Ir 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-BR/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) por meio da Doitong API. Documentação para agentes: https://doitong.com/pt-BR/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 status da resposta for "queued" ou "running", consulte GET https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20 repetidamente até que seja "succeeded"; os arquivos estão em outputs[].url. POST https://api.doitong.ru/v1/quote/blackforestlabs/flux-3-max/text-to-video com o mesmo corpo retorna o preço exato antes da execução.

Arquivos como o exemplo: $ 0,425 425 créditos de API · ≈ ₽ 45,67 seus arquivos 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 com som em 720p ou 1080p.

OpenAPI Markdown

Exemplos

Saída · ~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: false$ 0,213 · 213 créditos de API

Prompt de @umesh_ai no X

Preço por segundo do seu vídeo de saída

Preço calculado com base na sua entrada

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

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

Esta solicitação: 5 segundos × $ 0,0425 (720p) $ 0,425 425 créditos de API · ≈ ₽ 45,67

Executar · $ 0,425

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

duration 5 s

resolution

Preço por nível

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

O título mostra o nível mais baixo; o orçamento calcula o preço exato da sua entrada.

Seus arquivos são medidos antes da execução (duração, resolução, taxa de quadros); a cotação retorna o preço exato e a execução cobra exatamente esse valor.

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

Criar uma solicitação

Os controles são gerados a partir do esquema do modelo. O código e o preço são atualizados conforme você os altera.

prompt •obrigatório

Descrição em texto do vídeo desejado.

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` correspondendo à primeira imagem, exceto quando a entrada é um prompt de texto, caso em que seleciona 16:9.

Avançado reasoning_level · seed

reasoning_level padrão high

O esforço de raciocínio controla o equilíbrio entre a velocidade de geração e o trabalho que o harness dedica à compreensão do prompt: mais esforço leva mais tempo.

seed

Seed da geração; um valor aleatório é usado se 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 esta solicitação

Chave de API

Sua chave permanece neste navegador: ela é enviada somente à Doitong API e salva (localStorage) apenas se você marcar Lembrar. Lembrar neste navegador Obter uma chave de API

Feito no Doitong

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

Trabalhos públicos exibidos: 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

FLUX 3 Max leva o visual do FLUX ao vídeo: quadros detalhados e bem iluminados, movimento natural e áudio gerado. Ele raciocina sobre o prompt antes da renderização (esforço alto ou baixo), aceita clipes de 5 a 20 segundos e oito proporções de 9:16 a 21:9, em 720p ou 1080p. Uma semente torna as execuções reproduzíveis.

Parâmetros

NomeTipo PadrãoPermitido Descrição

promptobrigatório

Tipostring

Descrição em texto do vídeo desejado.

durationopcional

Tipoenum

Padrão5

567891011121314151617181920

Duração do vídeo de saída, medida em segundos.

resolutionopcional

Tipoenum

Padrão720p

720p1080p

Resolução do vídeo de saída.

reasoning_levelopcional

Tipoenum

Padrãohigh

lowhigh

O esforço de raciocínio controla o equilíbrio entre a velocidade de geração e o trabalho que o harness dedica à compreensão do prompt: mais esforço leva mais tempo.

aspect_ratioopcional

Tipoenum

Padrãoauto

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

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

generate_audioopcional

Tipoboolean

Padrãotrue

Controla se o vídeo inclui áudio gerado.

seedopcional

Tipointeger | null

Seed da geração; um valor aleatório é usado se omitida.

obrigatório

Saída

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"
  }
}

Seus arquivos, sua escolhaCada outputs[].url é uma cópia em nosso armazenamento: mantida para sempre (cobrada por GB-mês) ou por 7 dias gratuitamente, conforme a configuração da sua conta ou ?storage=.

Mesmo formato em todos os modelostype, url, content_type, width, height e duration, para imagens, vídeos e áudios. output é o próprio objeto de resultado do modelo.

Campos da saída

video: object {url, content_type, file_name, file_size, width, height, fps, duration, num_frames}Vídeo produzido pelo modelo.
seed: integerValor da seed usada durante a geração.
timings: objectDados de tempo com a expansão do prompt, a decodificação e o upload omitidos de `inference`, que mede apenas a redução de ruído do vídeo pelo modelo em segundos.

Mais modelos: Texto para vídeo

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