Aqbeż għall-kontenut

MiniMax H3 Image to Video

Integra

Id tal-mudell 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://vit.doitong.com/api/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://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

const API = "https://vit.doitong.com/api/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://vit.doitong.com/api/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/mt/developers/docs/mcp)
claude mcp add --transport http doitong-models https://vit.doitong.com/api/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"
  }
}

Ċempel il-mudell MiniMax H3 Image to Video (minimax/h3/image-to-video) permezz tad-Doitong API. Dokumentazzjoni għall-aġenti: https://doitong.com/mt/developers/models/minimax/h3/image-to-video.md

POST https://vit.doitong.com/api/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"
}

Jekk l-istatus tar-rispons huwa "queued" jew "running", agħmel polling fuq GET https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20 sakemm ikun "succeeded"; il-fajls jinsabu f’outputs[].url. POST https://vit.doitong.com/api/v1/quote/minimax/h3/image-to-video bl-istess body jirritorna l-prezz eżatt qabel it-tħaddim.

Din it-talba: $0.25 250 krediti tal-API Ħaddmu f’din il-paġna

Ikseb ċavetta API

MiniMax Immaġni għal vidjo Output 4K5–15 ssa 4K #motion#first-last-frame

Janimà l-ewwel frejm, l-aħħar frejm jew it-tnejn f'klipp MiniMax H3 ta' 5 sa 15-il sekonda, sa 4K.

OpenAPI Markdown

Eżempji

Input

Output · ~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 s480P$0.25 · 250 krediti tal-API

Prompt minn @CharaspowerAI fuq X

Prezz

Prezz eżatt

minn $0.05 / sekonda

50 krediti tal-API / sekonda

5 s ≈ $0.25

Din it-talba: 5 sekondi × $0.05 $0.25 250 krediti tal-API

Ħaddem · $0.25

Iċċarġjat biss jekk jirnexxi, u rimborżat awtomatikament jekk ifalli.

duration

resolution

Prezz skont il-livell

`resolution` = `480P`	$0.05 / sekonda
`resolution` = `768P`	$0.06 / sekonda
`resolution` = `2K`	$0.13 / sekonda
`resolution` = `4K`	$0.16 / sekonda

It-titlu juri l-inqas livell; il-kwotazzjoni tikkalkula l-prezz tal-input eżatt tiegħek.

Iċċarġjat għal kull sekonda ta’ output (duration).

Ħin tipiku: ~36 s
Endpoint tal-kwotazzjoni: POST /quote/{id}

Ibni talba

Il-kontrolli jiġu ġġenerati mill-iskema tal-mudell. Il-kodiċi u l-prezz jaġġornaw hekk kif tibdilhom.

prompt •meħtieġ 595 / 50000

Istruzzjonijiet tat-test għall-ġenerazzjoni tal-vidjo.

image image_url

Waqqa’ fajl, jew

URL ta’ immaġni mhux obbligatorju li jiddefinixxi l-frejm tal-bidu u l-kanvas tal-output. Jekk jiġi pprovdut biss end_image_url, il-frejm tat-tmiem tiegħu jiddetermina l-kanvas. Mingħajr ebda immaġni, il-ġenerazzjoni tuża text-to-video b’proporzjon tal-aspett prestabbilit ta’ 16:9.

resolution

Agħżel ir-riżoluzzjoni tal-vidjo iġġenerat, b’2K u 4K miksuba permezz ta’ upscaling ta’ bażi 768P. L-għażla ta’ 480P jew 768P tuża ġenerazzjoni nattiva.

duration

Tul tal-vidjo, imkejjel f’sekondi.

Avvanzat prompt_expansion_mode · target_audio_url · end_image · seed

prompt_expansion_mode prestabbilit balanced

Sforz għar-riformulazzjoni tal-prompt qabel il-ġenerazzjoni: agħżel 'quality' għal prompt aktar rikk li jieħu sa madwar 30 sekonda, jew 'fast' għal riżultat f’madwar sekonda. B’'balanced', l-għażla ssir għal kull talba; 'disabled' jitfi l-espansjoni.

target_audio_url

Waqqa’ fajl, jew

Soundtrack alternattiv mhux obbligatorju pprovdut permezz ta’ URL HTTP(S) jew data URI base64; il-klipp irid idum mill-inqas 2 sekondi u ma jkunx akbar minn 15 MB. L-awdjo pprovdut jissostitwixxi s-soundtrack iġġenerat bl-istess veloċità ta’ daqq: it-tul żejjed jitneħħa mit-tmiem, u klipps iqsar jirċievu silenzju biex jaqblu mal-vidjo. Jista’ jsir resampling għal 96 kHz għal frekwenzi ta’ kampjunar għoljin mhux tas-soltu.

end_image end_image_url

Waqqa’ fajl, jew

URL ta’ immaġni tal-aħħar frejm mhux obbligatorju, li jista’ jintuża anke mingħajr immaġni tal-bidu. F’dik il-modalità ta’ keyframe tat-tmiem biss, din l-immaġni tiddetermina l-kanvas tal-output.

seed

Seed għall-ġenerazzjoni każwali; jekk jitħalla barra, jintgħażel wieħed b’mod każwali.

POST /run/minimax/h3/image-to-video?wait=20 kwotazzjoni → $0.25

# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/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://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

const API = "https://vit.doitong.com/api/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://vit.doitong.com/api/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
    }
  }
}

Ħaddem din it-talba

Ċavetta API

Iċ-ċavetta tiegħek tibqa’ f’dan il-browser: tintbagħat biss lid-Doitong API u tiġi ssejvjata (localStorage) biss jekk timmarka Ftakar. Ftakar f’dan il-browser Ikseb ċavetta API

Dwar MiniMax H3 Image to Video

MiniMax H3 image-to-video jieħu l-ewwel frejm, l-aħħar frejm jew it-tnejn u jimla moviment ħaj u espressiv; il-kanvas isegwi l-immaġni li tagħti. 480P jew 768P nattivi, b'upscale 2K u 4K tar-riżultat 768P, 5 sa 15-il sekonda, kitba mill-ġdid tal-prompt fakultattiva u track tal-awdjo fakultattiv biex jintuża bħala soundtrack.

Parametri

Ibgħat jew l-isem kanoniku jew l-isem nattiv, mhux it-tnejn. Ismijiet kanoniċi

IsemTip PrestabbilitPermess Deskrizzjoni

promptmeħtieġ

Tipstring

≤ 50,000 karattri

Istruzzjonijiet tat-test għall-ġenerazzjoni tal-vidjo.

durationmhux obbligatorju

Tipinteger

Prestabbilit5

5 – 15

Tul tal-vidjo, imkejjel f’sekondi.

resolutionmhux obbligatorju

Tipenum

Prestabbilit2K

480P768P2K4K

Agħżel ir-riżoluzzjoni tal-vidjo iġġenerat, b’2K u 4K miksuba permezz ta’ upscaling ta’ bażi 768P. L-għażla ta’ 480P jew 768P tuża ġenerazzjoni nattiva.

seedmhux obbligatorju

Tipinteger | null

Seed għall-ġenerazzjoni każwali; jekk jitħalla barra, jintgħażel wieħed b’mod każwali.

prompt_expansion_modemhux obbligatorju

Tipstring | null

Prestabbilitbalanced

Sforz għar-riformulazzjoni tal-prompt qabel il-ġenerazzjoni: agħżel 'quality' għal prompt aktar rikk li jieħu sa madwar 30 sekonda, jew 'fast' għal riżultat f’madwar sekonda. B’'balanced', l-għażla ssir għal kull talba; 'disabled' jitfi l-espansjoni.

target_audio_urlmhux obbligatorju

Tipurl · audio

Soundtrack alternattiv mhux obbligatorju pprovdut permezz ta’ URL HTTP(S) jew data URI base64; il-klipp irid idum mill-inqas 2 sekondi u ma jkunx akbar minn 15 MB. L-awdjo pprovdut jissostitwixxi s-soundtrack iġġenerat bl-istess veloċità ta’ daqq: it-tul żejjed jitneħħa mit-tmiem, u klipps iqsar jirċievu silenzju biex jaqblu mal-vidjo. Jista’ jsir resampling għal 96 kHz għal frekwenzi ta’ kampjunar għoljin mhux tas-soltu.

image_urlmhux obbligatorju image

Tipurl · image

URL ta’ immaġni mhux obbligatorju li jiddefinixxi l-frejm tal-bidu u l-kanvas tal-output. Jekk jiġi pprovdut biss end_image_url, il-frejm tat-tmiem tiegħu jiddetermina l-kanvas. Mingħajr ebda immaġni, il-ġenerazzjoni tuża text-to-video b’proporzjon tal-aspett prestabbilit ta’ 16:9.

end_image_urlmhux obbligatorju end_image

Tipurl · image

URL ta’ immaġni tal-aħħar frejm mhux obbligatorju, li jista’ jintuża anke mingħajr immaġni tal-bidu. F’dik il-modalità ta’ keyframe tat-tmiem biss, din l-immaġni tiddetermina l-kanvas tal-output.

meħtieġ Isem kanoniku, aċċettat ukoll

Il-parametri tal-fajls jaċċettaw URL pubbliku https://, URI data: sa 10 MB, jew file_url ta’ upload. Fajls

Output

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://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}

Il-fajls tiegħek, l-għażla tiegħekKull outputs[].url huwa kopja fil-ħażna tagħna: miżmuma għal dejjem (imħallsa għal kull GB-xahar) jew 7 ijiem b’xejn, skont l-issettjar tal-kont tiegħek jew ?storage=.

L-istess struttura fuq kull mudelltype, url, content_type, width, height u duration, kemm għall-immaġnijiet kif ukoll għall-vidjo u l-awdjo. output huwa l-oġġett tar-riżultat tal-mudell innifsu.

Oqsma tal-output

video: object {url, content_type, file_name, file_size}Vidjo prodott mill-mudell.
expanded_prompt: string | nullPrompt estiż lest għall-mudell, jew null jekk ma jkunx hemm test estiż disponibbli. Il-każijiet null huma espansjoni diżattivata, espansjoni li ma biddlet xejn, u espansjoni ttrattata internament mill-API ospitat tal-mudell.

Aktar mudelli: Immaġni għal vidjo

Għall-aġenti tal-AI: din il-paġna bħala Markdown tinsab fuq https://doitong.com/mt/developers/models/minimax/h3/image-to-video.md. Il-mudelli u l-gwidi kollha: https://doitong.com/developers/llms.txt