Ir al contenido

MiniMax H3 Image to Video

Integrar

ID del modelo minimax/h3/image-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/minimax/h3/image-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Ultra cinematic wide shot: A vast field of burning embers stretches into darkness. Suddenly, an enormous wall of fire races across the ground, sending billions of glowing sparks into the air. The flames twist into a gigantic rotating fire vortex hundreds of feet high. Molten embers, smoke, and liquid fire spiral together, naturally forging the word \"IGNITE\" from blazing flames. The letters burn brighter and brighter before erupting into a colossal shockwave that fills the screen with fire and incandescent particles. Hollywood fire simulation, ultra-realistic VFX, blockbuster title reveal.",
    "duration": 5,
    "resolution": "480P",
    "image": "https://content.doitong.com/dev-api/2026/10/21/req_j9dik7xsuoammbgw6brdgafv/0-YyIruCJVEfXsz3wKufKD7_kmRHee8d.png"
  }'

# 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/minimax/h3/image-to-video?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "Ultra cinematic wide shot: A vast field of burning embers stretches into darkness. Suddenly, an enormous wall of fire races across the ground, sending billions of glowing sparks into the air. The flames twist into a gigantic rotating fire vortex hundreds of feet high. Molten embers, smoke, and liquid fire spiral together, naturally forging the word \"IGNITE\" from blazing flames. The letters burn brighter and brighter before erupting into a colossal shockwave that fills the screen with fire and incandescent particles. Hollywood fire simulation, ultra-realistic VFX, blockbuster title reveal.",
    "duration": 5,
    "resolution": "480P",
    "image": "https://content.doitong.com/dev-api/2026/10/21/req_j9dik7xsuoammbgw6brdgafv/0-YyIruCJVEfXsz3wKufKD7_kmRHee8d.png"
  }),
});
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": "Ultra cinematic wide shot: A vast field of burning embers stretches into darkness. Suddenly, an enormous wall of fire races across the ground, sending billions of glowing sparks into the air. The flames twist into a gigantic rotating fire vortex hundreds of feet high. Molten embers, smoke, and liquid fire spiral together, naturally forging the word \"IGNITE\" from blazing flames. The letters burn brighter and brighter before erupting into a colossal shockwave that fills the screen with fire and incandescent particles. Hollywood fire simulation, ultra-realistic VFX, blockbuster title reveal.",
    "duration": 5,
    "resolution": "480P",
    "image": "https://content.doitong.com/dev-api/2026/10/21/req_j9dik7xsuoammbgw6brdgafv/0-YyIruCJVEfXsz3wKufKD7_kmRHee8d.png",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/minimax/h3/image-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/es-ES/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": "minimax/h3/image-to-video",
  "input": {
    "prompt": "Ultra cinematic wide shot: A vast field of burning embers stretches into darkness. Suddenly, an enormous wall of fire races across the ground, sending billions of glowing sparks into the air. The flames twist into a gigantic rotating fire vortex hundreds of feet high. Molten embers, smoke, and liquid fire spiral together, naturally forging the word \"IGNITE\" from blazing flames. The letters burn brighter and brighter before erupting into a colossal shockwave that fills the screen with fire and incandescent particles. Hollywood fire simulation, ultra-realistic VFX, blockbuster title reveal.",
    "duration": 5,
    "resolution": "480P",
    "image": "https://content.doitong.com/dev-api/2026/10/21/req_j9dik7xsuoammbgw6brdgafv/0-YyIruCJVEfXsz3wKufKD7_kmRHee8d.png"
  }
}

Llama al modelo MiniMax H3 Image to Video (minimax/h3/image-to-video) a través de Doitong API. Documentación para agentes: https://doitong.com/es-ES/developers/models/minimax/h3/image-to-video.md

POST https://api.doitong.ru/v1/run/minimax/h3/image-to-video?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json

{
  "prompt": "Ultra cinematic wide shot: A vast field of burning embers stretches into darkness. Suddenly, an enormous wall of fire races across the ground, sending billions of glowing sparks into the air. The flames twist into a gigantic rotating fire vortex hundreds of feet high. Molten embers, smoke, and liquid fire spiral together, naturally forging the word \"IGNITE\" from blazing flames. The letters burn brighter and brighter before erupting into a colossal shockwave that fills the screen with fire and incandescent particles. Hollywood fire simulation, ultra-realistic VFX, blockbuster title reveal.",
  "duration": 5,
  "resolution": "480P",
  "image": "https://content.doitong.com/dev-api/2026/10/21/req_j9dik7xsuoammbgw6brdgafv/0-YyIruCJVEfXsz3wKufKD7_kmRHee8d.png"
}

Si el estado de la respuesta es "queued" o "running", consulta GET https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20 hasta que sea "succeeded"; los archivos están en outputs[].url. POST https://api.doitong.ru/v1/quote/minimax/h3/image-to-video con el mismo cuerpo devuelve el precio exacto antes de la ejecución.

Esta solicitud: 0,25 $ 250 créditos de API · ≈ 26,83 ₽ Ejecutar en esta página

Obtener clave de API

MiniMax Imagen a vídeo Salida 4K5–15 shasta 4K #motion#first-last-frame

Anima un primer fotograma, un último fotograma o ambos en un clip MiniMax H3 de 5 a 15 segundos, hasta 4K.

OpenAPI Markdown

Ejemplos

Entrada

Salida · ~36 s

PromptUltra cinematic wide shot: A vast field of burning embers stretches into darkness. Suddenly, an enormous wall of fire races across the ground, sending billions of glowing sparks into the air. The flames twist into a gigantic rotating fire vortex hundreds of feet high. Molten embers, smoke, and liquid fire spiral together, naturally forging the word "IGNITE" from blazing flames. The letters burn brighter and brighter before erupting into a colossal shockwave that fills the screen with fire and incandescent particles. Hollywood fire simulation, ultra-realistic VFX, blockbuster title reveal.

5 s480P0,25 $ · 250 créditos de API

Prompt de @CharaspowerAI en X

Precio

Precio exacto

desde 0,05 $ / segundo

50 créditos de API / segundo · ≈ 5,37 ₽

5 s ≈ 0,25 $

Esta solicitud: 5 segundos × 0,05 $ 0,25 $ 250 créditos de API · ≈ 26,83 ₽

Ejecutar · 0,25 $

Solo se cobra si la operación tiene éxito; en caso de error, se reembolsa automáticamente.

duration

resolution

Precio por nivel

`resolution` = `480P`	0,05 $ / segundo
`resolution` = `768P`	0,06 $ / segundo
`resolution` = `2K`	0,13 $ / segundo
`resolution` = `4K`	0,16 $ / segundo

El encabezado muestra el nivel más bajo; el presupuesto calcula el precio de tu entrada exacta.

Se factura por segundo de salida (duration).

Tiempo habitual: ~36 s
Endpoint de presupuesto: POST /quote/{id}

Crear una solicitud

Los controles se generan a partir del esquema del modelo. El código y el precio se actualizan al modificarlos.

prompt •obligatorio 595 / 50000

Instrucciones de texto para generar el vídeo.

image image_url

Suelta un archivo o

URL de imagen opcional que define el fotograma inicial y el lienzo de salida. Si solo se proporciona end_image_url, su fotograma final determina el lienzo. Sin ninguna imagen, la generación usa texto a vídeo con una relación de aspecto predeterminada de 16:9.

resolution

Elige la resolución del vídeo generado; 2K y 4K se obtienen ampliando una base de 768P. Elegir 480P o 768P utiliza generación nativa.

duration

Duración del vídeo, medida en segundos.

Avanzado prompt_expansion_mode · target_audio_url · end_image · seed

prompt_expansion_mode predeterminado balanced

Esfuerzo de reescritura del prompt antes de la generación: elige 'quality' para un prompt más completo que tarda hasta aproximadamente 30 segundos, o 'fast' para obtener un resultado en aproximadamente un segundo. Con 'balanced', la elección se realiza por solicitud; 'disabled' desactiva la ampliación.

target_audio_url

Suelta un archivo o

Banda sonora de reemplazo opcional proporcionada mediante una URL HTTP(S) o un URI de datos base64; el clip debe durar al menos 2 segundos y no superar los 15 MB. El audio proporcionado reemplaza la banda sonora generada a la misma velocidad de reproducción: la duración sobrante se elimina del final y los clips más cortos reciben silencio para igualar la duración del vídeo. Puede producirse un remuestreo a 96 kHz con frecuencias de muestreo inusualmente altas.

end_image end_image_url

Suelta un archivo o

URL opcional de imagen del último fotograma, utilizable incluso sin una imagen inicial. En este modo de fotograma clave final, la imagen determina el lienzo de salida.

seed

Semilla para la generación aleatoria; si se omite, se elige una al azar.

POST /run/minimax/h3/image-to-video?wait=20 presupuesto → 0,25 $

# 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/minimax/h3/image-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Ultra cinematic wide shot: A vast field of burning embers stretches into darkness. Suddenly, an enormous wall of fire races across the ground, sending billions of glowing sparks into the air. The flames twist into a gigantic rotating fire vortex hundreds of feet high. Molten embers, smoke, and liquid fire spiral together, naturally forging the word \"IGNITE\" from blazing flames. The letters burn brighter and brighter before erupting into a colossal shockwave that fills the screen with fire and incandescent particles. Hollywood fire simulation, ultra-realistic VFX, blockbuster title reveal.",
    "duration": 5,
    "resolution": "480P",
    "image": "https://content.doitong.com/dev-api/2026/10/21/req_j9dik7xsuoammbgw6brdgafv/0-YyIruCJVEfXsz3wKufKD7_kmRHee8d.png"
  }'

# 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/minimax/h3/image-to-video?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "Ultra cinematic wide shot: A vast field of burning embers stretches into darkness. Suddenly, an enormous wall of fire races across the ground, sending billions of glowing sparks into the air. The flames twist into a gigantic rotating fire vortex hundreds of feet high. Molten embers, smoke, and liquid fire spiral together, naturally forging the word \"IGNITE\" from blazing flames. The letters burn brighter and brighter before erupting into a colossal shockwave that fills the screen with fire and incandescent particles. Hollywood fire simulation, ultra-realistic VFX, blockbuster title reveal.",
    "duration": 5,
    "resolution": "480P",
    "image": "https://content.doitong.com/dev-api/2026/10/21/req_j9dik7xsuoammbgw6brdgafv/0-YyIruCJVEfXsz3wKufKD7_kmRHee8d.png"
  }),
});
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": "Ultra cinematic wide shot: A vast field of burning embers stretches into darkness. Suddenly, an enormous wall of fire races across the ground, sending billions of glowing sparks into the air. The flames twist into a gigantic rotating fire vortex hundreds of feet high. Molten embers, smoke, and liquid fire spiral together, naturally forging the word \"IGNITE\" from blazing flames. The letters burn brighter and brighter before erupting into a colossal shockwave that fills the screen with fire and incandescent particles. Hollywood fire simulation, ultra-realistic VFX, blockbuster title reveal.",
    "duration": 5,
    "resolution": "480P",
    "image": "https://content.doitong.com/dev-api/2026/10/21/req_j9dik7xsuoammbgw6brdgafv/0-YyIruCJVEfXsz3wKufKD7_kmRHee8d.png",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/minimax/h3/image-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": "minimax/h3/image-to-video",
      "input": {
        "prompt": "Ultra cinematic wide shot: A vast field of burning embers stretches into darkness. Suddenly, an enormous wall of fire races across the ground, sending billions of glowing sparks into the air. The flames twist into a gigantic rotating fire vortex hundreds of feet high. Molten embers, smoke, and liquid fire spiral together, naturally forging the word \"IGNITE\" from blazing flames. The letters burn brighter and brighter before erupting into a colossal shockwave that fills the screen with fire and incandescent particles. Hollywood fire simulation, ultra-realistic VFX, blockbuster title reveal.",
        "duration": 5,
        "resolution": "480P",
        "image": "https://content.doitong.com/dev-api/2026/10/21/req_j9dik7xsuoammbgw6brdgafv/0-YyIruCJVEfXsz3wKufKD7_kmRHee8d.png"
      },
      "wait_seconds": 20
    }
  }
}

Ejecutar esta solicitud

Clave de API

Tu clave permanece en este navegador: solo se envía a la Doitong API y solo se guarda en localStorage si marcas Recordar. Recordar en este navegador Obtener una clave de API

Creado en Doitong

Trabajos públicos creados con MiniMax H3 por la comunidad de Doitong. Reutiliza un prompt con un solo clic.

Trabajos públicos mostrados: 16

Close-up shot of a striking model with piercing eyes and flawless skin, a white snake elegantly c... — Close-up shot of a striking model with piercing eyes and flawless skin, a white snake elegantly coiled around her head and neck, its scales glistening in soft, diffused light. The camera gently zooms in, emphasizing the intricate texture of the snake’s scales and the model’s striking facial...

Animate the stickman drawings into a smooth dance animation. The simple black stick figure perfor... — Animate the stickman drawings into a smooth dance animation. The simple black stick figure performs fun rhythmic dance moves — waving its arms, bending knees, jumping lightly, spinning, and swaying side to side in time with upbeat music. Keep the white background clean and minimal. The motion...

A hyper-realistic, cinematic transformation sequence of the man in the uploaded image, sitting in... — A hyper-realistic, cinematic transformation sequence of the man in the uploaded image, sitting in meditation inside a traditional Japanese room. The atmosphere begins to tremble slightly as soft blue light flows around him. From the ground, thousands of magnetic nano-particles rise, shimmering...

A cinematic transformation video of the man. The scene begins with him standing naturally, then l... — A cinematic transformation video of the man. The scene begins with him standing naturally, then looking down at his hands as glowing holographic projections appear around his body. Mechanical parts of the Iron Man armor start assembling piece by piece with smooth animation: chest plate forming,...

An ultra-epic anime cinematic of Luffy’s greatest enemy unleashing a terrifying blind rage, rampa... — An ultra-epic anime cinematic of Luffy’s greatest enemy unleashing a terrifying blind rage, rampaging uncontrollably against nature itself. His gigantic body is surrounded by a storm of black and crimson energy, crackling with lightning that scorches the ground. His roar shakes the heavens,...

A fair-skinned red-haired woman with freckles tightly embraces a majestic white tiger with faint ... — A fair-skinned red-haired woman with freckles tightly embraces a majestic white tiger with faint reddish stripes. They remain close, perfectly synchronized in stillness. The woman blinks slowly, slightly tilting her head with a serious and intense expression. The tiger breathes gently — its...

The snowboarder is riding across massive, fluffy white clouds as if they were snow-covered mounta... — The snowboarder is riding across massive, fluffy white clouds as if they were snow-covered mountains, with dramatic lighting and deep shadows adding volume and realism. The background shows a stunning blue sky with scattered soft clouds and subtle light rays. crisp cinematic quality, vivid...

Vídeo

Используй это изображение как точный референс. Вертикальное реалистичное видео 9:16, тёплая кинематографичная ночная сцена в спальне. Полностью сохранить лица Ани и Павла, их внешность, причёски, одежду, освещение, кровать, панорамные окна и ночной город. Камера статичная, средний крупный план....

Acerca de MiniMax H3 Image to Video

MiniMax H3 image-to-video toma un primer fotograma, un último fotograma o ambos y añade movimiento dinámico y expresivo; el lienzo sigue la imagen proporcionada. 480P o 768P nativos, con escalados a 2K y 4K del resultado 768P, de 5 a 15 segundos, reescritura opcional del prompt y una pista de audio opcional que se fija como banda sonora.

Parámetros

Envía el nombre canónico o el nombre nativo, pero no ambos. Nombres canónicos

NombreTipo PredeterminadoPermitido Descripción

promptobligatorio

Tipostring

≤ 50.000 caracteres

Instrucciones de texto para generar el vídeo.

durationopcional

Tipointeger

Predeterminado5

5 – 15

Duración del vídeo, medida en segundos.

resolutionopcional

Tipoenum

Predeterminado2K

480P768P2K4K

Elige la resolución del vídeo generado; 2K y 4K se obtienen ampliando una base de 768P. Elegir 480P o 768P utiliza generación nativa.

seedopcional

Tipointeger | null

Semilla para la generación aleatoria; si se omite, se elige una al azar.

prompt_expansion_modeopcional

Tipostring | null

Predeterminadobalanced

Esfuerzo de reescritura del prompt antes de la generación: elige 'quality' para un prompt más completo que tarda hasta aproximadamente 30 segundos, o 'fast' para obtener un resultado en aproximadamente un segundo. Con 'balanced', la elección se realiza por solicitud; 'disabled' desactiva la ampliación.

target_audio_urlopcional

Tipourl · audio

Banda sonora de reemplazo opcional proporcionada mediante una URL HTTP(S) o un URI de datos base64; el clip debe durar al menos 2 segundos y no superar los 15 MB. El audio proporcionado reemplaza la banda sonora generada a la misma velocidad de reproducción: la duración sobrante se elimina del final y los clips más cortos reciben silencio para igualar la duración del vídeo. Puede producirse un remuestreo a 96 kHz con frecuencias de muestreo inusualmente altas.

image_urlopcional image

Tipourl · image

URL de imagen opcional que define el fotograma inicial y el lienzo de salida. Si solo se proporciona end_image_url, su fotograma final determina el lienzo. Sin ninguna imagen, la generación usa texto a vídeo con una relación de aspecto predeterminada de 16:9.

end_image_urlopcional end_image

Tipourl · image

URL opcional de imagen del último fotograma, utilizable incluso sin una imagen inicial. En este modo de fotograma clave final, la imagen determina el lienzo de salida.

obligatorio Nombre canónico, también aceptado

Los parámetros de archivo aceptan una URL pública https://, un URI data: de hasta 10 MB o el file_url de una subida. Archivos

Salida

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t

{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "minimax/h3/image-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": 250,
    "usd": "0.25",
    "charged": 250,
    "refunded": 0
  },
  "input": {
    "prompt": "The camera slowly pulls back as the fox runs off the path into the misty forest, fireflies scatter",
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "duration": 6,
    "resolution": "768P"
  },
  "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
    },
    "expanded_prompt": "string"
  },
  "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"
  }
}

Tus archivos, tú eligesCada outputs[].url es una copia en nuestro almacenamiento: conservada para siempre (con pago por GB-mes) o 7 días gratis, según la configuración de tu cuenta o ?storage=.

La misma estructura en todos los modelostype, url, content_type, width, height y duration, tanto para imágenes como para vídeo y audio. output es el objeto de resultado propio del modelo.

Campos de salida

video: object {url, content_type, file_name, file_size}Vídeo producido por el modelo.
expanded_prompt: string | nullPrompt ampliado listo para el modelo, o null si no hay texto ampliado disponible. Los casos null corresponden a la ampliación desactivada, a una ampliación que no produjo cambios y a una ampliación gestionada internamente por la API alojada del modelo.

Más modelos: Imagen a vídeo

Para agentes de IA: esta página en Markdown está en https://doitong.com/es-ES/developers/models/minimax/h3/image-to-video.md. Todos los modelos y guías: https://doitong.com/developers/llms.txt