Avançar para o conteúdo

FLUX 3 Max Text to Video

Integrar

ID do modelo 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/pt-PT/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
  }
}

Chame o modelo FLUX 3 Max Text to Video (blackforestlabs/flux-3-max/text-to-video) através da Doitong API. Documentação para agentes: https://doitong.com/pt-PT/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
}

Se o estado da resposta for "queued" ou "running", consulte GET https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20 repetidamente até ficar "succeeded"; os ficheiros estão em outputs[].url. POST https://api.doitong.ru/v1/quote/blackforestlabs/flux-3-max/text-to-video com o mesmo corpo devolve o preço exato antes da execução.

Ficheiros como o exemplo: 0,425 $ 425 créditos da API · ≈ 45,67 ₽ os seus ficheiros são medidos antes da execução Executar nesta página

Obter chave de API

Black Forest Labs Texto para vídeo Áudio nativo5–20 saté 1080p #audio#long-clips#1080p

Modelo de vídeo da Black Forest Labs, com clipes de 5 a 20 segundos e som em 720p ou 1080p.

OpenAPI Markdown

Exemplos

Resultado · ~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 créditos da API

Prompt de @umesh_ai no X

Preço por segundo do seu vídeo de saída

Preço baseado na sua entrada

a partir de 0,0425 $ / segundo de vídeo de saída

42,5 créditos da API / segundo de vídeo de saída · ≈ 4,57 ₽

Este pedido: 5 segundos × 0,0425 $ (720p) 0,425 $ 425 créditos da API · ≈ 45,67 ₽

Executar · 0,425 $

Cobrado apenas em caso de sucesso; reembolsado automaticamente em caso de falha.

duration 5 s

resolution

Preço por escalão

720p	0,0425 $ / segundo de vídeo de saída
1080p	0,0725 $ / segundo de vídeo de saída

O título apresenta o escalão mais baixo; o orçamento calcula o preço da sua entrada exata.

Os seus ficheiros são medidos antes da execução (duração, resolução, taxa de fotogramas); o orçamento devolve o preço exato e a execução cobra exatamente esse valor.

Tempo habitual: ~30 s
Endpoint de cotação: POST /quote/{id}

Criar um pedido

Os controlos são gerados a partir do esquema do modelo. O código e o preço são atualizados à medida que os altera.

prompt •obrigatório

Descrição textual do vídeo pretendido.

duration 5 s

Duração do vídeo de saída, medida em segundos.

resolution

Resolução do vídeo de saída.

aspect_ratio

Proporção do vídeo gerado, com `auto` a corresponder à primeira imagem, exceto quando a entrada é um prompt de texto, caso em que seleciona 16:9.

Avançado reasoning_level · seed

reasoning_level predefinição high

O esforço de raciocínio controla o compromisso entre a velocidade de geração e o trabalho que o harness dedica à compreensão do prompt: um esforço maior demora mais tempo.

seed

Seed da geração; é utilizado um valor aleatório se for omitida.

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

Executar este pedido

Chave de API

A sua chave permanece neste navegador: é enviada apenas para a Doitong API e guardada em localStorage apenas se selecionar Lembrar. Lembrar neste navegador Obter uma chave de API

Criado na Doitong

Trabalhos públicos criados com FLUX 3 Max pela comunidade Doitong. Reutilize um prompt com um clique.

Trabalhos públicos apresentados: 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...

Sobre FLUX 3 Max Text to Video

O FLUX 3 Max traz o visual FLUX para o vídeo: frames detalhados e bem iluminados, movimento natural e áudio gerado. O modelo raciocina sobre o prompt antes da renderização (esforço alto ou baixo), suporta clipes de 5 a 20 segundos e oito proporções de 9:16 a 21:9, em 720p ou 1080p. Uma semente torna as execuções repetíveis.

Parâmetros

NomeTipo PredefiniçãoPermitido Descrição

promptobrigatório

Tipostring

Descrição textual do vídeo pretendido.

durationopcional

Tipoenum

Predefinição5

567891011121314151617181920

Duração do vídeo de saída, medida em segundos.

resolutionopcional

Tipoenum

Predefinição720p

720p1080p

Resolução do vídeo de saída.

reasoning_levelopcional

Tipoenum

Predefiniçãohigh

lowhigh

O esforço de raciocínio controla o compromisso entre a velocidade de geração e o trabalho que o harness dedica à compreensão do prompt: um esforço maior demora mais tempo.

aspect_ratioopcional

Tipoenum

Predefiniçãoauto

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

Proporção do vídeo gerado, com `auto` a corresponder à primeira imagem, exceto quando a entrada é um prompt de texto, caso em que seleciona 16:9.

generate_audioopcional

Tipoboolean

Predefiniçãotrue

Controla se o vídeo inclui áudio gerado.

seedopcional

Tipointeger | null

Seed da geração; é utilizado um valor aleatório se for omitida.

obrigatório

Resultado

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"
  }
}

Os seus ficheiros, a sua escolhaCada outputs[].url é uma cópia no nosso armazenamento: guardada para sempre (paga por GB-mês) ou durante 7 dias gratuitamente, conforme a definição da sua conta ou ?storage=.

A mesma estrutura em todos os modelostype, url, content_type, width, height e duration, tanto para imagens como para vídeo e áudio. output é o próprio objeto de resultado do modelo.

Campos do resultado

video: object {url, content_type, file_name, file_size, width, height, fps, duration, num_frames}Vídeo produzido pelo modelo.
seed: integerValor de seed utilizado durante a geração.
timings: objectDados de temporização sem a expansão do prompt, a descodificação e o carregamento incluídos em `inference`, que mede apenas a remoção de ruído do vídeo pelo modelo em segundos.

Mais modelos: Texto para vídeo

Para agentes de IA: esta página em Markdown está disponível em https://doitong.com/pt-PT/developers/models/blackforestlabs/flux-3-max/text-to-video.md. Todos os modelos e guias: https://doitong.com/developers/llms.txt