr-CA/developers/models/blackforestlabs/flux-3-max/text-to-video.md

POST https://api.doitong.ru/v1/run/blackforestlabs/flux-3-max/text-to-video?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json

{
  "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
}

Si l’état de la réponse est "queued" ou "running", interrogez GET https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20 jusqu’à ce qu’il soit "succeeded"; les fichiers se trouvent dans outputs[].url. POST https://api.doitong.ru/v1/quote/blackforestlabs/flux-3-max/text-to-video avec le même corps renvoie le prix exact avant l’exécution.

Fichiers comme dans l’exemple: 0,425 $ 425 crédits API · ≈ 45,67 ₽ vos fichiers sont mesurés avant l’exécution L’exécuter sur cette page

Obtenir une clé API

Black Forest Labs Texte vers vidéo Audio natif5–20 sjusqu’à 1080p #long-clips#1080p

Modèle vidéo de Black Forest Labs, clips de 5 à 20 secondes avec son en 720p ou 1080p.

OpenAPI Markdown

Exemples

Sortie · ~30 s

InviteFour-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 crédits API

Invite de @umesh_ai sur X

Prix par seconde de votre vidéo de sortie

Tarification selon votre entrée

à partir de 0,0425 $ / seconde de vidéo de sortie

42,5 crédits API / seconde de vidéo de sortie · ≈ 4,57 ₽

Cette requête: 5 secondes × 0,0425 $ (720p) 0,425 $ 425 crédits API · ≈ 45,67 ₽

Exécuter · 0,425 $

Facturé uniquement en cas de succès, remboursé automatiquement en cas d’échec.

duration 5 s

resolution

Prix par niveau

720p	0,0425 $ / seconde de vidéo de sortie
1080p	0,0725 $ / seconde de vidéo de sortie

Le titre affiche le niveau le moins cher; le devis établit le prix exact de votre entrée.

Vos fichiers sont mesurés avant l’exécution (durée, résolution, fréquence d’images); le devis renvoie le prix exact et l’exécution facture exactement ce montant.

Durée habituelle: ~30 s
Point de terminaison du devis: POST /quote/{id}

Créer une requête

Les contrôles sont générés à partir du schéma du modèle. Le code et le prix se mettent à jour au fur et à mesure de vos modifications.

prompt •requis

Description textuelle de la vidéo souhaitée.

duration 5 s

Durée de la vidéo de sortie, en secondes.

resolution

Résolution de la vidéo de sortie.

aspect_ratio

Rapport hauteur-largeur de la vidéo générée; `auto` correspond à la première image, sauf si l’entrée est une invite textuelle, auquel cas 16:9 est sélectionné.

Avancé reasoning_level · seed

reasoning_level par défaut high

L’effort de raisonnement contrôle l’équilibre entre la vitesse de génération et le travail consacré par le harnais à la compréhension de l’invite : un effort accru prend plus de temps.

seed

Valeur de départ de la génération; une valeur aléatoire est utilisée si elle est omise.

POST /run/blackforestlabs/flux-3-max/text-to-video?wait=20 devis → 0,425 $

# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/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://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

const API = "https://api.doitong.ru/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/blackforestlabs/flux-3-max/text-to-video?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "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
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");

import os
import requests

API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "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,
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/blackforestlabs/flux-3-max/text-to-video", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "blackforestlabs/flux-3-max/text-to-video",
      "input": {
        "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
      },
      "wait_seconds": 20
    }
  }
}

Exécuter cette requête

Clé API

Votre clé reste dans ce navigateur : elle est envoyée uniquement au Doitong API et enregistrée dans localStorage uniquement si vous cochez Mémoriser. Mémoriser dans ce navigateur Obtenir une clé API

Créé sur Doitong

Créations publiques réalisées avec FLUX 3 Max par la communauté Doitong. Réutilisez une invite en un clic.

Créations publiques affichées : 9

Close-up portrait seorang wanita berkulit pucat berdiri setengah tubuh di dalam air berwarna lemb... — Close-up portrait seorang wanita berkulit pucat berdiri setengah tubuh di dalam air berwarna lembut kebiruan, dikelilingi bunga teratai berkelopak penuh yang bermekaran indah di permukaan air. Rambutnya pirang pucat tersanggul longgar dengan beberapa helaian tipis jatuh alami membingkai sisi...

Close-up portrait seorang wanita berkulit pucat berdiri setengah tubuh di dalam air berwarna lemb... — Close-up portrait seorang wanita berkulit pucat berdiri setengah tubuh di dalam air berwarna lembut kebiruan, dikelilingi bunga teratai berkelopak penuh yang bermekaran indah di permukaan air. Rambutnya pirang pucat tersanggul longgar dengan beberapa helaian tipis jatuh alami membingkai sisi...

Prompt Details Seorang wanita berkulit pucat berdiri setengah tubuh di dalam air berwarna lembut ... — Prompt Details Seorang wanita berkulit pucat berdiri setengah tubuh di dalam air berwarna lembut kebiruan, dikelilingi bunga teratai berkelopak penuh yang bermekaran indah di permukaan air. Rambutnya pirang pucat tersanggul longgar dengan beberapa helaian tipis jatuh alami membingkai sisi...

Seorang wanita berkulit pucat berdiri setengah tubuh di dalam air berwarna lembut kebiruan, dikel... — Seorang wanita berkulit pucat berdiri setengah tubuh di dalam air berwarna lembut kebiruan, dikelilingi bunga teratai berkelopak penuh yang bermekaran indah di permukaan air. Rambutnya pirang pucat tersanggul longgar dengan beberapa helaian tipis jatuh alami membingkai sisi wajahnya. Ia memeluk...

"Potret sinematik ultra-realistis close-up seorang anak laki-laki kecil (balita) yang sangat men... — "Potret sinematik ultra-realistis close-up seorang anak laki-laki kecil (balita) yang sangat menggemaskan dengan mata cokelat besar yang ekspresif, rambut hitam berantakan yang tebal, mengenakan kaus putih kerah henley. Dia berpose dengan kedua tangan terkatup di depan dada, menunjukkan senyum...

"Potret sinematik ultra-realistis close-up seorang anak laki-laki kecil (balita) yang sangat men... — "Potret sinematik ultra-realistis close-up seorang anak laki-laki kecil (balita) yang sangat menggemaskan dengan mata cokelat besar yang ekspresif, rambut hitam berantakan yang tebal, mengenakan kaus putih kerah henley. Dia berpose dengan kedua tangan terkatup di depan dada, menunjukkan senyum...

"Potret sinematik ultra-realistis close-up seorang anak laki-laki kecil (balita) yang sangat men... — "Potret sinematik ultra-realistis close-up seorang anak laki-laki kecil (balita) yang sangat menggemaskan dengan mata cokelat besar yang ekspresif, rambut hitam berantakan yang tebal, mengenakan kaus putih kerah henley. Dia berpose dengan kedua tangan terkatup di depan dada, menunjukkan senyum...

Foto sinematik hiper-realistis resolusi tinggi menampilkan seorang pria muda Indonesia dengan tub... — Foto sinematik hiper-realistis resolusi tinggi menampilkan seorang pria muda Indonesia dengan tubuh ramping dan proporsional, rambut hitam pendek agak acak, mengenakan jaket kulit hitam, celana riding fit, dan sepatu motor. Ia sedang melakukan aksi freestyle ekstrem dengan motor sport 500cc...

À propos de FLUX 3 Max Text to Video

FLUX 3 Max transpose l’esthétique FLUX à la vidéo : images détaillées et bien éclairées, mouvement naturel et audio généré. Il raisonne sur l’invite avant le rendu (effort élevé ou faible), prend en charge des clips de 5 à 20 secondes et huit rapports de forme de 9:16 à 21:9, en 720p ou 1080p. Une graine rend les exécutions reproductibles.

Paramètres

NomType Par défautAutorisé Description

promptrequis

Typestring

Description textuelle de la vidéo souhaitée.

durationfacultatif

Typeenum

Par défaut5

567891011121314151617181920

Durée de la vidéo de sortie, en secondes.

resolutionfacultatif

Typeenum

Par défaut720p

720p1080p

Résolution de la vidéo de sortie.

reasoning_levelfacultatif

Typeenum

Par défauthigh

lowhigh

L’effort de raisonnement contrôle l’équilibre entre la vitesse de génération et le travail consacré par le harnais à la compréhension de l’invite : un effort accru prend plus de temps.

aspect_ratiofacultatif

Typeenum

Par défautauto

auto21:92:116:94:31:13:49:16

Rapport hauteur-largeur de la vidéo générée; `auto` correspond à la première image, sauf si l’entrée est une invite textuelle, auquel cas 16:9 est sélectionné.

generate_audiofacultatif

Typeboolean

Par défauttrue

Contrôle l’inclusion d’un audio généré dans la vidéo.

seedfacultatif

Typeinteger | null

Valeur de départ de la génération; une valeur aléatoire est utilisée si elle est omise.

requis

Sortie

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://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}

Vos fichiers, votre choixChaque outputs[].url est une copie dans notre stockage : conservée indéfiniment (facturation par Go-mois) ou pendant 7 jours gratuitement, selon le réglage de votre compte ou ?storage=.

Même structure pour chaque modèletype, url, content_type, width, height et duration, pour les images, les vidéos et les fichiers audio. output est l’objet de résultat propre au modèle.

Champs de sortie

video: object {url, content_type, file_name, file_size, width, height, fps, duration, num_frames}Vidéo produite par le modèle.
seed: integerValeur de départ utilisée pendant la génération.
timings: objectDonnées temporelles excluant le développement de l’invite, le décodage et le téléversement de `inference`, qui mesure uniquement le débruitage vidéo du modèle en secondes.

Plus de modèles : Texte vers vidéo

Pour les agents IA : cette page en Markdown se trouve à https://doitong.com/fr-CA/developers/models/blackforestlabs/flux-3-max/text-to-video.md. Tous les modèles et guides : https://doitong.com/developers/llms.txt