Vai al contenuto

MiniMax H3 Text to Video

Integra

ID del modello minimax/h3/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/minimax/h3/text-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Create a 15-second luxury cinematic product showcase for premium wireless over-ear headphones. 0–4s: Begin with an extreme macro tracking shot moving across the soft memory-foam ear cushion, fine fabric texture, brushed-metal hinge and precision-machined controls. A narrow light band travels across the surface, revealing realistic materials against a deep black studio background. 4–8s: Pull back into a three-quarter hero view. The headphones rotate slowly above a glossy reflective pedestal. The ear cups pivot naturally while the adjustable headband extends slightly, demonstrating flexible construction and comfort. Maintain exact symmetry, stable geometry and consistent proportions. 8–12s: Transition into an elegant exploded-view reveal. The ear cushion, acoustic driver, internal sound chamber, control ring and outer shell separate smoothly in perfect alignment. Subtle luminous sound waves pulse outward from the driver while the camera performs a restrained side orbit. 12–15s: Every component reconnects seamlessly. The headphones settle into a centered front-facing hero composition as soft rim lighting defines the silhouette. Complete a gentle dolly-in toward the ear cups. Premium technology-commercial finish, controlled reflections, realistic shadows, shallow depth of field, crisp surface detail, stable product shape, no hands, no distortion, no onscreen text.",
    "duration": 5,
    "resolution": "480P",
    "aspect_ratio": "16:9"
  }'

# 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"

Questa richiesta: 0,25 $ 250 crediti API · ≈ 26,89 ₽ Esegui in questa pagina

Ottieni la chiave API
MiniMax Da testo a video Output 4K5–15 sfino a 4K #motion#soundtrack

Modello video MiniMax (Hailuo) per movimenti vivaci, da 5 a 15 secondi, fino a 4K.

Esempi

Output · ~39 s

PromptCreate a 15-second luxury cinematic product showcase for premium wireless over-ear headphones. 0–4s: Begin with an extreme macro tracking shot moving across the soft memory-foam ear cushion, fine fabric texture, brushed-metal hinge and precision-machined controls. A narrow light band travels across the surface, revealing realistic materials against a deep black studio background. 4–8s: Pull back into a three-quarter hero view. The headphones rotate slowly above a glossy reflective pedestal. The ear cups pivot naturally while the adjustable headband extends slightly, demonstrating flexible construction and comfort. Maintain exact symmetry, stable geometry and consistent proportions. 8–12s: Transition into an elegant exploded-view reveal. The ear cushion, acoustic driver, internal sound chamber, control ring and outer shell separate smoothly in perfect alignment. Subtle luminous sound waves pulse outward from the driver while the camera performs a restrained side orbit. 12–15s: Every component reconnects seamlessly. The headphones settle into a centered front-facing hero composition as soft rim lighting defines the silhouette. Complete a gentle dolly-in toward the ear cups. Premium technology-commercial finish, controlled reflections, realistic shadows, shallow depth of field, crisp surface detail, stable product shape, no hands, no distortion, no onscreen text.

5 s480P16:90,25 $ · 250 crediti API

Prompt di @LudovicCreator su X

Crea una richiesta

I controlli vengono generati dallo schema del modello. Il codice e il prezzo si aggiornano mentre li modifichi.

•obbligatorio 1382 / 50000

Istruzioni testuali per la generazione del video.

resolution

Scegli la risoluzione del video generato, con 2K e 4K ottenuti tramite upscaling di una base 768P. La scelta di 480P o 768P usa invece la generazione nativa.

aspect_ratio

Proporzioni del video di output.

Durata del video, misurata in secondi.

Avanzate prompt_expansion_mode · target_audio_url · seed
predefinito balanced

Livello di riscrittura del prompt prima della generazione: scegli 'quality' per un prompt più ricco che richiede fino a circa 30 secondi oppure 'fast' per un risultato in circa un secondo. Con 'balanced', la scelta viene effettuata per ogni richiesta; 'disabled' disattiva l'espansione.

Trascina un file oppure

Colonna sonora sostitutiva facoltativa fornita tramite un URL HTTP(S) o un URI dati base64; il clip deve durare almeno 2 secondi e non superare 15 MB. L'audio fornito sostituisce la colonna sonora generata mantenendo invariata la velocità di riproduzione: la durata in eccesso viene rimossa dalla fine e ai clip più brevi viene aggiunto silenzio per raggiungere la durata del video. Per frequenze di campionamento insolitamente elevate può essere eseguito un ricampionamento a 96 kHz.

Seed per la generazione casuale; se omesso, ne viene scelto uno casualmente.

POST /run/minimax/h3/text-to-video?wait=20 preventivo → 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/text-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Create a 15-second luxury cinematic product showcase for premium wireless over-ear headphones. 0–4s: Begin with an extreme macro tracking shot moving across the soft memory-foam ear cushion, fine fabric texture, brushed-metal hinge and precision-machined controls. A narrow light band travels across the surface, revealing realistic materials against a deep black studio background. 4–8s: Pull back into a three-quarter hero view. The headphones rotate slowly above a glossy reflective pedestal. The ear cups pivot naturally while the adjustable headband extends slightly, demonstrating flexible construction and comfort. Maintain exact symmetry, stable geometry and consistent proportions. 8–12s: Transition into an elegant exploded-view reveal. The ear cushion, acoustic driver, internal sound chamber, control ring and outer shell separate smoothly in perfect alignment. Subtle luminous sound waves pulse outward from the driver while the camera performs a restrained side orbit. 12–15s: Every component reconnects seamlessly. The headphones settle into a centered front-facing hero composition as soft rim lighting defines the silhouette. Complete a gentle dolly-in toward the ear cups. Premium technology-commercial finish, controlled reflections, realistic shadows, shallow depth of field, crisp surface detail, stable product shape, no hands, no distortion, no onscreen text.",
    "duration": 5,
    "resolution": "480P",
    "aspect_ratio": "16:9"
  }'

# 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"

Esegui questa richiesta

La tua chiave rimane in questo browser: viene inviata solo al Doitong API e salvata in localStorage solo se selezioni Ricorda. Ottieni una chiave API

Creato su Doitong

Lavori pubblici creati con MiniMax H3 dalla community di Doitong. Riutilizza un prompt con un clic.

Lavori pubblici mostrati: 16
Close-up shot of a striking model with piercing eyes and flawless skin, a white snake elegantly c... Video

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... Video

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... Video

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... Video

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... Video

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 ... Video

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... Video

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...

Video

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....

Informazioni su MiniMax H3 Text to Video

MiniMax H3 genera movimenti espressivi di personaggi e camera a partire da un prompt. Esegue il rendering nativamente a 480P o 768P; le opzioni 2K e 4K aumentano la risoluzione di un risultato 768P. Le clip durano da 5 a 15 secondi in sei rapporti d'aspetto; un riscrittore integrato opzionale del prompt offre quattro livelli di intensità e puoi fissare una tua traccia audio come colonna sonora.

Parametri

NomeTipo PredefinitoConsentiti Descrizione
promptobbligatorio
Tipostring
≤ 50.000 caratteri
Istruzioni testuali per la generazione del video.
durationfacoltativo
Tipointeger
Predefinito5
5 – 15
Durata del video, misurata in secondi.
resolutionfacoltativo
Tipoenum
Predefinito2K
480P768P2K4K
Scegli la risoluzione del video generato, con 2K e 4K ottenuti tramite upscaling di una base 768P. La scelta di 480P o 768P usa invece la generazione nativa.
seedfacoltativo
Tipointeger | null
Seed per la generazione casuale; se omesso, ne viene scelto uno casualmente.
prompt_expansion_modefacoltativo
Tipostring | null
Predefinitobalanced
Livello di riscrittura del prompt prima della generazione: scegli 'quality' per un prompt più ricco che richiede fino a circa 30 secondi oppure 'fast' per un risultato in circa un secondo. Con 'balanced', la scelta viene effettuata per ogni richiesta; 'disabled' disattiva l'espansione.
target_audio_urlfacoltativo
Tipourl · audio
Colonna sonora sostitutiva facoltativa fornita tramite un URL HTTP(S) o un URI dati base64; il clip deve durare almeno 2 secondi e non superare 15 MB. L'audio fornito sostituisce la colonna sonora generata mantenendo invariata la velocità di riproduzione: la durata in eccesso viene rimossa dalla fine e ai clip più brevi viene aggiunto silenzio per raggiungere la durata del video. Per frequenze di campionamento insolitamente elevate può essere eseguito un ricampionamento a 96 kHz.
aspect_ratiofacoltativo
Tipoenum
Predefinito16:9
21:916:94:31:13:49:16
Proporzioni del video di output.
obbligatorio

I parametri file accettano un URL pubblico https://, un URI data: fino a 10 MB oppure il file_url di un caricamento. File

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "minimax/h3/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": 250,
    "usd": "0.25",
    "charged": 250,
    "refunded": 0
  },
  "input": {
    "prompt": "A white kitten chases a butterfly across a sunlit garden, gentle tracking camera, soft afternoon light",
    "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"
  }
}
I tuoi file, la tua sceltaOgni outputs[].url è una copia nella nostra archiviazione: conservata per sempre (a pagamento per GB-mese) oppure 7 giorni gratuitamente, in base all'impostazione dell'account o a ?storage=.
Stessa struttura per ogni modellotype, url, content_type, width, height e duration, per immagini, video e audio. output è l'oggetto risultato del modello.
Campi dell'output
video
object {url, content_type, file_name, file_size}Video prodotto dal modello.
expanded_prompt
string | nullPrompt espanso pronto per il modello, oppure null se non è disponibile alcun testo espanso. I casi null sono: espansione disabilitata, espansione che non ha apportato modifiche ed espansione gestita internamente dall'API ospitata del modello.

Altri modelli: Da testo a video

Per gli agenti AI: questa pagina in Markdown è disponibile all'indirizzo https://doitong.com/it/developers/models/minimax/h3/text-to-video.md. Tutti i modelli e le guide: https://doitong.com/developers/llms.txt