تخطّي إلى المحتوى

FLUX 3 Max Text to Video

التكامل

معرّف النموذج 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/ar/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
  }
}

استدعِ نموذج FLUX 3 Max Text to Video (blackforestlabs/flux-3-max/text-to-video) عبر Doitong API. توثيق الوكلاء: https://doitong.com/ar/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
}

إذا كانت حالة الاستجابة "queued" أو "running"، فأرسل طلبات GET إلى https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20 حتى تصبح "succeeded"؛ توجد الملفات في outputs[].url. يعيد POST https://api.doitong.ru/v1/quote/blackforestlabs/flux-3-max/text-to-video مع نفس النص الأساسي السعر الدقيق قبل التشغيل.

ملفات مثل المثال: ⁨‏0.425 $⁩ 425 رصيد API · ≈ ⁨‏45.61 ₽⁩ تُقاس ملفاتك قبل التشغيل تشغيله في هذه الصفحة

الحصول على مفتاح API

Black Forest Labs من نص إلى فيديو صوت أصلي5–20 ثحتى 1080p #audio#long-clips#1080p

نموذج فيديو من Black Forest Labs، ينشئ مقاطع من 5 إلى 20 ثانية مع صوت بدقة 720p أو 1080p.

OpenAPI Markdown

أمثلة

المخرجات · ~30 ث

المطالبةFour-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 رصيد API

المطالبة من @umesh_ai على X

السعر لكل ثانية من فيديو الإخراج

السعر وفقًا لإدخالك

ابتداءً من ⁨‏0.0425 $⁩ / ثانية من فيديو المخرج

42.5 رصيد API / ثانية من فيديو المخرج · ≈ ⁨‏4.56 ₽⁩

هذا الطلب: 5 ثوانٍ × ⁨‏0.0425 $⁩ (720p) ⁨‏0.425 $⁩ 425 رصيد API · ≈ ⁨‏45.61 ₽⁩

تشغيل · ⁨‏0.425 $⁩

يتم الخصم عند النجاح فقط، وتتم إعادة المبلغ تلقائيًا عند الفشل.

duration 5 s

resolution

السعر حسب المستوى

720p	⁨‏0.0425 $⁩ / ثانية من فيديو المخرج
1080p	⁨‏0.0725 $⁩ / ثانية من فيديو المخرج

يعرض العنوان أقل مستوى؛ ويُسعّر العرض مدخلك الدقيق.

تُقاس ملفاتك قبل التشغيل (المدة والدقة ومعدل الإطارات)؛ ويُرجع عرض السعر السعر الدقيق، ويُحصّل التشغيل هذا السعر بالضبط.

الوقت المعتاد: ~30 ث
نقطة نهاية عرض السعر: POST /quote/{id}

إنشاء طلب

تُنشأ عناصر التحكم من مخطط النموذج. يتحدّث الرمز والسعر عند تغييرها.

prompt •مطلوب

وصف نصي للفيديو المطلوب.

duration 5 s

مدة الفيديو الناتج، مقاسة بالثواني.

resolution

دقة الفيديو الناتج.

aspect_ratio

نسبة عرض الفيديو المولّد إلى ارتفاعه، مع مطابقة `auto` للصورة الأولى ما لم يكن المدخل موجّهاً نصياً، حيث تختار 16:9.

متقدم reasoning_level · seed

reasoning_level الافتراضي high

تتحكم جهود الاستدلال في المفاضلة بين سرعة التوليد والعمل الذي يخصصه النظام لفهم الموجّه: تتطلب الجهود الأكبر وقتاً أطول.

seed

بذرة التوليد؛ تُستخدم قيمة عشوائية عند حذفها.

POST /run/blackforestlabs/flux-3-max/text-to-video?wait=20 عرض السعر → ⁨‏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
    }
  }
}

تشغيل هذا الطلب

مفتاح API

يبقى مفتاحك في هذا المتصفح: لا يُرسل إلا إلى Doitong API ويُحفظ في localStorage فقط إذا فعّلت خيار التذكّر. تذكّر في هذا المتصفح الحصول على مفتاح API

أُنشئت على Doitong

أعمال عامة أُنشئت باستخدام FLUX 3 Max من مجتمع Doitong. أعد استخدام موجّه بنقرة واحدة.

الأعمال العامة المعروضة: 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...

حول FLUX 3 Max Text to Video

يقدّم FLUX 3 Max مظهر FLUX إلى الفيديو: إطارات مفصّلة ومضاءة جيدًا، وحركة طبيعية وصوتًا مولّدًا. يت عامل مع الموجّه قبل التصيير (بجهد عالٍ أو منخفض)، ويدعم مقاطع من 5 إلى 20 ثانية وثماني نسب عرض إلى ارتفاع من 9:16 إلى 21:9، بدقة 720p أو 1080p. تجعل البذرة عمليات التشغيل قابلة للتكرار.

المعاملات

الاسمالنوع الافتراضيمسموح الوصف

promptمطلوب

النوعstring

وصف نصي للفيديو المطلوب.

durationاختياري

النوعenum

الافتراضي5

567891011121314151617181920

مدة الفيديو الناتج، مقاسة بالثواني.

resolutionاختياري

النوعenum

الافتراضي720p

720p1080p

دقة الفيديو الناتج.

reasoning_levelاختياري

النوعenum

الافتراضيhigh

lowhigh

تتحكم جهود الاستدلال في المفاضلة بين سرعة التوليد والعمل الذي يخصصه النظام لفهم الموجّه: تتطلب الجهود الأكبر وقتاً أطول.

aspect_ratioاختياري

النوعenum

الافتراضيauto

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

نسبة عرض الفيديو المولّد إلى ارتفاعه، مع مطابقة `auto` للصورة الأولى ما لم يكن المدخل موجّهاً نصياً، حيث تختار 16:9.

generate_audioاختياري

النوعboolean

الافتراضيtrue

تحدد ما إذا كان الفيديو يتضمن صوتاً مولّداً.

seedاختياري

النوعinteger | null

بذرة التوليد؛ تُستخدم قيمة عشوائية عند حذفها.

مطلوب

المخرجات

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"
  }
}

ملفاتك، خيارككل outputs[].url هو نسخة على تخزيننا: تُحفظ إلى الأبد (مع الدفع لكل غيغابايت-شهر) أو لمدة 7 أيام مجانًا، وفق إعداد حسابك أو ?storage=.

البنية نفسها في كل نموذجtype وurl وcontent_type وwidth وheight وduration للصور والفيديو والصوت على حد سواء. output هو كائن النتائج الخاص بالنموذج.

حقول المخرجات

video: object {url, content_type, file_name, file_size, width, height, fps, duration, num_frames}الفيديو الذي أنتجه النموذج.
seed: integerقيمة البذرة المستخدمة أثناء التوليد.
timings: objectبيانات التوقيت مع استبعاد توسيع الموجّه وفك الترميز والرفع من `inference`، الذي يقيس إزالة تشويش فيديو النموذج فقط بالثواني.

مزيد من النماذج: من نص إلى فيديو

لوكلاء الذكاء الاصطناعي: تتوفر هذه الصفحة بصيغة Markdown على https://doitong.com/ar/developers/models/blackforestlabs/flux-3-max/text-to-video.md. جميع النماذج والأدلة: https://doitong.com/developers/llms.txt