H3 Max Reframe
Integréieren
minimax/h3-max/reframe-video
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/minimax/h3-max/reframe-video?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}'
# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY"
const API = "https://api.doitong.com/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/minimax/h3-max/reframe-video?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/minimax/h3-max/reframe-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/lb/developers/docs/mcp)
claude mcp add --transport http doitong-models https://api.doitong.com/v1/mcp \
--header "Authorization: Bearer $DOITONG_API_KEY"
# 2. Your agent calls the "run" tool with:
{
"model_id": "minimax/h3-max/reframe-video",
"input": {
"video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
}
Rufft de H3 Max Reframe-Modell (minimax/h3-max/reframe-video) iwwer d'Doitong API op. Dokumentatioun fir Agenten: https://doitong.com/lb/developers/models/minimax/h3-max/reframe-video.md
POST https://api.doitong.com/v1/run/minimax/h3-max/reframe-video?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json
{
"video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
Wann de Äntwertstatus "queued" oder "running" ass, frot GET https://api.doitong.com/v1/requests/REQUEST_ID?wait=20 of, bis en "succeeded" ass; d'Dateie stinn an outputs[].url. POST https://api.doitong.com/v1/quote/minimax/h3-max/reframe-video mam selwechte Body gëtt de geneeë Präis virun der Ausféierung zréck.
Dateie wéi am Beispill: 0,80 $ 800 API-Kreditter Är Dateie gi virun der Ausféierung gemooss Op dëser Säit ausféieren
Ären neien API-Schlëssel. Si gëtt nëmmen elo ugewisen a steet schonn am Code an am API-Schlëssel-Feld hei drënner. Halt se geheim: Setz se ni an Code, deen an engem Browser leeft.
Op Doitong erstallt
Ëffentlech Wierker, déi d'Doitong-Communautéit mat Hailuo 03 New Turbo erstallt huet. Benotz e Prompt mat engem Klick nach eng Kéier.
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...
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...
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...
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,...
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,...
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...
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
[Global Parameters] Duration: 15 seconds. Aspect ratio: 16:9. Output as one continuous long-video generation with native timestamp-controlled beats as specified below. [Creatives Description] Based on the uploaded references: @image1 is the MAN — take his entire appearance 100% from this...
Video
Extreme close-up of a smartphone on a marble kitchen table. A text notification appears on screen. A woman's elegant hand freezes above a coffee cup. Slow push-in, warm morning light, tense atmosphere, cinematic, photorealistic, vertical 9:16. A woman speaks softly in Russian, whispering in a...
Art style: warm European aesthetic, golden hour light, soft bokeh, intimate close-ups, film grain, muted warm tones. Мужчина нажимает кнопку звонка, держа цветок. Дверь открывается, и перед ним предстает удивленная девушка. Оба замирают на месте в полном оцепенении от взаимного узнавания, не...
Art style: 3D Pixar. Каспер решительно парит навстречу Теневому Стражу, свет вокруг них усиливается, Лена наблюдает сзади. Камера остаётся неподвижной. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ FINAL STYLE ENFORCEMENT (this is the authoritative rendering directive — it overrides any style wording...
Art style: Classic Fairytale. RAPID MULTI-CUT SEQUENCE, ~5 hard cuts. Clinical top-down white light, palette stark white / deep black / pale skin. (0-1s) EXTREME CLOSE-UP: @Detective Alexander Vance's black-nitrile-gloved fingers press into the victim's pale neck. No pulse. Held, dead still....
Camera: orbit. Art style: DreamWorks-inspired. Low-angle cinematic shot of the gray wolf raising its head and howling melodically. Camera catches the golden late afternoon light catching the wolf's fur and the awe on Talisa and Elky's faces. SPOKEN LINE — AUTHORITATIVE, overrides any line quoted...
Camera: dolly out. Art style: DreamWorks-inspired. Camera slowly cranes upward and pulls backward into a wide panoramic sunset shot of the cozy cabin at the forest edge as Talisa and Elky reach the front door, with Elky cheering joyfully. SPOKEN LINE — AUTHORITATIVE, overrides any line quoted...
Art style: Ghibli-style anime illustration. She gently dries the rabbit's fur. The fire glows and sparks. The camera captures the cozy, safe atmosphere. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ FINAL STYLE ENFORCEMENT (this is the authoritative rendering directive — it overrides any style wording...
Art style: Photorealistic Cinematic Adventure Naturalism. Continue directly from the source image. Preserve Mara and Rhyss exactly as shown in the source image. Do not change their appearance, anatomy, clothing, proportions or scale. Rhyss and Mara move together upward and forward toward the...
Eng Ufro erstellen
D'Kontrolle ginn aus dem Modellschema generéiert. De Code an de Präis aktualiséiere sech, wann s du se ännerst.
/run/minimax/h3-max/reframe-video?wait=20
Präis → 0,80 $
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/minimax/h3-max/reframe-video?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}'
# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY"
const API = "https://api.doitong.com/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/minimax/h3-max/reframe-video?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/minimax/h3-max/reframe-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-max/reframe-video",
"input": {
"video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
},
"wait_seconds": 20
}
}
}
Dës Ufro ausféieren
Äre Schlëssel bleift an dësem Browser: e gëtt nëmmen un d'Doitong API geschéckt an nëmme gespäichert (localStorage), wann s du „Erënneren“ aktivéiers. En API-Schlëssel kréien
Iwwer H3 Max Reframe
Passt de Quellvideo (0.25 bis 300 Sekonnen) un e Zilcanvas un a generéiert d'Ëmgéigend. `aspect_ratio`-Optioune sinn 16:9, 9:16, 1:1, 4:3, 3:4, 21:9 an 9:21. En optionalen `prompt` leet déi nei Ëmgéigend. `resolution` ass 480p, 768p oder 1080p, woubäi 1080p aus engem nativen 768p-Reframe eropgeskaliert gëtt.
Parameteren
Schéck entweder den kanoneschen Numm oder den natierlechen Numm, net béid. Kanonesch Nimm
promptoptional
video_urlobligatoresch
video
aspect_ratiooptional
resolutionoptional
seedoptional
enable_safety_checkeroptional
Fichierparameter akzeptéieren eng ëffentlech https:// URL, eng data: URI bis zu 10 MB oder de file_url vun engem Upload. Fichieren
Output
{
"id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
"object": "request",
"model": "minimax/h3-max/reframe-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": 800,
"usd": "0.80",
"charged": 800,
"refunded": 0
},
"input": {
"video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
},
"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,
"placement": {},
"frame_count": 1,
"frames_per_second": 24,
"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.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
"cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
}
}
Output-Felder
- video
- object {url, content_type, file_name, file_size, width, height, fps, duration, num_frames}
- seed
- integer
- placement
- object
- frame_count
- integer
- frames_per_second
- integer
- expanded_prompt
- string | null
Aner Hailuo 03 New Turbo-Varianten
Méi Modeller: Video zu Video
Fir AI-Agenten: dës Säit als Markdown ass ënner https://doitong.com/lb/developers/models/minimax/h3-max/reframe-video.md. All Modeller a Guiden: https://doitong.com/developers/llms.txt