Wan-2.1 LoRA Trainer · T2V

Unganisha

Kitambulisho cha modeli wan-trainer/t2v

# 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/wan-trainer/t2v?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "training_data_url": "https://example.com/your-file.zip"
  }'

# 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/wan-trainer/t2v?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "training_data_url": "https://example.com/your-file.zip"
  }),
});
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 = {
    "training_data_url": "https://example.com/your-file.zip",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/wan-trainer/t2v", 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/sw/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": "wan-trainer/t2v",
  "input": {
    "training_data_url": "https://example.com/your-file.zip"
  }
}

Piga modeli ya Wan-2.1 LoRA Trainer · T2V (wan-trainer/t2v) kupitia Doitong API. Nyaraka za mawakala: https://doitong.com/sw/developers/models/wan-trainer/t2v.md

POST https://api.doitong.ru/v1/run/wan-trainer/t2v?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json

{
  "training_data_url": "https://example.com/your-file.zip"
}

Ikiwa hali ya jibu ni "queued" au "running", piga GET https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20 mara kwa mara hadi iwe "succeeded"; faili ziko kwenye outputs[].url. POST https://api.doitong.ru/v1/quote/wan-trainer/t2v yenye mwili uleule hurejesha bei kamili kabla ya kuendesha.

Ombi hili: $ 2.00 salio za API 2,000 · ≈ ₽ 210.93 Iendeshe kwenye ukurasa huu

Pata ufunguo wa API

Alibaba Mafunzo #lora#training

Kifunzaji cha LoRA cha modeli ndogo ya Wan 2.1 text-to-video 1.3B, kutoka kwenye zipu ya picha au video

OpenAPI Markdown

Imetengenezwa kwenye Doitong

Kazi za umma zilizotengenezwa kwa Wan-2.1 LoRA Trainer na jumuiya ya Doitong. Tumia tena kidokezo kwa kubofya mara moja.

Kazi za umma zilizoonyeshwa: 2

Unda ombi

Vidhibiti vinazalishwa kutoka kwenye schema ya modeli. Msimbo na bei husasishwa unapovibadilisha.

training_data_url •inahitajika

URL ya kumbukumbu ya ZIP ya mafunzo kwa picha zenye mtindo thabiti, ikiweza kujumuisha faili za maandishi ya manukuu zilizopewa majina yanayolingana na faili zao za picha au video. Lenga kujumuisha angalau picha 10, video, au mchanganyiko wa zote mbili, huku mikusanyiko mikubwa ikipendelewa.

number_of_steps chaguomsingi 400

Jumla ya idadi ya hatua za mafunzo.

Ya kina trigger_phrase · learning_rate · auto_scale_input

trigger_phrase chaguomsingi

Kauli inayochochea modeli kutoa picha.

learning_rate chaguomsingi 0.0002

Mpangilio wa learning rate: mafunzo yanaweza kuwa ya haraka zaidi lakini yana hatari ya overfitting kiwango kinapoongezwa.

POST /run/wan-trainer/t2v?wait=20 makadirio → $ 2.00

# 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/wan-trainer/t2v?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "training_data_url": "https://example.com/your-file.zip"
  }'

# 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/wan-trainer/t2v?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "training_data_url": "https://example.com/your-file.zip"
  }),
});
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 = {
    "training_data_url": "https://example.com/your-file.zip",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/wan-trainer/t2v", 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": "wan-trainer/t2v",
      "input": {
        "training_data_url": "https://example.com/your-file.zip"
      },
      "wait_seconds": 20
    }
  }
}

Endesha ombi hili

Ufunguo wa API

Key yako inabaki kwenye kivinjari hiki: inatumwa kwa Doitong API pekee na kuhifadhiwa (localStorage) tu ukiweka tiki kwenye Kumbuka. Kumbuka katika kivinjari hiki Pata ufunguo wa API

Kuhusu Wan-2.1 LoRA Trainer · T2V

Hufunza LoRA ya Wan 2.1 text-to-video 1.3B kutoka kwenye jalada la zip kwenye `training_data_url`, ambalo linaweza kujumuisha maelezo kama faili za maandishi. Weka `number_of_steps` kati ya 100 na 20000 na rekebisha `learning_rate`. `trigger_phrase` ni ya hiari, na `auto_scale_input` hubadilisha video kuwa fremu 81 kwa 16fps. Hurejesha uzito wa LoRA na faili ya usanidi.

Vigezo

JinaAina ChaguomsingiInaruhusiwa Maelezo

training_data_urlinahitajika

Ainastring

number_of_stepssi lazima

Ainainteger

Chaguomsingi400

100 – 20,000

Jumla ya idadi ya hatua za mafunzo.

learning_ratesi lazima

Ainanumber

Chaguomsingi0.0002

0.000001 – 1

Mpangilio wa learning rate: mafunzo yanaweza kuwa ya haraka zaidi lakini yana hatari ya overfitting kiwango kinapoongezwa.

trigger_phrasesi lazima

Ainastring

Chaguomsingi

Kauli inayochochea modeli kutoa picha.

auto_scale_inputsi lazima

Ainaboolean

Chaguomsingifalse

Iwapo video ya ingizo irekebishwe kiotomatiki: true huweka urefu wake kuwa fremu 81 na kasi yake ya fremu kuwa 16 fps.

inahitajika

Tokeo

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t

{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "wan-trainer/t2v",
  "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": 2000,
    "usd": "2.00",
    "charged": 2000,
    "refunded": 0
  },
  "input": {
    "training_data_url": "https://example.com/your-file.zip"
  },
  "output": {
    "lora_file": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "config_file": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "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"
  }
}

Faili zako, chaguo lakoKila outputs[].url ni nakala kwenye hifadhi yetu: huhifadhiwa milele (hutozwa kwa GB kwa mwezi) au 7 siku bila malipo, kulingana na mpangilio wa akaunti yako au ?storage=.

Muundo uleule kwenye kila modelitype, url, content_type, width, height na duration, kwa picha, video na sauti. output ni kitu cha matokeo cha modeli yenyewe.

Sehemu za tokeo

lora_file: object {url, content_type, file_name, file_size}URL inayoelekeza kwenye uzito wa LoRA uliotolewa na mafunzo.
config_file: object {url, content_type, file_name, file_size}Usanidi wa kuanzisha endpoint za inference.

Miundo zaidi: Mafunzo

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/wan-trainer/t2v.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt

Imetengenezwa kwenye Doitong

Unda ombi

Endesha ombi hili

Kuhusu Wan-2.1 LoRA Trainer · T2V

Vigezo

Tokeo

Tofauti nyingine za Wan-2.1 LoRA Trainer

Wan-2.1 LoRA Trainer · I2V 720p Tofauti: 3

Wan-2.1 LoRA Trainer · T2V 14b Tofauti: 3

Miundo zaidi: Mafunzo

Qwen Image 2512 Trainer

Qwen Image Edit 2509 Trainer

Wan 2.2 14B Image Trainer

Wan-2.2 LoRA Trainer · I2V A14b Tofauti: 2