H3 Max Reference to Video
Whakauru
minimax/h3-max/reference-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-max/reference-to-video?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"prompt_expansion_mode": "balanced"
}'
# 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 $DOITONG_API_KEY"
const API = "https://vit.doitong.com/api/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/minimax/h3-max/reference-to-video?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"prompt_expansion_mode": "balanced"
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://vit.doitong.com/api/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"prompt_expansion_mode": "balanced",
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/minimax/h3-max/reference-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/mi/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-max/reference-to-video",
"input": {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"prompt_expansion_mode": "balanced"
}
}
Karangahia te tauira H3 Max Reference to Video (minimax/h3-max/reference-to-video) mā te Doitong API. Tuhinga mō ngā āpiha: https://doitong.com/mi/developers/models/minimax/h3-max/reference-to-video.md
POST https://vit.doitong.com/api/v1/run/minimax/h3-max/reference-to-video?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json
{
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"prompt_expansion_mode": "balanced"
}
Mēnā ko "queued" "running" rānei te tūnga whakautu, uiuitia GET https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20 kia "succeeded"; kei outputs[].url ngā kōnae. Ko POST https://vit.doitong.com/api/v1/quote/minimax/h3-max/reference-to-video me taua tinana anō ka whakahoki i te utu tika i mua i te whakahaere.
Ngā kōnae pēnei i te tauira: $ 0.40 400 whiwhinga API ka inea ō kōnae i mua i te whakahaere Whakahaerehia ki tēnei whārangi
Tō kī API hou. Ka whakaaturia ināianei anake, ā, kua whakaurua kētia ki te waehere me te āpure kī API kei raro. Me huna: kaua rawa e waiho ki te waehere e whakahaere ana i roto i te pūtirotiro.
Kei konei tō hua tuatahi
Hangaia he tono ki raro nei, ka whakahaere mā tō kī API. Ka tāruatia ngā putanga ki tō mātou rokiroki, ka puritia mō ake tonu atu, mō rānei 7 rā mō te kore utu.
Hangaia he tono
Ka hangaia ngā mana whakahaere mai i te aronuinga o te tauira. Ka whakahoungia te waehere me te utu ina whakarerekē koe.
/run/minimax/h3-max/reference-to-video?wait=20
utu → $ 0.40
# 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-max/reference-to-video?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"prompt_expansion_mode": "balanced"
}'
# 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 $DOITONG_API_KEY"
const API = "https://vit.doitong.com/api/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/minimax/h3-max/reference-to-video?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"prompt_expansion_mode": "balanced"
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://vit.doitong.com/api/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"prompt_expansion_mode": "balanced",
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/minimax/h3-max/reference-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-max/reference-to-video",
"input": {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"prompt_expansion_mode": "balanced"
},
"wait_seconds": 20
}
}
}
Whakahaerehia tēnei tono
Ka noho tō kī ki tēnei pūtirotiro: ka tukuna ki te Doitong API anake, ā, ka tiakina ki te localStorage anake ina tohua e koe te Mahara. Tikina he kī API
Mō H3 Max Reference to Video
Ka hanga ataata mā ngā rawa tohutoro: tae atu ki te 9 whakaahua, 3 ataata me te 3 topenga oro, me te 12 kōnae te tapeke mōrahi. Ka tohu te tono ki a rātou ko Image 1, Video 1, Audio 1 me ērā atu. Mā ngā anga tuatahi, waenga (`middle_image_url` i `middle_frame_time`) me whakamutunga kōwhiringa e titi te tīmatanga, te wā waenga me te mutunga. Ko `duration` mai i te 0.92 ki te 15 hēkona, ā, ka taea te urutau o `aspect_ratio`.
Ngā tawhā
Tukuna te ingoa tōmua, te ingoa taketake rānei, kaua e rua. Ngā ingoa tōmua
prompte hiahiatia ana
reference_image_urlskōwhiringa
images
reference_video_urlskōwhiringa
reference_audio_urlskōwhiringa
image_urlkōwhiringa
image
middle_image_urlkōwhiringa
middle_frame_timekōwhiringa
end_image_urlkōwhiringa
end_image
durationkōwhiringa
resolutionkōwhiringa
seedkōwhiringa
enable_safety_checkerkōwhiringa
prompt_expansion_modee hiahiatia ana
aspect_ratiokōwhiringa
reference_conditionskōwhiringa
reference_conditions[].typee hiahiatia ana
reference_conditions[].urle hiahiatia ana
Mō ngā tawhā kōnae, whakamahia he URL tūmatanui https://, he URI data: tae atu ki te 10 MB, he file_url rānei o tētahi tukuake. Ngā kōnae
Putanga
{
"id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
"object": "request",
"model": "minimax/h3-max/reference-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": 400,
"usd": "0.40",
"charged": 400,
"refunded": 0
},
"input": {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"prompt_expansion_mode": "balanced"
},
"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",
"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://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
"cancel": "https://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
}
}
Ngā āpure o te putanga
- video
- object {url, content_type, file_name, file_size}Te ataata i hangaia e te tauira.
- expanded_prompt
- string | nullHe tohutohu kua whakawhānuitia, kua rite mō te tauira, he null rānei mēnā kāore he kuputuhi whakawhānui. Ko ngā take null ko te whakawhānui kua mono, te whakawhānui kāore i panoni, me te whakawhānui i whakahaere ā-roto e te API manaaki a te tauira.
- seed
- integerTe kākano pūtake hei whakaputa anō i te hua whakaputaina.
- timings
- object | nullNgā inenga wā i whakaaturia ki ngā hēkona, ka wātea anake ki ngā ara e tuku ana i ngā wā backend; ki te kore, he null. Mā te urunga 'inference' e ine te roa o te denoising DiT i runga i te backend GPU.
Ētahi atu rerekētanga Hailuo 03 New Turbo
Ētahi atu tauira: Tohutoro ki te Ataata
Mō ngā āpiha AI: kei te wātea tēnei whārangi hei Markdown ki https://doitong.com/mi/developers/models/minimax/h3-max/reference-to-video.md. Ngā tauira me ngā aratohu katoa: https://doitong.com/developers/llms.txt