TRELLIS.2 Trainer

Unganisha

Kitambulisho cha modeli trellis-2-lora-trainer

# 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/trellis-2-lora-trainer?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "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/trellis-2-lora-trainer?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "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 = {
    "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/trellis-2-lora-trainer", 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": "trellis-2-lora-trainer",
  "input": {
    "data_url": "https://example.com/your-file.zip"
  }
}

Piga modeli ya TRELLIS.2 Trainer (trellis-2-lora-trainer) kupitia Doitong API. Nyaraka za mawakala: https://doitong.com/sw/developers/models/trellis-2-lora-trainer.md

POST https://api.doitong.ru/v1/run/trellis-2-lora-trainer?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json

{
  "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/trellis-2-lora-trainer yenye mwili uleule hurejesha bei kamili kabla ya kuendesha.

Faili kama mfano: $ 15.973 salio za API 15,973 · ≈ ₽ 1,684.56 faili zako hupimwa kabla ya kuendesha Iendeshe kwenye ukurasa huu

Pata ufunguo wa API

Microsoft Mafunzo

Hufunza adapta za LoRA za Trellis 2 kwenye zip ya rasilimali za 3D, kwa hadi viondoa kelele vitatu

OpenAPI Markdown

Microsoft · Faili

Tokeo lako la kwanza linaonekana hapa

Unda ombi hapa chini na uliendeshe kwa ufunguo wako wa API. Matokeo yanakiliwa kwenye hifadhi yetu, yakihifadhiwa milele au 7 siku bila malipo.

Unda ombi

Bei kwa kila uendeshaji

Bei kulingana na uingizaji wako

$ 15.973kwa utekelezaji

salio za API 15,973 · ≈ ₽ 1,684.56

Bei: kuanzia $ 1.751

utekelezaji 1 × $ 15.9723 Endesha · $ 15.973

Hutozwa tu ikifanikiwa, na kurejeshewa kiotomatiki ikishindwa.

resolution chaguomsingi 512

rank chaguomsingi 32

training_steps chaguomsingi 1000

Faili zako hupimwa kabla ya kuendeshwa (urefu, mwonekano, kasi ya fremu); makadirio hurejesha bei kamili na uendeshaji hutozwa kiasi hicho hicho.

Endpoint ya makadirio: POST /quote/{id}

Unda ombi

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

resolution chaguomsingi 512

Mwonekano wa mafunzo lazima uwe sawa na mwonekano wa uchakataji wa awali wa dataset. Mafunzo ya geometry na texture yana usanidi tofauti kwa 512 na 1024, ilhali mafunzo ya sparse-structure hushiriki usanidi katika miwonekano hii.

rank chaguomsingi 32

Rank ya adapta ya LoRA; thamani kubwa hutoa uwezo mkubwa zaidi wa adapta.

data_url •inahitajika

URL ya hifadhi ya dataset: toa mali ghafi za 3D zilizofungwa kama .zip, au tumia zip ya dataset ya TRELLIS.2 iliyochakatwa awali na kurejeshwa na data_preprocessing.

training_steps chaguomsingi 1000

Jumla ya idadi ya hatua za mafunzo.

denoisers

Uteuzi wa denoiser 1–3 tofauti za TRELLIS.2 kutoka sparse_structure, geometry na texture kwa fine-tuning. Mafunzo sambamba hutumia dataset moja iliyochakatwa awali ili kutoa adapta tofauti ya LoRA kwa kila ingizo lililochaguliwa.

Ya kina learning_rate

learning_rate chaguomsingi 0.0001

Kasi ya ujifunzaji inayotumika kuboresha LoRA.

POST /run/trellis-2-lora-trainer?wait=20 makadirio → $ 15.973

# 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/trellis-2-lora-trainer?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "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/trellis-2-lora-trainer?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "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 = {
    "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/trellis-2-lora-trainer", 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": "trellis-2-lora-trainer",
      "input": {
        "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 TRELLIS.2 Trainer

Huboresha adapta kutoka zip iliyo kwenye `data_url`, yenye vipengee mbichi vya 3D au dataset iliyochakatwa awali. `denoisers` huchagua malengo 1 hadi 3, kila moja ikifunzwa kama adapta yake. Mipangilio: `resolution` 512 au 1024, `rank` 16, 32 au 64, `learning_rate`, na `training_steps` kutoka 100 hadi 10000. Hurudisha adapta, hitilafu zozote na data iliyochakatwa awali inayoweza kutumiwa tena.

Vigezo

JinaAina ChaguomsingiInaruhusiwa Maelezo

data_urlinahitajika

Ainastring

URL ya hifadhi ya dataset: toa mali ghafi za 3D zilizofungwa kama .zip, au tumia zip ya dataset ya TRELLIS.2 iliyochakatwa awali na kurejeshwa na data_preprocessing.

denoiserssi lazima

Ainaenum[]

≤ vipengee 3

resolutionsi lazima

Ainaenum

Chaguomsingi512

5121024

ranksi lazima

Ainaenum

Chaguomsingi32

163264

Rank ya adapta ya LoRA; thamani kubwa hutoa uwezo mkubwa zaidi wa adapta.

learning_ratesi lazima

Ainanumber

Chaguomsingi0.0001

0.000001 – 0.01

Kasi ya ujifunzaji inayotumika kuboresha LoRA.

training_stepssi lazima

Ainainteger

Chaguomsingi1000

100 – 10,000

Jumla ya idadi ya hatua za mafunzo.

inahitajika

Tokeo

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t

{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "trellis-2-lora-trainer",
  "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": 15973,
    "usd": "15.973",
    "charged": 15973,
    "refunded": 0
  },
  "input": {
    "data_url": "https://example.com/your-file.zip"
  },
  "output": {
    "adapters": [
      {
        "denoiser": "sparse_structure",
        "resolution": 1,
        "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
        },
        "rank": 1,
        "training_steps": 1,
        "learning_rate": 1.0
      }
    ],
    "failed": [
      {
        "denoiser": "sparse_structure",
        "error": "string"
      }
    ],
    "preprocessed_data_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

adapters: array of object {denoiser, resolution, lora_file, rank, training_steps, learning_rate}Faili za adapta za LoRA zilizopangwa kwa sehemu za inference zinazolingana za trellis-2-lora. Jibu linajumuisha adapta moja kwa kila denoiser ambayo mafunzo yake yalifaulu; tumia faili yake katika sehemu inayolingana.
failed: array of object {denoiser, error}Matokeo ya mafunzo ya denoiser yasiyofaulu; denoiser zilizoshindwa kumaliza mafunzo pekee ndizo huonekana hapa, hivyo mafanikio kwa denoiser zote zilizoombwa huacha sehemu hii tupu.
preprocessed_data_file: object {url, content_type, file_name, file_size}Zip ya dataset ya TRELLIS.2 iliyochakatwa awali, iliyotumika wakati wa mafunzo na inayopatikana kwa matumizi tena.

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/trellis-2-lora-trainer.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt

Tokeo lako la kwanza linaonekana hapa

Unda ombi

Endesha ombi hili

Kuhusu TRELLIS.2 Trainer

Vigezo

Tokeo

Miundo zaidi: Mafunzo

ERNIE-Image Trainer

FLUX 2 [klein] 9b Base Trainer Tofauti: 2

Flux 2 Klein 9B Base Trainer Tofauti: 2

FLUX 2 Trainer Tofauti: 2